The Mobile & Digital Assistant Blog covers the latest in mobile and conversational AI development and engagement

Article by Kadday Oucif, January 2020 Being able to integrate Oracle Digital Assistant with the Oracle Database is a frequently asked topic addressed in this article. In a very informative way and in great detail, this article steps you through the creation of a Oracle Autonomous Transaction Processing (ATP) database cloud instance and the creation of database REST services that allow CRUD access to data stored in the database. In a second step, the article then looks into how to create a custom Oracle Digital Assistant component that accesses the ORDS Rest service within a chatbot conversation.  Following the instructions in this article, and downloading the sample skill built for it, you will obtain a working sample that integrates Oracle Rest Data Services in Oracle Digital Assistant chatbot conversations. This article is also suited for developers that are new to Oracle Digital Assistant because each part of the hands-on outlines background  information that teach dialog flows, custom component development and conversation testing.  READ ARTICLE (PDF) Download Sample Skill (ZIP) Related Content TechExchange: All 2-Minutes Oracle Digital Assistant Tech Tip Videos on YouTube TechExchange Quick-Tip: Follow Best Practices By Keeping External Configurations Out of Your Dialog Flow TechExchange: The various options for creating and working with mockup data in Oracle Digital Assistant

Article by Kadday Oucif, January 2020 Being able to integrate Oracle Digital Assistant with the Oracle Database is a frequently asked topic addressed in this article. In a very informative way and in...

article by Frank Nimphius, January 2020 Oracle Digital Assistant is a cloud service on Oracle Cloud Infrastructure (OCI). To provision and administer Oracle Digital Assistant instances, you use the browser based OCI administration console. This article describes the minimum steps required to subscribe to a free Oracle Cloud trial and to setup an Oracle Digital Assistant instance. Once you have access to Oracle Digital Assistant, I recommend you try one of the hands-on tutorials provided here: https://docs.oracle.com/en/cloud/paas/digital-assistant/tutorials.html    READ article and get started (PDF) ------------ Related Content: Oracle Digital Assistant Product Documentation Oracle Digital Assistant help forum Oracle Cloud Infrastructure documentation Oracle TechExchange content related to the OCI version of Oracle Digital Assistant TechExchange: Mastering Dynamic Entities in Oracle Digital Assistant TechExchange Quick-Tip: Using RAW Message Payloads in Custom Components to Leverage Channel Specific UI Extensions (MS TEAMS Example) TechExchange - QuickTip: Oracle Digital Assistant As an Agent Overview of the new Oracle Web SDK and its customization features in Oracle Digital Assistant 19.10 and later TechExchange: How to Build a Remote JWT Token Server in Node for Use With Oracle Web SDK Client Authentication

article by Frank Nimphius, January 2020 Oracle Digital Assistant is a cloud service on Oracle Cloud Infrastructure (OCI). To provision and administer Oracle Digital Assistant instances, you use the...

As we close out an awesome 2019, we’d like to celebrate with the launch of our 19.12 ODA Platform release. This release coincides with our full transition into being an OCI Native Service.  A) Oracle Voice:  Oracle Voice is now generally available to all our customers and partners as a key feature within the ODA platform. With Oracle Voice, customers can use cutting-edge automatic speech recognition that is pre-built with enterprise vocabulary. Additionally, customers can do this end-to-end within the ODA Platform without having to worry about using external transcription APIs.    B) Oracle Native SDKs: When it comes to incorporating digital assistants in various client environments, we strongly believe one size doesn’t fit all. After working with several customers to understand different usage models for ODA client SDKs, we have released the GA versions of our Oracle Web SDK and Oracle Android SDK -- both enabled with Oracle Voice. The Oracle Web SDK also features Auto Complete suggestions to better guide the users. Additionally we'll soon be releasing several derivatives of the Web SDK such as the Hybrid SDK for Cordova-based mobile development, a headless Web SDK for customers who want to create a chat UI from scratch, and a VBCS Web Component for developers who would like to embed an ODA channel within their VBCS/JET web applications.   C) Scenario validation with Test Suite: Our customers have long used the Bot Tester to verify how their Skills are performing in various scenarios. Now they can save these scenarios as test cases and validate them before making any major changes in their Skills. Each test case can be customized through UI or in JSON, and can be enhanced by passing in dynamic variables.   As we complete our transition into a full OCI Native service, we have brought in other exciting features into this native version of the platform such as enhancements to our Service Cloud DA-as-Agent channels, Q&A Intents, Optimized NLU models, etc. We hope you’re able to get the maximum value from the above capabilities in the coming months.

As we close out an awesome 2019, we’d like to celebrate with the launch of our 19.12 ODA Platform release. This release coincides with our full transition into being an OCI Native Service.  A) Oracle...

Connectors in Oracle Digital Assistant ensure that the bot response is rendered best for different messengers. The foundation of this rendering is the conversation message model (CMM) that is the metadata used by Oracle Digital Assistant built-in components to define the bot user interface. The metadata is then transformed by connectors to the format expected by messengers like Facebook, Slack, MS Teams and many more. Custom components integrate with CMM through the MessageModel class in the Oracle custom component SDK.  Like when using the System.CommonResponse component channelCustomProperties component (as explained in another Oracle TechExchange article), you can return a message payload from custom components that are messenger specific and that allow you to use layout extensions available on a specific messenger channel. By doing so, you bypass the payload format transformation in the channel connectors and instead post the payload "as is" to the messenger client.  In this article, I explain how you use the MessageModel's RAW message format to send a channel specific layout. The example used is Microsoft Teams' adaptive card layout. 

Connectors in Oracle Digital Assistant ensure that the bot response is rendered best for different messengers. The foundation of this rendering is the conversation message model (CMM) that is the...

Messengers differ in the layout they support. The Oracle Digital Assistant connector architecture renders the best possible bot response for a connected client based on its internal metadata (CMM). With the connector architecture, a skill that renders a rich card layout on Facebook would render a list of text messages on SMS without the user needing to code for it. Still, a messenger platform like Microsoft Teams, Facebook or Slack may provide functionality that is not created by the connector architecture. The System.CommonResponse component has a property called "channelCustomProperties" that you can use to implement channel specific layout properties. This way you can optimize the Oracle Digital Assistant generated bot response for specific channels. This article explains the channelCustomProperties property by example of adaptive cards in the Microsoft Teams channel.

Messengers differ in the layout they support. The Oracle Digital Assistant connector architecture renders the best possible bot response for a connected client based on its internal metadata (CMM)....

When you are using a digital assistant, user input is routed to the most appropriate skill automatically by the digital assistant.  But what if you want to pre-process the user input?  For example, you mind find extraneous punctuation such as an exclamation mark which impacts the intent resolution so you want to strip it out before the System.Intent.  Or maybe you want to force a particular behavior by altering or augmenting the original user input in order to slightly skew the intent resolution.

When you are using a digital assistant, user input is routed to the most appropriate skill automatically by the digital assistant.  But what if you want to pre-process the user input?  For example,...

Users fail because the design fails. Conversational design skills are an important asset for any bot developer, regardless of the development platform used. With chatbots you always build for two types of users: 1. new users that use a bot for the first time 2. expert users that did use the bot before This article explains a solution that allows experienced users to skip a dialog in a bot-user interaction

Users fail because the design fails. Conversational design skills are an important asset for any bot developer, regardless of the development platform used. With chatbots you always build for...

Dynamic entities are value list entities for which you create, modify and delete values at runtime using Oracle Dynamic Entities REST APIs. Dynamic entities, like other entities, can be used with NLP entity extraction to find information in user messages or to validate user input against a known set of values and synonyms. Use cases for dynamic entities are value lists that frequently change due to underlying data changes and include product catalogs, food menus, departments, events and event locations, flight tables and many more. There is no known lower limit for the frequency of changes, though given that any change to the list data in a dynamic entity is followed by a model training, you want to keep the frequency of change reasonable. This article introduces and explains dynamic entities in Oracle Digital Assistant version 19.10 and later. 

Dynamic entities are value list entities for which you create, modify and delete values at runtime using Oracle Dynamic Entities REST APIs. Dynamic entities, like other entities, can be used with NLP...

By default, Oracle Digital Assistant (ODA) supports the integration of human agents into bot conversations through the Oracle Service Cloud (OSC).  A new open source project that extends the existing integration to third-party agent systems has now been released to GitHub by Tamer Qumhieh. The project leverages ODA out of the box features integrating with Oracle Service Cloud to different agent systems. With this, you will be able to use the out of the box System.AgentInitiation and System.AgentConversation components; hence your skill is totally abstracted from back-end agent system details.

By default, Oracle Digital Assistant (ODA) supports the integration of human agents into bot conversations through the Oracle Service Cloud (OSC).  A new open source project that extends the existing...

Oracle Digital Assistant lets you to integrate with the Oracle Service Cloud Chat Service in two ways: DA as an Oracle Service Cloud agent lets you turn a digital assistant into an automated agent that participates in Oracle Service Cloud chats in much the same what that live agents do. All conversations take place in an Oracle Service Cloud Live Help chat window regardless of whether the agent is a human agent or a digital assistant. Live-agent transfer enables you to hand off a skill's conversation to an Oracle Service Cloud live agent. With this feature, you can enhance your skill to handle user tasks that require human intervention by transferring the conversation to a live agent. The conversation continues in the same user channel that the customer used to invoke the skill. In this article, I explain DA as an Oracle Service Cloud agent, which is a new feature in Oracle Digital Assistant 19.4.1, in more detail. You can read up about both implementations in the Oracle Digital Assistant product documentation:

Oracle Digital Assistant lets you to integrate with the Oracle Service Cloud Chat Service in two ways: DA as an Oracle Service Cloud agent lets you turn a digital assistant into an automated agent...

With Oracle Digital Assistant 19.10 and later, Oracle provides a new Web SDK, the Oracle Web SDK, for integrating Oracle Digital Assistant to Web applications and web sites. This article will guide you through the steps required to integrate the Oracle Digital Assistant web SDK in a Visual Builder Cloud Service (VBCS) project.

With Oracle Digital Assistant 19.10 and later, Oracle provides a new Web SDK, the Oracle Web SDK, for integrating Oracle Digital Assistant to Web applications and web sites. This article will guide...

Microsoft teams and other channels, e.g. Slack, do not have the same mechanism for accessing user profile information like e.g. the Oracle Web SDKs has. The reason for this is that, when using MS Teams, the user is already identified by the Microsoft platform. However, it is a common requirement that bots can access user information such as the user's first and last name. For you to access user profile information in MS Teams you need to call a protected Microsoft REST endpoint from within your bot (using a custom component). This article walks you through the steps to retrieve user profile information - MS Team Name, First Name, and Email ID. The examples use Postman for accessing the MS Teams API and a custom component for accessing the conversation identifier.

Microsoft teams and other channels, e.g. Slack, do not have the same mechanism for accessing user profile information like e.g. the Oracle Web SDKs has. The reason for this is that, when using...

Oracle Digital Assistant analyzes user messages to identify intents and to extract information. This article explains 4 options you can use to find and extract information from user messages sent to skills in Digital Assistant. 

Oracle Digital Assistant analyzes user messages to identify intents and to extract information. This article explains 4 options you can use to find and extract information from user messages sent...

​​​​​​​There are entity use cases in which a particular bot user only needs a subset of the values that could be extracted by an entity. However, there is a good reason to train the bot with all possible entity values and not just those of interest to the user. The following is a use case from one of our internal teams which is a common enough use case worth sharing with the wider community: that an entity value can be further validated against a dynamic subset of values based on, in this case, the current user.

​​​​​​​There are entity use cases in which a particular bot user only needs a subset of the values that could be extracted by an entity. However, there is a good reason to train the bot with...

In Oracle Digital Assistant version 19.10 (Oracle Digital Assistant for Oracle SaaS) and later, a new Oracle Web SDK integrates Oracle Digital Assistant with web applications and web pages. In addition to its extensive functionality, the Oracle Web SDK supports client security through domain whitelisting and signed JSON Web Token (JWT). Once JWT client security is enabled for an Oracle Web channel, all messages to the web channel require a signed and valid token to be processed by the associated digital assistant. This article explains how to create a JWT token for use with the Oracle Web SDK messenger. The provided sample follows the recommended security practice, which is to generate the token on a remote server and not in the browser application itself.  

In Oracle Digital Assistant version 19.10 (Oracle Digital Assistant for Oracle SaaS) and later, a new Oracle Web SDK integrates Oracle Digital Assistant with web applications and web pages. In...

Starting Oracle Digital Assistant 19.4.1, you have two options to handle questions in a bot conversation.  QnA Module - the QnA module in Oracle Digital Assistant allows you to upload frequently asked question documents that consist of one or many questions associated with a single answer. The QnA module uses elastic search to find the best matching answer or answers to a question. Dependent on how you configure the QnA module routing, bot users may get multiple hits for a question. Multiple possible answers to a question are shown in a carousel layout for the user to browse and select the answer she feels is the most relevant.  QnA modules are referenced from the System.QnA component that you add to a state in the skill dialog flow. The decision whether or not QnA is called, is then made by the intent engine through the System.Intent component. Again, depending on your configuration settings, the QnA module can be queried parallel to the intent model or only if the intent model does not resolve an intent for the user message.  QnA intent - The new QnA intent allows you to return a defined an answer for a resolved intent. Intents that have a response defined will not be resolved by the System.Intent component, which means there is no need for you to create a dialog flow state to return the response. QnA intents are kind of a "QnA light" in that they don't require any dialog flow settings and in that they only return a single answer, which sometimes is a customer requirement. The QnA intent is documented in the ODA product documentation.  This article provides a quick tutorial for you to try the new QnA intent. I assume you have access to Oracle Digital Assistant 19.4.1 or later and also assume you understand how to import skills using the Oracle Digital Assistant skill dashboard. 

Starting Oracle Digital Assistant 19.4.1, you have two options to handle questions in a bot conversation.  QnA Module - the QnA module in Oracle Digital Assistant allows you to upload frequently asked...

User scope variables in Oracle Digital Assistant keep their values beyond conversation sessions. So if, in the context of a conversation, the bot needs to memorize information, then this information should be saved in a user scope variable. User scope variables are defined at runtime, and not at design time. The variables are saved in the instance specific Oracle Digital Assistant internal database. User scope variables cannot be shared between users and also are messenger specific. This means that a user who runs the same bot on two different messaging channels will save information twice. As far as the content goes that can be saved in a user scope variable, the same types apply as can be used with variables defined in a dialog flow. To create user scope variables and to store values, you can use the System.SetVariable component or a custom components. To read from user scope variables, you use an expression the dialog flow or a custom component.  This article explains how to work with user scope variables in a dialog flow. 

User scope variables in Oracle Digital Assistant keep their values beyond conversation sessions. So if, in the context of a conversation, the bot needs to memorize information, then this information...

In Oracle Digital Assistant 19.10 and later, Oracle provides a new web SDK for integrating Oracle Digital Assistant to web applications and web sites. The new Oracle Web SDK provides the features available in the current version of the Oracle JS Client SDK, but then goes beyond in providing new messenger functionalities as well as client security. This article explores customization features of the new Oracle Web SDK that you can download for Oracle Digital Assistant 19.10 and later from https://www.oracle.com/downloads/cloud/amce-downloads.html (see Oracle Web SDK v1.0). The download contains a developer guide in its readme that explains all properties you can use with the new Web SDK. 

In Oracle Digital Assistant 19.10 and later, Oracle provides a new web SDK for integrating Oracle Digital Assistant to web applications and web sites. The new Oracle Web SDK provides the features...

We are excited to announce the 19.4.1 version of the Oracle Digital Assistant platform with a host of cool features and capabilities. I’d like to thank all our valued customers and partners who worked with us to deliver these innovations: A) Q&A Intents + optimized ML model: To streamline integration of Q&A with transactional intents, 19.4.1 comes with Q&A Intents. These intents are similar to transactional intents, except that you can specify answers when you define them. These answers do not require any further dialog or YAML changes, and hence are easily configurable by business analysts. We have also updated the Trainer Tm model to ensure it can work effectively with lots of Q&A Intents — to leverage this, you simply have to enable "Optimize for Answer Intents" option for Trainer Tm model under settings. B) DA as Agent channels:  Customers have often appreciated the breadth of channels the ODA Platform provides. Now for customers who already have an existing contact center pre-configured with Oracle Service Cloud and channels such as Live Chat, they can simply add ODA on to their contact center  with the new "DA as Agent" channel.  This is as simple as say hiring a new agent — the ODA plugs into your Service Cloud backend as a new agent, and is able to honor all the complex routing strategies that you may have implemented in Service Cloud for your contact center. C) Service Cloud optimized insights: For business analysts, 19.4.1 comes with a streamlined view of deflection and usage-based insights. You can view popular intents through word clouds and retrain your skills with a single click.  D) Conversation Designer Update: Thanks again for all the feedback you provided for the Conversation Designer Beta. We have now rolled most of the feedback and fixes into the Conversation Designer Update. Additionally 19.4.1 comes with entity highlighting in user queries and ODA responses within the Conversation Designer.  Overall the 19.4.1 release improves the stability of the platform and provides significant new functionality. We strongly recommend all our existing customers to upgrade to this release. Over the next 3-4 weeks, we will reach out to you on the upgrade plan for 19.4.1. Meanwhile, if you have any questions about upgrades, please reach out to your customer success PM.

We are excited to announce the 19.4.1 version of the Oracle Digital Assistant platform with a host of cool features and capabilities. I’d like to thank all our valued customers and partners who worked...

Oracle Digital Assistant uses system intents to provide common functionality. Initially, system intents existed for help, unresolved intents and to exit a conversation. The default help implementation for the system help intent displays the configured skills along with sample utterances for users to learn about the options. This article explains how you can

Oracle Digital Assistant uses system intents to provide common functionality. Initially, system intents existed for help, unresolved intents and to exit a conversation. The default help implementation...

As of Oracle Digital Assistant 19.4.1, the local deployment of custom components has changed to the point that custom component tar balls (".tgz" files) must now contain all node module dependencies. This change addresses the new Acceptable Use of the Public Registry announcement by NPM , Inc.

As of Oracle Digital Assistant 19.4.1, the local deployment of custom components has changed to the point that custom component tar balls (".tgz" files) must now contain all node module dependencies....

Using multi select lists are common user interface widgets in mobile and web application development. In conversations, graphical multi select lists are difficult to create because users not only would need to select values, they also would need to click on a button to progress to a next dialog flow state. Here, form based use cases as in web and mobile are much better suited for the use of multi select lists.  Still, multi value selects is an options available in Oracle Digital Assistant. This article explains how to create multi select lists in Oracle Digital Assistant skills. 

Using multi select lists are common user interface widgets in mobile and web application development. In conversations, graphical multi select lists are difficult to create because users not...

Oracle Digital Assistant supports OAuth2 authorization through the built-in System.OAuthAccountLink component. You use the System.OAuthAccountLink component to get an authorization token, which you then exchange for an access token in a custom component call to the OAuth2 token endpoint, so that subsequent custom component calls can access protected REST resources. This article explains how to authorize custom component requests for OAuth2 protected resources using Facebook as an example. Facebook supports OAuth2 and allows a bot to access user profile information if authorized by the user.

Oracle Digital Assistant supports OAuth2 authorization through the built-in System.OAuthAccountLink component. You use the System.OAuthAccountLink component to get an authorization token, which you...

Oracle Digital Assistant orchestrates individual chatbots (skills) to a unified chatbot experience. In this architecture, skills are individual chatbots that represent modular building blocks and perform a specific task or set of tasks. The role of the digital assistant is to "host" skills and intelligently route user messages to the skills and intents that fit the best.  Although skills are independent chatbots, they may need to exchange information when executed in the context of a digital assistant. A usecase e.g. is to share an access token obtained in an authorization skill that then is used in other skills to perform backend service access. This way you don't need to implement the authorization logic in all skills but just one. Another use case is where skills implement related tasks: one skill to perform a banking transaction whereas a second tracks the transaction.  In this article, I'll explain how to use Oracle Digital Assistant user-scope variables to exchange information between skills. I'll also explain how to use custom skill parameters to avoid dependencies in the skill BotML code. The design goals are Skills should not depend on implementation details of other skills Skills should be designed for stand-alone use and not as a dependent detail of a master Information is shared using user scope variables. The name of the user scope variables should be defined by the digital assistant designer, not the skill developer

Oracle Digital Assistant orchestrates individual chatbots (skills) to a unified chatbot experience. In this architecture, skills are individual chatbots that represent modular building blocks...

Oracle today announced availability of its AI-trained voice with Oracle Digital Assistant. “Enterprises are demanding an AI-powered voice assistant that understands their specific vocabulary and enables naturally expressive interactions for its users,” said Suhas Uliyar, vice president, AI and Digital Assistant, Oracle. “Most of all though, enterprises value a highly secure AI-powered voice assistant that stores their businesses sensitive data in Oracle’s second-generation cloud infrastructure.” Read the full announcement here: Oracle Unveils AI-Voice for the Enterprise, and see what Oracle Digital Assistant customers are saying about the value of driving conversational voice and text interactions with Oracle Digital Assistant, the only true enterprise AI-powered digital assistant in the market today. In another significant announcement, Oracle and Microsoft expand on their Cloud partnership with the availability of integration between Microsoft Teams and Oracle Digital Assistant. With this, Microsoft 365 and Oracle Cloud customers can access Oracle Cloud applications using Oracle Digital Assistant – an  AI-powered conversational voice and text interface, directly from within Teams. “Our aim is to have it (Oracle Digital Assistant) be the preferred method to get questions answered 24x7, access to policies and an amazing end-to-end approach for completing transactions with more speed and accuracy. We knew we wanted our HR digital assistant to be available where employees spend their time online, and an integration with Teams was therefore essential. Our vision is to have it become to employees what J.A.R.V.I.S. is to Iron Man.” says Mark Burgess, senior director, HR Technology Solutions, Honeywell. Read the full announcement here: Oracle and Microsoft Expand Cloud Partnership to Boost Workplace Productivity For more information on Oracle Digital Assistant for Teams, enterprises can now sign up for a private preview by sending in a request to oda_teams_ww_grp@oracle.com If you are at OracleOpenWorld, don't miss Oracle executive, Suhas Uliyar's session that goes into details around these announcements and is packed with exciting solution demos. GEN5607 Oracle Speaks: Conversational AI for Enterprise Apps with a Chatbot Assistant Tuesday, September 16, 2019, 1:45 pm -2:30 pm Moscone South, Room 209 More information on Oracle Digital Assistant at Oracle OpenWorld at bit.ly/ODA_OOW19 and join the conversation using #OOW19, #OracleAssistant

Oracle today announced availability of its AI-trained voice with Oracle Digital Assistant. “Enterprises are demanding an AI-powered voice assistant that understands their specific vocabulary and...

This article is hands-on oriented and explains how you can integrate Google Assistant to Oracle Digital Assistant. Sample code is provided for you to get started easily. 

This article is hands-on oriented and explains how you can integrate Google Assistant to Oracle Digital Assistant. Sample code is provided for you to get started easily. 

Oracle OpenWorld 2019 provides a unique opportunity for all of us to learn. Learn about Oracle Cloud services, strategic direction, key trends in the industry, product use cases, and such. But perhaps more than anything else, it provides us an opportunity to learn from our peers – learn from organizations who may be facing similar industry challenges or are guided by similar innovation goals or are looking to drive transformation or deliver/meet unique business needs. This Oracle OpenWorld plan to spend some time learning from your peers. We are very excited to have a slew of sessions featuring customer organizations including, Banco Daycoval, Exelon, FedEx, HSBC, Honeywell, Telefonica SA, Tokyo Gas, University of Adelaide, among others. For convenience, I have curated a list of sessions where you will hear first-hand from Oracle Digital Assistant customers and get to hear about their use cases, business goals, results achieved and best practices that may be of interest to you. Monday, September 16, 2019 PRO5704: Why Chatbots Fail: 10 Common Mistakes Developing a Digital Assistant (Chatbot) 1:15 a.m. - 12:00 p.m. | Moscone West - Room 2024B CON5620: Design Your Own Digital Assistant and Chatbot Conversations 1:45 p.m. - 2:30 p.m. | Moscone South - Room 159A DEV5644: Oracle Digital Assistant Architecture Patterns and Design Practices 6:00 p.m. - 6:45 p.m. | Moscone South - Room 303   Tuesday, September 17, 2019 GEN5607: Oracle Speaks: Conversational AI for Enterprise Apps with a Chatbot Assistant 1:45 p.m. - 2:30 p.m. | Moscone South - Room 209 CON5609: Explore Oracle Digital Assistant Channels, Client SDKs, and Messaging Services 5:15 p.m. - 6:00 p.m. | Moscone South - Room 151B Wednesday, September 18, 2019 GEN6040: Extend Oracle SaaS and Design New Experiences with Intelligent Automation 11:15 a.m. - 12:00 p.m. | Moscone South - Room 207/208 CAS5610: Oracle Digital Assistant Customer Panel 3:45 p.m. - 4:30 p.m. | Moscone South - Room 151B CON5616: Five Crucial Ways Oracle Digital Assistant Will Transform Your Enterprise Applications 4:45 p.m. - 5:30 p.m. | Moscone South - Room 151B You may want to pre-register for some or all of these sessions by adding to your Schedule Builder today. And, do keep bit.ly/ODA_OOW19 handy on your devices so you can look at what’s ahead wherever, whenever. For a snapshot of what to expect, check out my previous blog post. The team is also planning to drive updates via social channels so be sure to join in on the conversation using #OOW19 #OracleAssistant. Oh, and one final tip – you may want to wear some comfortable shoes! See you soon at Oracle OpenWorld!

Oracle OpenWorld 2019 provides a unique opportunity for all of us to learn. Learn about Oracle Cloud services, strategic direction, key trends in the industry, product use cases, and such. But perhaps...

Oracle OpenWorld 2019 is just around the corner. We look forward to seeing you in San Francisco from September 16-19, 2019. Whether you are looking to learn about Oracle’s latest technologies, product roadmaps, customer implementations, get hands-on learning, dive into product demonstrations and/or networking with your peers, we are confident that this year’s conference will not disappoint!  For easier navigation, here we highlight key sessions and activities for all interested in Oracle Digital Assistant. A reminder that you can access the very latest information on upcoming sessions and events for Oracle Digital Assistant by simply going to bit.ly/ODA_OOW19 on your devices before or during Oracle OpenWorld. As always, for the latest information on Oracle Digital Assistant, visit Oracle.com/da Looking Beyond Keynotes GEN5607 Oracle Speaks: Conversational AI for Enterprise Apps with a Chatbot Assistant featuring customer Honeywell Tuesday, September 17, 01:45 PM - 02:30 PM | Moscone South - Room 209 Join Oracle executive, Suhas Uliyar, vice president, Digital Assistant, AI and Integration, live at Oracle OpenWorld  in a General Session like you haven’t seen before! Learn about areas of investments for Oracle Digital Assistant, latest product enhancements and see  chatbot technology live in action. Hear directly from our customer, Honeywell, on how they are seeing quantifiable benefits from use of Oracle Digital Assistant. GEN4060 Extend Oracle SaaS and Design New Experiences with Intelligent Automation featuring customer Ferrari Wednesday, September 18, 11:15 AM - 12:00 PM | Moscone South - Room 207/208 If you are looking to add new capabilities to extend Oracle SaaS applications, or trying to create ways to support new business models, then you would definitely want to make your way to this General Session. Oracle executive, Suhas Uliyar, vice president, Digital Assistant, AI and Integration, is joined on stage by lead executives for the different Oracle Cloud Platform services and our customer, Ferrari, to showcase the power of one Cloud platform. Hear Directly from Digital Assistant Customers One of the biggest benefits of attending Oracle OpenWorld is hearing directly from peers in other organizations about their use cases, how they are driving value with Oracle Cloud services and finding paths to success and innovation. We are very excited to have a slew of sessions featuring customer organizations including, Banco Daycoval, Exelon, FedEx, HSBC, Honeywell, IFFCO, Telefonica SA, Tokyo Gas, University of Adelaide, among others. Partners including AuraPlayer, Avanttic, eProseed, Fishbowl Solutions, IntraSee and Rubicon Red alongside Oracle’s technical experts, would also be at hand, and presenting sessions to support dialogues around best practices and implementations. Browse through our customer-centric sessions listing to add to your Schedule Builder Hands-On-Labs Take Oracle Digital Assistant for a test drive. Get hands-on experience working, building or delivering use cases for a Digital Assistant that fits your business model. See how you can create your own skills to easily converse with Cloud applications. Reserve your spot today for one or both of these hands-on-Labs (seating limited): HOL5639 Compose Digital Assistant for Oracle Applications with SaaS Skills HOL5640 Getting hands on with Oracle Digital Assistant Conversation Designer Demos and Product Showcases Seeing is believing. Experience it live to learn more about how Oracle Digital Assistant can create value for your organization. Don’t miss Oracle Digital Assistant demo stations in demo ground conveniently located on both the technology and applications showcase floors. Access complete list of Digital Assistant demos Blogs and Social Start a conversation or stay up to date with Oracle Digital Assistant happenings, the latest announcements, tracking key activities from Oracle OpenWorld in real time using social channels and hashtags #OOW19, #OracleAssistant. Follow us on: Blogs: Oracle Digital Assistant Twitter: @OracleMobile For more information, visit bit.ly/ODA_OOW19  

Oracle OpenWorld 2019 is just around the corner. We look forward to seeing you in San Francisco from September 16-19, 2019. Whether you are looking to learn about Oracle’s latest technologies,...

This article uses the example of a pasta menu to explain how an Apache FreeMarker expression can be used in a System.CommonResponse component to store selected data objects in a dialog flow variable using in a postback action. It's the Apache FreeMarker expression that you should know about. 

This article uses the example of a pasta menu to explain how an Apache FreeMarker expression can be used in a System.CommonResponse component to store selected data objects in a dialog flow...

Adding webviews to your skill allows it support structured data input through UI elements like forms, date pickers, fields, and LOVs. In Oracle Digital Assistant, the web apps that are delivered within the chat as webviews are single-page apps (SPAs). A new feature added to Oracle Digital Assistant 19.1.5 is the ability to add images to the System.WebView UI

Adding webviews to your skill allows it support structured data input through UI elements like forms, date pickers, fields, and LOVs. In Oracle Digital Assistant, the web apps that are...

When working with real data, objects typically contain more content (attributes) than being displayed on a map or in a list within a bot conversation. Skills in Oracle Digital Assistant obtain access to live data to display through custom components saving the data as an object, or an array of objects into a dialog flow variable. This quick-tip explains how to use the array index of a selected object in a cars or list UI to access the object to read its attributes and data

When working with real data, objects typically contain more content (attributes) than being displayed on a map or in a list within a bot conversation. Skills in Oracle Digital Assistant obtain...

The development of an Oracle Digital Assistant projects, like any other Chatbot project, does not begin with the technology. Instead you start with a planning phase that clearly identifies the bot's usecases, its data requirements, the intents and entities, and the conversation flow. Having a solid agreed-upon idea of what to build and in which increments to build it, as well as getting stake holder buy-in, is an important pre-requisite to a successful bot project. The next step is to identify intents and utterances with which to train the bot. This is easier said than done and you should definitely avoid making them up. Make sure you find realistic data from real customer interactions and derive intentions and expressions from them. Like in mathematics, if the algorithm you use (the model) is wrong, then chances are bad that the end result will be correct nevertheless. So make sure that you identify good intents and utterances before you build a bot. Once you are done and the conditions look good, you can put your ideas into action and create a first model of what your bot could become later. Oracle Digital Assistant got a new Conversation Designer added as a beta feature in September 2019. With the Conversational Designer, you can build skill conversations declaratively so that technical and non-technical people can follow and collaborate. With the modeled conversation, you can then run a recorded simulation of your conversation design, or even generate the Oracle Digital Assistant skill, including intents, entities and the dialog flows, to perform a realistic test and demonstration to show to stake holders,  This article is a quick start that will help you get going easily with the Oracle Digital Assistant Conversation Designer. The tutorial example teaches you about the editing environment, the dialogs, and the code generator.

The development of an Oracle Digital Assistant projects, like any other Chatbot project, does not begin with the technology. Instead you start with a planning phase that clearly identifies the...

This page lists all Oracle Digital Assistant 2-Minute Tech Tip videos recorded for the The Oracle Groundbreakers YouTube channel. In exact 120 seconds, each video provides an expert tip about Oracle Digital Assistant. We will update this blog post on a weekly basis to add new videos as they become available.  For many videos there is an accompanying article or quick-tip here on TechExchange which allows you to download sample codes and skills. 

This page lists all Oracle Digital Assistant 2-Minute Tech Tip videos recorded for the The Oracle Groundbreakers YouTube channel. In exact 120 seconds, each video provides an expert tip about Oracle...

article by Frank Nimphius, August 2019   "textReceived" is an action transition that exist on many Oracle Digital Assistant select components and that is followed when users enter free text instead of selecting a value from a choice. For example, in a retail bot, if the user is prompted to select the size of a shirt to buy and the user instead types "I like to buy a pair of shorts", then the textReceived action would allow the bot designer to stop the current conversation flow and navigate to a System.Intent component state to discover the new intent and extract the new entity information.  To implement this on a component (e.g. System.CommonResponse, System.List) supporting the textReceived action transition, you use the following component configuration in the dialog flow name_of_date:   component: "System.List"   properties:      ...   transitions:     next: ...     actions:       textReceived: "intent_state" System.QnA The System.QnA component that is used in a skill to display QnA questions and answers does not have a textReceived action. However, this does not mean you cannot implement the behavior described in the previous paragraph. The System.QnA component has a property "transitionOnTextReceived", that when set to true, follows the "next" transition when a user entered text instead of selecting the answer for a question. For example, the following message, when entered in the skill tester, understands the request as an intent and follows up with a conversation. The same skill answers with a QnA view when the message is not identified as a request for a conversation but a question ("sometimes a question is what it is; a question"). As shown in the image below, the QnA component displays a card layout if there are many candidate questions and answers matching the initial user question (you can fine-tune the QnA matches using settings on the System.QnA component and the QnA feature in Oracle Digital Assistant).   So if a user, instead of selecting the "view" action button, types a new message into the messenger client, then this triggers the dialog flow state to navigate out of the System.QnA component state to the state defined by the next transition. In the image below, the navigation is to a System.Intent component state, which then detects a new intent.  So what's the challenge then? The challenge is that the next transition is also followed when the user selected a View action button (the label of the button can be customized). So to implement the textReceived transition behavior, you need to be able to tell whether a user selected a answer from the QnA component layout or typed free text.  The System.Intent component shown in the image below handles the user message first and either routes it to a dialog flow state handling the intent or a QnA state handling a question. Notice the qnaSkipIfIntentFound and the qnaMinimumMatch properties that you can use to "fine tune" the behavior on the System.Intent component level. To implement the textReceived transition behavior on the System.QnA component state, you set the keepTurn property to true, so that the dialog flow transition immediately continues after the user entered free text. Important, the transitionOnTextReceived property must be set to true as otherwise the System.QnA component tries to find the user entered message as a question in QnA. The secret recipe to success is the expression used in the next transition: "${(system.message.stateCount<=1 && system.message.messagePayload.text?has_content)?then('state_name_if_has_content','state_name_if_empty')}" When a user selects an answer from QnA cards, then the message payload is empty, whereas if the user typed free text, it will have content. Using this expression you can distinguish between a QnA selection and a new user message. (Note, you can also navigate to a System.Switch component state and use the expression in there to determine the next navigation).  So in the image above (and the skill you can download for this article), when a user selects an answer from the QnA component, navigation is to a dialog asking if the user wants to ask another question (in which case navigation goes back to the System.QnA component state). If however the user typed free text, the transition is to the System.Intent dialog flow state explained earlier in this article.  Note: The "system.message.stateCount<=1" part of the expression ensures the state not to go into an infinite loop if the Q&A question returns a single answer.  Download Skill You can download a sample skill used to take the screen shots shown in this article.  Download Skill (ZIP) Import the skill Train the skill Start by asking "I have a question about credit cards" Then select the "view" option for a question Click "yes" to ask a new question Ask "how can I cancel a card?" Order a new card (intent): I like to order a new credit card  Related articles TechExchange Quick-Tip: How-to add the user query string to the Q&A optionsLabel property on the System.Intent component YouTube Video: Calling QnA Module in Separate Skill TechExchange - Using Apache Freemarker Expression in Oracle Intelligent Bots  

article by Frank Nimphius, August 2019   "textReceived" is an action transition that exist on many Oracle Digital Assistant select components and that is followed when users enter free text instead of...

Oracle Digital Assistant orchestrates multiple different skills to a common chatbot user experience. For each user message, Oracle Digital Assistant forwards the request to the skill that fits the best. If in doubt, a smart dialog is displayed for the user to disambiguate the request. In addition, there are requirements for skills that call other skills directly, which can be done using the System.CommonResponse component as documented in the Oracle Digital Assistant product documentation.

Oracle Digital Assistant orchestrates multiple different skills to a common chatbot user experience. For each user message, Oracle Digital Assistant forwards the request to the skill that fits...

In a recent Oracle TechExchange article, Upload Documents in an Oracle Digital Assistant Conversation with Messengers like Facebook or the Oracle JavaScript Client SDK, I explained how to upload documents in a messenger client through Oracle Digital Assistant. In this article I now explain the opposite, which is how to download of documents like audio, video, image and document files within a bot conversation. Basically, to download documents in Oracle Digital Assistant conversations, you have three implementation options available Using the System.CommonResponse component attachment response type, you navigate to a dialog flow state that returns the download URL along with the document type (audio, video, image, file) to the messenger client to download the content. The rendering of the document, whether it is in place within the messenger conversation, or in an external browser or webview window, is not in the control of Oracle Digital Assistant but the messenger used. Using a custom component, you use the JavaScript MessageModel object available in the Oracle custom component SDK. Using a custom component is what you would use if the document URL and type is accessed dynamically from a remote service call. The rendering location, in-place within the messenger client, or external in a web browser or webview, depends on the messenger client used. Oracle Digital Assistant , like any other chatbot too, does not control the messenger client. Using the System.CommonResponse component url action, you can redirect the user to an online source that is always opened in a separate browser tab, or in a webview on a mobile devices.

In a recent Oracle TechExchange article, Upload Documents in an Oracle Digital Assistant Conversation with Messengers like Facebook or the Oracle JavaScript Client SDK, I explained how to...

Computer interfaces have come a long way. From punch cards, to keyboards, to graphical user interfaces (GUI) + mouse, to swiping your finger, elbows, or nose at that mobile phone or tablet. (Laugh if you must, but if you’ve ever had a pair of heavy gloves on, and get an important call, you know what I mean). Now imagine if you were a bee keeper, and had to take a call, or try to use a mobile app on your phone. Yeah, that could sting...   Voice is What’s Next for the Enterprise Jeff Bezos and team deserve credit for having the foresight and success with their Alexa powered devices. I have a few at home, and my family talks to them regularly - while apparently, Amazon listens to us? :-\  Bottom line, the average consumer is using voice more and more to talk to computers. It's expected. Oracle's recent acquisition of speak.ai shows it's leading the way in bringing voice powered apps to the enter prise. To learn more, checkout this webcast, Oracle's New AI Voice for the Enterprise. It's lends credence as to why Oracle was honored by Gartner when it was named a leader for Multi-Experience Development Platforms. (MXDP). Third year in a row - but who's counting?  :) Oracle's Voice for the Enterprise That brings me to the enterprise – Oracle’s sweet spot. That’s where security and privacy are taken more seriously. It’s not a matter of if – but when, that we will be talking to mission critical systems as the new normal. 100%. I have no doubt.  Most analysts agree. In fact, Gartner predicts Gartner predicts that by 2022, 70% of white-collar workers will interact with conversational platforms on a daily basis. This year’s OpenWorld, you’ll see exciting progress with our AI powered, conversational interfaces. The Oracle Digital Assistant (ODA) platform is leveraged by all the Oracle SaaS and on-premises app teams to build conversational interfaces for solutions. And with the recent speak.ai acquisition, ODA will be able to handle complex sentences like: “Find the address to the closest parking garage, near the Japanese restaurant by the Space Needle”  and understand the unique context and vocabulary that various systems (HCM, ERP, CX, etc.) use regularly.   OpenWorld 2019 - The Must Attend General Session by Suhas Uliyar For Oracle Digital Assistant, if there’s one key session to catch (Ok, maybe Larry’s keynote is higher on your list) it’s the General Session led by Suhas Uliyar, Oracle VP of Product Management for Oracle Digital Assistant where you’ll see and hear about the latest and greatest related to Oracle Digital Assistant.   For a dedicated list of Oracle Digital Assistant related sessions, check the program guide. Can't wait? Catch an early glimpse from Suhas' recent interview (the guy is a workaholic) by Regalix. Ok - I've covered a lot of ground. OpenWorld is around the corner. If you're planning to attend, digital assistants will be everywhere! Stop by and have a chat. Cheers!

Computer interfaces have come a long way. From punch cards, to keyboards, to graphical user interfaces (GUI) + mouse, to swiping your finger, elbows, or nose at that mobile phone or tablet. (Laugh if...

Value lists can be displayed using the System.List, System.CommonResponse and SystemResolveEntities component in Oracle Digital Assistant. A challenge for developers that is addressed in this article is how to sort entity derived lists.

Value lists can be displayed using the System.List, System.CommonResponse and SystemResolveEntities component in Oracle Digital Assistant. A challenge for developers that is addressed in this article...

In particular, when working with custom components or webviews (also known as Instant Apps), you may need to add external system configurations, such as server URLs, tokens, Oracle Identity Cloud service, Oracle Digital Assistant instance URL, and more. Of course, you can directly set these dependencies in the dialog flow (BotML) when defining the dialog flow state that references a custom component or webview. However, this has an impact to reuse of skills, and certainly would not follow best practices. As an example, when cloning a skill or when loading a skill from the skill store (a Fusion App feature only at current), you would need to be aware of and know how to find the code lines to change in the BotML code. Instead, Oracle Digital Assistant Best Practices is to use custom skill parameters that help you keep external dependencies out of the dialog flow code, and also clarify where the configuration needs to be set and what values to enter.

In particular, when working with custom components or webviews (also known as Instant Apps), you may need to add external system configurations, such as server URLs, tokens, Oracle Identity...

Oracle Three-Peats Gartner Magic Quadrant We are excited to share that for 2019, Oracle has been recognized as a Leader in Gartner’s first Multi-Experience Development Platform (MDXP) Magic Quadrant!! But wait, you say, if this is the first MDXP report, what’s with the three-peat headline? Well, historically speaking, prior to MXDP, its predecessor was Mobile Application Development Platforms (MADP), of which, Oracle was also “named a leader” for the previous 2 years, back to back. Gartner recognized that market trends were changing and the previous title was too focused on mobile and needed to be updated to reflect evolving trends that reached beyond mobile and include progressive web apps, conversational apps (chatbots) and immersive apps (AR/VR) - as the types of apps people were using to engage businesses. We absolutely agree – especially considering the growth in AI powered conversational interfaces! From the 2019 MXDP report, key takeaways for Oracle included: Core back-end services:  Considering Oracle’s deep portfolio of SaaS and on-premises applications, and preexisting connectors to our own and 3rd party applications, this is Oracle’s sweet spot. Customer experience: “Reference customers for Oracle reported some of the highest levels of satisfaction, compared with those of other vendors in this Magic Quadrant.”  I think that line speaks for itself. Code-centric developer tooling: Oracle has been supportive of open platforms and tools for many years now. For MXDP, we offered: great support for JavaScript, check. React and Cordova, check. SDKs for iOS and Android, check. And “one of the highest satisfaction scores for developer training and support” Check-mate! Oracle is honored by be recognize as a leader (again) and the teams will continue to strive to deliver innovative products for its customers. To download your complimentary copy of Gartner’s 2019 Multi-Experience Development Platform report, click here. Our official press release is here.

Oracle Three-Peats Gartner Magic Quadrant We are excited to share that for 2019, Oracle has been recognized as a Leader in Gartner’s first Multi-Experience Development Platform (MDXP) Magic Quadrant!! Bu...

How to access to conversation logs is common question among Oracle Digital Assistant bot designers, developers and administrators. Oracle Digital Assistant provides several options for accessing conversation logs. A new option, which was introduced in Oracle Digital Assistant Version 19.1.5, is the ability to access session-specific conversation log information through a protected REST API. This REST API can also be used from a custom component to access the conversation log for a session for further processing. Using many screenshots, this article explains how to access conversation session specific log information from a custom component. The custom component and sample skill used in this article is provided for you to download.  

How to access to conversation logs is common question among Oracle Digital Assistant bot designers, developers and administrators. Oracle Digital Assistant provides several options for...

If you bookmarked the Oracle My Cloud Services home page, then it may have come up like shown in the image below. The Oracle Cloud Infrastructure (OCI) console looks modern, fresh and nice. Though you may be wondering, since not all cloud products are yet on OCI, where the My Cloud Services page has been gone to. Especially if you follow documents on Oracle TechExchange, or watch videos, you may want to know how to access the dashboard. The answer is that the Oracle My Cloud Services home page is still there and accessible.

If you bookmarked the Oracle My Cloud Services home page, then it may have come up like shown in the image below. The Oracle Cloud Infrastructure (OCI) console looks modern, fresh and nice. Though you...

Announcement of Oracle Digital Assistant Customer Summit and Program Guide for the Oracle OpenWorld 2019 in SF

Announcement of Oracle Digital Assistant Customer Summit and Program Guide for the Oracle OpenWorld 2019 in SF

By Suhas Uliyar, Oracle VP Product Management   These are exciting times for those of us who are working in Artificial Intelligence (AI) and Machine Learning (ML) space.  Take Voice Assistants as an example. In the consumer world, voice assistants have gone from “the next best thing” to ubiquitous household items. We turn to these voice devices at our homes to get the weather forecast, listen to our favorite tunes, find out the latest in news, play trivia, or simply to entertain ourselves. All this while we are acutely aware that at the end of the day, it is simply a machine. It is nowhere near the capacity of a human mind to be able to process complex statements let alone switch gears from one topic to the other and making sense of it all. Plus, there’s the fact that it is recording our private conversations! But convenience outweighs even our hesitation due to privacy concerns. In the enterprise world, however, such security breaches are a non-starter! So, how do we drive an intelligent Voice Assistant for an enterprise - enabling it to analyze enterprise specific and domain specific vocabulary that the open domain models are not trained with? Make voice, user interactions become more expressive that requires the voice assistant to process even the more complex queries, deriving intelligence from all available enterprise resources and respond in context to the request made? And more importantly, how do we avoid the security and privacy issues that we are seeing with most of the current consumer-grade voice assistants today? Join me on a live webcast as we unveil Oracle’s new AI-Voice for the enterprise this Wednesday, July 17that 10 am PT. I will be going through the details on how we are doing things different at Oracle and the possibilities with an enterprise-grade, secure AI-voice enabled Digital Assistant. I will also be going through a demo that you wouldn’t want to miss. To register, simply sign up here: http://bit.ly/OracleNewAIVoice Happy to discuss more during or after the webcast!    

By Suhas Uliyar, Oracle VP Product Management   These are exciting times for those of us who are working in Artificial Intelligence (AI) and Machine Learning (ML) space.  Take Voice Assistants as an...

Experience has shown that whilst you might invest considerable effort in training your chatbot to handle requests from users about your business domain intents, much of the traffic to a public chatbot is what we generally regard as small talk. “Are you a bot”, “tell me joke”, “Do you like football”. For right or wrong, the success of your bot is, in part, measured by how it handles ALL possible interactions: even the ones in which the user is being deliberately challenging! This article and sample provide a smalltalk skill whose job is exclusively to understand these small talk topics.

Experience has shown that whilst you might invest considerable effort in training your chatbot to handle requests from users about your business domain intents, much of the traffic to a public chatbot...

The webview feature in Oracle Digital Assistant is a powerful approach that enables you to integrate remote and locally deployed custom Web applications and pages into your bot conversations. An earlier article on Oracle TechExchangeexplained how webviews work in detail and how you create remote Web applications that you then integrate with Oracle Digital Assistant skill conversations. This article follows up and extends the previously written article and walk you through the required steps to deploy the intermediary service and remote web application to an OCI Compute node. Hence, you will be using Oracle Cloud offerings to deploy all your assets while using web views in ODA.

The webview feature in Oracle Digital Assistant is a powerful approach that enables you to integrate remote and locally deployed custom Web applications and pages into your bot conversations....

Chatbot use-cases like incident and expense reporting require bot users to be able to upload images and documents through the messenger client and the bot to a remote server. So when the conversation pauses for the user to provide input, then the following could happen 1. The user enters free text 2. The user taps a list item or button, if the input allows it 3. The user uploads a document or image Oracle Digital Assistant supports uploading images and documents through the System.Text, System.List, and System.CommonResponse components. This article explains how to implement the uploading of images and documents from end to end.

Chatbot use-cases like incident and expense reporting require bot users to be able to upload images and documents through the messenger client and the bot to a remote server. So when the conversation...

  My family and I continue to have more and more conversations with Alexa, Siri and Google Assistant lately. Yeah, all three - I’ve no excuse. Having three AI based sources within speaking range of each other, we have a tendency to fact check them against one another - especially when someone doesn’t quite trust or agree with the answer they get. For example, is Australia considered a continent or is it Oceania? Is a hot dog a sandwich?  Who is the best NBA player of all time ever? At the end of the day, even for these sophisticated conversational AI sources, the “trusted” source is key. The old programming adage, garbage in – garbage out, still applies.  Content is King, but Context is Everything Extracting accurate text, from the spoken word, has gotten pretty accurate.  Talk to Alexa, Google and even Siri, they can translate voice to text well enough. Extracting the intent – the meaning behind those words, is hard. It’s hard, because context is everything.  When people talk, we humans are pretty good at switching topics, without much fuss. Go from basketball, to fishing, to baking cookies – not a problem. Switching gears on AI – problem.  Conversational AI – All In Here at Oracle, we’re making great strides to address context.  The Oracle SaaS teams in particular, are all-in on adopting conversational interfaces for their products.  The Customer Experience (CX) team is making access to CRM systems easier.  The Human Capital Management (HCM) team, is also embracing the future – as we speak. <groan>.  And because the Oracle SaaS teams are using Oracle Digital Assistant platform, conversing with the Oracle powered assistant, switching context between app skills from a single digital assistant, will be much easier. Oracle’s New AI Powered Voice You might ponder, Alexa, Google and Siri, they’ve pretty much have the voice to text portion locked down. But in the enterprise space, it’s different. We can do better - not only from a technical perspective, but also from the all the more important privacy and security perspective.  While Oracle Digital Assistant is it’s own platform, within Oracle’s own cloud environment, processing voice to text, using Alexa, etc., isn’t always an ideal or even acceptable situation.  That’s why Oracle’s investing in it’s own AI powered voice technologies.  From what I’ve seen – it’s well worth the investment and a potential game changer in the enterprise. You can hear a quick intro on this topic, on this 10 min podcast interview with Suhas Uliyar, VP Product Management, and also catch a deeper dive in this upcoming free webcast on July 17. And of course, to see how much conversational AI is being embraced, check out Oracle OpenWorld – where Digital Assistant will literally be the talk of the show.  FWIW, Australia is a continent.  Oceania is a region that includes the country/continent of Australia. A hotdog is a sandwich.  And the GOAT NBA player is of course, Michael Jordan. 

  My family and I continue to have more and more conversations with Alexa, Siri and Google Assistant lately. Yeah, all three - I’ve no excuse. Having three AI based sources within speaking range of...

You use webviews in Oracle Digital Assistant to integrate web application forms in your chatbot conversations. A reason for using web forms in a conversation is to simplify the input of structured data as in application forms. Another is to assist users with user interface widget that don't exist in messenger clients. As of Oracle Digital Assistant 19.1.5, Webviews can also be deployed as Single Page Applications (SPA) in a local skill container, which opens for many use cases. In this article, I'll explain an example that uses a locally deployed Oracle JavaScript Extension Toolkit (JET) SPA application to provide users with a calendar widget that helps them to enter dates more conveniently in a bot conversation.

You use webviews in Oracle Digital Assistant to integrate web application forms in your chatbot conversations. A reason for using web forms in a conversation is to simplify the input of...

Google reCaptcha is used in many web applications to distinguish humans from bots. A type of reCaptcha is where users select a checkbox or select images showing common objects like a bus, traffic lights, street signs and so on. Google reCaptcha can also be implemented in chatbots built with Oracle Digital Assistant. For this you use a locally deployed webview for displaying the challenge and a custom component for verifying the prove that a human is what he claims to be: a human. This article explains how you use the System.Webview component and a custom component to integrate Google reCaptcha in Oracle Digital Assistant chatbot conversations. In addition, you can download the Oracle JET webview application and the custom component as packed files for immediate use in your own chatbots.

Google reCaptcha is used in many web applications to distinguish humans from bots. A type of reCaptcha is where users select a checkbox or select images showing common objects like a bus, traffic...

Zendesk is a customer relationship management platform like Oracle Service Cloud. In this article, for developers, we explain how to connect the Zendesk web-based chat widget with Oracle Digital Assistant using the webhook channel and Oracle Bots Node.js SDK. ODA will provide the intelligence to Zendesk web widget and automate the replies of customer and hand over to human agent (Zendesk Agent) with chat history to provide the solution to the customer. Zendesk communicates with its chat widget and directs requests to Oracle Digital Assistant until users request a live agent.

Zendesk is a customer relationship management platform like Oracle Service Cloud. In this article, for developers, we explain how to connect the Zendesk web-based chat widget with Oracle...

A common requirement among Oracle Digital Assistant customers is to export conversation logs using a non-GUI approach. Oracle Bots Insights, the bot analytic feature in Oracle Digital Assistant, provides a REST API for you to export conversation information based on optional custom filter criteria. The REST API is documented in REST API for Oracle Digital Assistant, which is a part of the Oracle product documentation for Oracle Digital Assistant. This article explains the steps to export conversation logs for a skill in Oracle Digital Assistant using Google Chrome Postman as a client. With this article, which closely follows the product documentation, you get a second option for exporting and accessing conversation data.

A common requirement among Oracle Digital Assistant customers is to export conversation logs using a non-GUI approach. Oracle Bots Insights, the bot analytic feature in Oracle Digital...

Natural language conversations are, by their very nature, free-flowing. But they may not always be the best way for your skill to collect information from a user. For example, when entering credit card or passport details, users need to enter this information precisely. In addition, information like passwords or secrets should not be displayed in the messenger conversation history. Webview (System.Webview ) is a powerful approach that allows you to integrate remotely and locally deployed custom web applications to your bot conversations. All bot designers working with Oracle Digital Assistant should start using webviews for integrating external web application calls. In writing and in a sample for download, this article will show you how to integrate the interaction between a remotely deployed web application and a skill in Oracle Digital Assistant. Oracle Digital Assistant skills can call external web applications, pass parameters to them, and receive a response payload

Natural language conversations are, by their very nature, free-flowing. But they may not always be the best way for your skill to collect information from a user. For example, when entering credit...

he widgets most commonly used when creating chatbot user interfaces are input text fields and value lists. The Common Response component in Oracle Digital Assistant lets you create text and value list user interfaces directly from entity definitions. What not many bot designers know is that the dialog flow code for building such interfaces can be created generically, so it can be re-used in various dialog flow states. This article explains how to configure entities and the Common Response component to display text and lists following a generic approach.

he widgets most commonly used when creating chatbot user interfaces are input text fields and value lists. The Common Response component in Oracle Digital Assistant lets you create text and value list...

ES 6, known as ECMA Script 2015 or JavaScript 6, introduced the concept of destructuring. Destructuring is a JavaScript expression syntax that reads values ​​from arrays and objects and assigns them to variables. Custom components in Oracle Digital Assistant support JavaScript destructuring and custom component developers may use this syntax to assign component input parameter values to variables. This article explains destructuring variable-assignments in custom components and points out the benefits.

ES 6, known as ECMA Script 2015 or JavaScript 6, introduced the concept of destructuring. Destructuring is a JavaScript expression syntax that reads values ​​from arrays and objects and assigns...

The Oracle Bots Node.js SDK includes a command line utility that you can install globally on your local computer and that lets you easily create new custom component and custom component projects. The custom components created by the Oracle Bots Node.js SDK contain a "hello world" content that contains examples fo the two main function calls: metadata() and invoke(). In addition, the invoke() function implementation shows example code for how to access input parameters ("human" in the example), how to print responses to the bot ("conversation.replay(...)) and how to pass control back to the bot ("done()"). Unless "hello world" is all you need to build, or if this is the first time you use the Oracle Bots Node.js SDK to create custom components, you may be interested to learn how to customize the template to contain e.g. the author name, a use license and more. Especially when working in teams you may want to enforce consistency across custom components that are integrated, which includes a common set of input parameters (e.g. always use "variable" as an input parameter for the reference to the dialog flow variable to update (like system components do). This article explains how to modify the component template in a global Oracle Bots Node.js SDK installation.

The Oracle Bots Node.js SDK includes a command line utility that you can install globally on your local computer and that lets you easily create new custom component and custom component projects. The...

One of the key factors of a successful digital assistant is to make it easy for the user to make the right choices and stay on the “happy path”. Consider the example of booking a flight. If you know the user nearly always travels to the same two or three airports then wouldn’t it make sense to present those common choices up front. The user can simply select the correct option rather than typing in the airport name. Of course, you still want to give the flexibility that they can free-type in any possible airport, but you want to make sure it’s a valid airport! Or another common example when inputting expenses – maybe most of the time your expense currency is EUR, USD or GBP – so those might be the options you see up front but you should still be able to select any other valid currency In this article I’ll show you how you how to easily present a list of common entity choices to the user, but still allow a natural language input which is validated as a valid value.

One of the key factors of a successful digital assistant is to make it easy for the user to make the right choices and stay on the “happy path”. Consider the example of booking a flight. If you...

Let's assume you built a chatbot using Oracle Digital Assistant and you've exposed it on various messengers and Alexa too. A next step then could be to connect your chatbot to Google Home. I die research this topic quite a lot but couldn't find anything complete describing how to do this using Google Actions on Google API version 2. So, what has started as a research, eventually has become an opportunity for me to write a comprehensive guide to integrate Oracle Digital Assistant with Google Home. Following this article, you learn how to build a webhook, how to create an Action on Google, how to create a channel in Oracle Digital Assistant and how to use Goggle sign-in (account linking) to access user information from Google. Note that because I live in Brazil, a requirement was to build chatbots in more than one language (English, Spanish and Portuguese). Therefore I built the webhook to be able to call two different channels, each calling a different language optimized skill.

Let's assume you built a chatbot using Oracle Digital Assistant and you've exposed it on various messengers and Alexa too. A next step then could be to connect your chatbot to Google Home. I...

Composite bag entities are like business domain objects and consist of multiple entities, string variables or attachments. Using composite bag entities you leverage the System.ResolveEntities and the System.CommonResponse component to display prompts to users until all entities and variables in a composite bag entity have a value. No explicit dialog flow steps need to be written for this. Using composite bag entities, there is a smart feature "Out of Order Extraction" that may cause side effects for bag items that reference the same entity. This article explains the side effect and how to solve the problem.

Composite bag entities are like business domain objects and consist of multiple entities, string variables or attachments. Using composite bag entities you leverage the System.ResolveEntities and the...

The Oracle Digital Assistant Client SDK for JavaScript provides a messenger widget for you to integrate Oracle Digital Assistant bot conversations in your web sites and web applications. The chat widget can be customized through the setting of properties. This article covers advanced customization options that include

The Oracle Digital Assistant Client SDK for JavaScript provides a messenger widget for you to integrate Oracle Digital Assistant bot conversations in your web sites and web applications. The...

In a recent article on Oracle TechExchange, Grant Ronald explained a solution for displaying randomized bot responses. In this quick tip, I am taking Grant's solution to a next level, which is to use resource bundles to store the random strings to display.

In a recent article on Oracle TechExchange, Grant Ronald explained a solution for displaying randomized bot responses. In this quick tip, I am taking Grant's solution to a next level, which is to...

One element to the success of your bot is the tone and voice your bots uses. Informal and “chatty” response may be a more engaging and better fit with your brand. In line with this approach, you would probably want to ensure your bot replies are not formulaic and predictable. In this article I demonstrate how you can easily randomize the responses from your bot.

One element to the success of your bot is the tone and voice your bots uses. Informal and “chatty” response may be a more engaging and better fit with your brand. In line with this approach, you would...

You use Apache FreeMarker expressions in Oracle Digital Assistant skill dialog flows to define conditional blocks, iterate arrays, perform string, date, number and arithmetic operations and formatting, and many more. Apache FreeMarker is a powerful "tool" that allows developers to add custom logic to an otherwise declarative and component based dialog design. Through Apache FreeMarker is the programming language in Oracle Digital Assistant, at current there is no declarative expression builder or tester available for you to develop expressions. In this article we explain a simple technique to create a custom Apache Freemarker tester using a skill and the embedded conversation tester in Oracle Digital Assistant.

You use Apache FreeMarker expressions in Oracle Digital Assistant skill dialog flows to define conditional blocks, iterate arrays, perform string, date, number and arithmetic operations...

Beside of conversations, chatbots need data. Especially when starting out with a chatbot project, you may need to be able to quickly show something to the stakeholders to illustrate your ideas and concepts. If things need to be quick, then often the integration of real backends is either not possible or not required. Another reason to look for and use mockup data is to bridge the time it takes service developers to provide access to backend systems. In this article I explain four options for you to define mockup data in Oracle Digital Assistant. Each option defines a different type of data or provides a different approach of querying the data.

Beside of conversations, chatbots need data. Especially when starting out with a chatbot project, you may need to be able to quickly show something to the stakeholders to illustrate your ideas and...

One of the key features of a chatbot or digital assistant is understanding and extracting entity values from a user utterance. These entity values are critical pieces of information which are usually used as data for backend systems or acted upon within the conversation. However, the nature of entities and user input is that you don’t always know how many entity values you are likely to get, if in fact any at all. In this article I’ll show how you can introspect the various entities within an entity list, and then access each of the entity values regardless of how many entity values the user says.

One of the key features of a chatbot or digital assistant is understanding and extracting entity values from a user utterance. These entity values are critical pieces of information which are usually...

List-of-values, as well a action lists (menus), use buttons for rendering the list's select items. Apart from long lists of values that result in poor usability, some messengers, including Facebook, have a limitation on the number of action items that can be displayed in a list at the same time. The solution to this is pagination, in which bot designers allow users to scroll within a list of values by showing a reduced set of values at a time. There are two components in Oracle Digital Assistant that you can use to build list-of-values that support pagination System.ResolveEntities System.CommonResponse component Both components require the rangeSize for pagination to be defined on the entity itself. The System.ResolveEntities component does not require any configuration than to reference a variable of the entity type from its "variable" property. For the System.CommonResponse component, pagination works with a few settings. Note that the reason that System.CommonResponse requires configuration is that it is a very flexible component that allows bot designers to customize bot responses, which you cannot using the System.ResolveEntities component. This article explains the use of the System.CommonResponse component

List-of-values, as well a action lists (menus), use buttons for rendering the list's select items. Apart from long lists of values that result in poor usability, some messengers, including...

Put simple, dialog flows are user-bot interaction scripts that a skill in a digital assistant conversation follows to assist users in completing a task using the conversational channel. Though dialog flows are needed, the best dialog flow would be no dialog flow. Using composite bags in Oracle Digital Assistant you can partially achieve this. Composite bag entities are like business domain objects in that they group several entities and variable type items to a single "super" entity that then aligns with a business object like an order, a customer etc. Configurations like prompts, error messages, validation, range size settings and more, that normally you would define on a UI component are contained in the composite bag entity attributes. Attributes of an entity bag item are referred to as bag items and can be of type entity or a variable of a primitive data type. In Oracle Digital Assistant, there are two system components that can be used in combination with composite bag entities to auto-generate bot responses and dialog flows from definitions saved in bag items: System.ResolveEntities is one, System.CommonResponse is the other. In this article I explain how to use the System.ResolveEntities with component with composite bags. Using a System.CommonResponse component with composite bag entities may be a topic for a later TechExchange article. Most of the default settings and behaviors though are identical.

Put simple, dialog flows are user-bot interaction scripts that a skill in a digital assistant conversation follows to assist users in completing a task using the conversational channel. Though dialog...

The conversation interface is not just about text messaging. Most messengers support a list of values, and many even support card layouts. Chatbot users select a value from a list by either tapping the list item or typing the displayed list item label into the message field. In this article I explain how to assign keywords as shortcuts to list items (and card layouts, as it is the same code) for users to select an item. With card layouts, when not all cards are displayed in a horizontal carousel (so when some are hidden), then, using predictable keywords, keyword shortcuts allow users to select an item even if it is not visible* * the restriction is when you use page ranging, in which case a card is not hidden but not available at all. In this case you can only access those cards that belong to the current displayed range of cards.

The conversation interface is not just about text messaging. Most messengers support a list of values, and many even support card layouts. Chatbot users select a value from a list by either...

The Oracle Digital Assistant Client SDK for JavaScript provides functionality to communicate with a Oracle Digital Assistant from the web. Part of the Client SDK for JavaScript functionality is a JavaScript based web widget that can be added to your web applications or web sites to launch a message window. In a typical chat conversation, users initiate the conversation by typing a message similar to shown below, assuming the receiving bot has an intent defined so it responds to the request. Hi Hello I would like to make a complaint The bot replies with a text message or rich UI response (e.g. card layouts or a list) that then is understood by the web client and rendered for the user to make a selection or type a next message. A problem reported by users is that the chat window initially is empty leaving the bot users stunning of how to start a conversation. So ideally, the chat windows open with the Oracle Digital Assistant bot to welcome a user with a clear message or menu to choose from. This article explains how to initiate a bot conversation with Oracle Digital Assistant upon launching the web messenger widget on a website or in a web application.

The Oracle Digital Assistant Client SDK for JavaScript provides functionality to communicate with a Oracle Digital Assistant from the web. Part of the Client SDK for JavaScript functionality is...

This article summarizes new features in Oracle Digital Assistant release 19.1.3 and describes important changes that must be made when migrating chatbots that were built on versions prior to 19.1.3. Oracle Digital Assistant 19.1.3 introduces significant new capabilities including • Support for additional messaging channels (Microsoft Teams, Cortana, Skype and Slack) • Service Cloud agent handoff enhancements • WebView component self-hosting • Improvements to system intents and conversational routing

This article summarizes new features in Oracle Digital Assistant release 19.1.3 and describes important changes that must be made when migrating chatbots that were built on versions prior to 19.1.3....

Skills in Oracle Digital Assistant can have custom parameters defined that you can either use to achieve consistent configuration for entities and components in the skill, or to provide controls for digital assistant bot designers to "harmonize" the behavior of different skills. Especially skills developed by different teams may not follow the same look and feel or may not adapt the same to constraints applied by messengers. If you are a digital assistant developer today, what are your guidelines e.g. for the orientation of card layouts and how how many cards are displayed at once? Do you know that messengers vary in the number of cards they support for rendering at the same time? But even in a skill itself, is there a way in your bot building guidelines that ensures e.g. range sizes set on entities and components are the same for a consistent look and feel? Do you allow customization of system messages on the skill and digital assistant level?

Skills in Oracle Digital Assistant can have custom parameters defined that you can either use to achieve consistent configuration for entities and components in the skill, or to provide controls for...

A very popular use case for chatbots is the integration of the chat window into a website or web application. However, a challenge with this setup is when the user abandons a chat conversation by closing the browser window. In this case, Oracle Digital Assistant stops the Web Channel conversation after a predefined period of time, which usually is not within seconds but mostly within the 10s of minutes. However, what if the user was interacting with a human agent through the bot conversation when deciding to the leave the conversation by closing the browser window? And what is the impact? Oracle Digital Assistant has no way to tell when the user closes the browser window. This leads to the agent integration connection to stay open until the session expires, which however then means that the overall number of connections to the human agent backend system doesn't match the number of active connections until the session expired. Another impact is the situation the agent is in. Because the agent is not aware of he user leaving the conversation, he or she may continue checking if the user s still there and spend time waiting until they eventually decide the user may no longer be online. This article describes a strategy for ending the interaction between a user and an agent when the user leaves the bot conversation by closing the browser window.

A very popular use case for chatbots is the integration of the chat window into a website or web application. However, a challenge with this setup is when the user abandons a chat conversation by...

Dialog flows in Oracle Digital Assistant intelligently guide users through a conversation to complete a task or request. Users may have different experiences with bot interactions. Although the bot designer's goal is to make the conversation as natural as possible to humans, there still is a possibility of users getting stuck. One reason for users to get stuck is when they don't know how to provide a valid answer to a bot question. Another reason is that the bot user changes his mind and wants to continue with a different task or request. Often it is the validation loop implemented on a dialog flow state that makes the bot appearing stubborn and not letting users out. In this article I explain Oracle Digital Assistant features and implementation strategies for you to use in your skill design to keep users unlocked.

Dialog flows in Oracle Digital Assistant intelligently guide users through a conversation to complete a task or request. Users may have different experiences with bot interactions. Although the...

Traveling to Dubai next week for Oracle OpenWorld - Middle East, or just happen to be passing through on Monday, February 11th and Tuesday, February 12th?  Curious about how Oracle is innovating for the enterprise with artificial intelligence and conversational interfaces?  Here are six sessions and two demos at next week's conference that should be on your list:   Sessions Oracle Cloud: The Next Big Things February 11th @ 9:30-10:05, Arena 1 (Level 1), Dubai World Trade Centre Learn about the cutting-edge solutions that will accelerate your business. From Machine learning to speech-based analytics, trust fabric, automated application development (leveraging AR and VR), to digital assistants. Experience transformational cloud platform and application solutions that will enhance productivity, lower costs, and accelerate innovation across the enterprise.   Building Next-Gen Cloud Apps with Chatbots, Embedded Intelligence, and Blockchain February 11th @ 9:30am-10:45am, Arena 2 (Level 1), Dubai World Trade Centre The cloud is fundamentally changing how enterprise applications are being built today. Developers are leveraging new services and capabilities up and down the stack to more quickly deliver innovation and provide greater ease of use, management, and integration, while also providing deeper intelligence through these applications. In this session see how digital assistants, AI and ML, and blockchain based cloud infrastructure are enabling these next generations of cloud native apps to be built on Oracle Cloud Platform.   Beyond the Screen: From Chatbots to Your Own Digital Assistant February 11th @ 10:15-10:50, Arena 4 (Level 1), Dubai World Trade Centre In the past two years, AI technologies have transformed the way we interact with systems and devices across channels. Chatbots have become widely adopted, and Oracle has evolved them into digital assistants that can complete complex user tasks. A digital assistant is able to leverage AI to make recommendations, possess many skills, initiate conversations, and use cognitive services to provide an ambient human experience. In this session see how Oracle Digital Assistant can transform enterprises with next-generation conversational AI technologies.   Lessons From Deploying Digital Assistants & Chatbots February 11th @ 10:15-10:50, Forum 6 (The Exchange, Level 1), Dubai World Trade Centre Join Oracle's Ian Wallis and Asser Smidt from Botsupply to hear about Oracle’s real customer experiences in deploying chatbots and digital assistants in the market. These practical lessons will span scope, language, training, supervision and many more topics.   10 Keys to Successful Digital Assistant and Chatbot Implementation for the Enterprise February 11th @ 10:55, Arena 5, Dubai World Trade Centre Chatbots and Digital Assistants are a hot and emerging technology where best practices are still evolving. How will real users interact with a Chatbot? How to identify the top use cases to being your Chatbot journey? How to extract bots conversational design from LOB stakeholders who may never have interacted with Chatbots before? In this session, we will outline keys to a successful Chatbot implementation - how to identify Chatbot use cases, design top-notch conversational flows, target bots functionality for your key users, integrate with back-end system and data sources, and most importantly, pick the right Chatbot platform. Come to this session and hear us sharing the secrets to successful Chatbot implementations and how you can reap real business benefits.   From Zero to Chatbot to Digital Assistant in Under Two Hours February 11th @ 15:15-17:15, Arena 9 (Level 1), Dubai World Trade Centre Chatbots are one of the first widespread uses of artificial intelligence and natural language processing. As chatbots have evolved in enterprise use, so has the emergence of Digital Assistants. In this hands-on-lab (*your own laptop is required*,) you will get your hands dirty with this new technology. You will first “educate” your Digital Assistant with a rich set of available application skills from Oracle, without writing any code. You will then develop and train a new skill defining intents, utterances, and entities. You will then design the conversation flow, connect the skill to a back-end API, and enhance it with QnA functionality. Finally, you will add the new skill to your Digital Assistant and publish it to a chat client.   Enabling Effortless Interactions - How Chatbots and Voice Assistants Change CX Forever February 12th @ 10:15-10:50, Arena 2 (Level 1), Dubai World Trade Centre Join this expert panel session to understand how conversational approaches and innovation around how these interactions can be successfully applied and adopted as part of CX. We will discuss how digital interactions have evolved, why effortless interactions even matter in today’s customer-empowered era, and use cases of human-centric interactions.   Demos Digital Assistants February 11th - February 12th, The Exchange, Dubai World Trade Centre Enabled by artificial intelligence, today's chatbots and virtual assistants are supercharging productivity for sales and service professionals, whether in the office, the contact center, or on the go. Come see how these smart Oracle solutions can work in your business to save precious selling time, reduce inbound service inquiries, and improve the customer service. We'll demonstrate, Virtual Assistant for Service Cloud, and Sales Virtual Assistant, as well as tell you about our platform that lets you develop custom chatbots. Learn about our chatbot integrations with Facebook Messenger and WeChat too.   Oracle Digital Assistant Cloud: Next-Generation Conversational AI for Enterprises February 11th - February 12th, The Exchange, Dubai World Trade Centre Chatbots technology has evolved rapidly during the past two years. When it comes to enterprise requirements, the current chatbot falls short, however. Users now demand bot-initiated conversations, richly interactive conversational interfaces, deep analytics/insights, and the ability to access multiple chatbots from a single interface. Come to this demo to see how Oracle is pushing conversational AI to next-generation digital assistants that overcome chatbots’ shortcomings. You’ll also get an introduction to Oracle Digital Assistant Cloud.   If you can't make it to Dubai next week, you also can learn more about Oracle Digital Assistant, and we'll be hosting additional Cloud Days and OpenWorld events throughout 2019 so come and see what the buzz is all about.

Traveling to Dubai next week for Oracle OpenWorld - Middle East, or just happen to be passing through on Monday, February 11th and Tuesday, February 12th?  Curious about how Oracle is innovating for...

Digital assistants like Siri, Alexa & Co control your smart home: switch on lights, control heating and more. But can you do the same using Oracle Digital Assistant (ODA)? Or is Oracle Digital Assistant just an intelligent front end for integrating enterprise backend systems? The answer to both questions is a big and bold yes. It is the part where IFTTT (if-this-then-that) comes into play. IFTT provides a software platform that connects apps, devices, and services from different developers to trigger automation. In this article I explain how you create a custom component that connects to an IFTTT applet to control dimming the light from an Oracle Digital Assistant skill bot. All resources files are provided for download from the Oracle TechExchange blog where they reside with this article.

Digital assistants like Siri, Alexa & Co control your smart home: switch on lights, control heating and more. But can you do the same using Oracle Digital Assistant (ODA)? Or is Oracle...

The power of a conversational interface, such as Oracle Digital Assistant, lies in the ability for a user to communicate using natural language using phrases and terms with which they are familiar and comfortable. So, rather than a user interaction being railroaded by the implementation of an IT system, the Nirvana is a naturally flowing conversation. However, the freedom of an open and loosely structured interface such as spoken and written language may exponentially add to the complexity of how you design these systems. The very nature of language is complex, often imprecise and ambiguous. It is therefore critically important to design conversational interfaces with strategies and techniques to mitigate this complexity. This paper discusses a number of important tips and lessons for building a conversational interface including designing conversations, voice and personality, natural language intelligence, help, guidance and error handling.

The power of a conversational interface, such as Oracle Digital Assistant, lies in the ability for a user to communicate using natural language using phrases and terms with which they are familiar and...

Today, Oracle Digital Assistant product management has launched a new public Website to share tutorials and training materials with bot developers. The new website is hosted on GitHub and can be accessed by anyone. Releasing tutorials and trainings on GitHub also is an invitation to the Oracle Digital Assistant developer community to contribute with their own tutorials on Oracle Digital Assistant. You can access the all new Oracle TechExchange - Oracle Digital Assistant Tutorials and Hands-on site from the link below. http://bit.ly/ODAEnablement Oracle TechExchange was launched as a blog in 2017 (https://blogs.oracle.com/mobile/tech-exchange) and since then provides Oracle chatbot developers with technical information, hints and tips beyond the official product documentation. In an effort to do more, Oracle Digital Assistant product management launched this new web site to share additional hands-on focused content. The plan for the Oracle TechExchange tutorial and training site is to frequently release new tutorials addressing new product features, as well as topics frequently requested by the Oracle Digital Assistant developer community. This new site is in addition to the Oracle TechExchange blog, which remains as an independent blog page and the go-to page for advanced information about Oracle Digital Assistant.

Today, Oracle Digital Assistant product management has launched a new public Website to share tutorials and training materials with bot developers. The new website is hosted on GitHub and can...

Messaging channels vary in the richness of their user interface. For example, Facebook supports rich media like images, card layouts, attachments, quick answers, and more. Other channels like WeChat or SMS do not provide the same UI functionality. As a bot designer you need to be able to adapt bot responses to the channel that is used. Voice also is a good example of a channel that does not do well with rich user interface components. When using speech, the bot response should be simple and text-driven. The term adaptive design for bots is not widely used (at least I did not find an article yet taking about it). To create bots that should be accessed from different channels, you as a bot designer should already be aware of this. Oracle Digital Assistant supports adaptive design in BotML, the CommonResponse component, and custom components, which basically means everywhere. Use cases for adaptive design: Show user interfaces that are optimized for a channel Change the behavior of a bot based on a channel. For example, a specific channel might be more trusted than another, in which case you don't allow the same set of actions Change the messages displayed to users. For example, users of the embedded test channel would see error messages in their purest form, while users would see in a less technical term In this article I will show how expressions can be used in BotML to detect the user channel type and the channel name. The channel name is the name you give to a channel configuration in Oracle Digital Assistant.

Messaging channels vary in the richness of their user interface. For example, Facebook supports rich media like images, card layouts, attachments, quick answers, and more. Other channels like WeChat...

All bot responses are messages. The most common output is the text message that prints in a bubble. Especially at the end of a bot task, bot designers look for a way to print a summary of outcome of the user-bot interaction. For this, designers have different requirements Print text messages in Multiple Bubbles Print multi-line text messages in a single bubble This article provides examples for Oracle Digital Assistant

All bot responses are messages. The most common output is the text message that prints in a bubble. Especially at the end of a bot task, bot designers look for a way to print a summary of outcome...

Sample describes how to use the index of an object in .a data array in a common response component postback action

Sample describes how to use the index of an object in .a data array in a common response component postback action

As you may know, the Common Response component (System.CommonResponse) can be used to iteratively stamp response items sourced from an array. Sometimes however it is not the repeated rendering of a response item that bot designers need but the repeated looping over a dialog flow state or many dialog flow states (block). In this quick tip I explain how to create a loop in the dialog flow of a skill bot that gets terminated when a specific condition is met.

As you may know, the Common Response component (System.CommonResponse) can be used to iteratively stamp response items sourced from an array. Sometimes however it is not the repeated rendering of a...

  Traveling to London next week for Oracle OpenWorld - Europe, or just happen to be in town on Wednesday January 16th and Thursday, January 17th?  Curious about how Oracle is innovating for the enterprise with artificial intelligence and conversational interfaces?  Here are five sessions at next week's conference that you need to attend:   Lessons From Deploying Digital Assistants & Chatbots January 16th @ 9:00-9:35, Forum 2 (Level 0), ExCeL London Join Oracle's Ian Wallis and Asser Smidt from Botsupply to hear about Oracle’s real customer experiences in deploying chatbots and digital assistants in the market. These practical lessons will span scope, language, training, supervision and many more topics.   10 Keys to Successful Digital Assistant & Chatbot Implementation January 16th @ 11:15-12:00, Arena 6 (Level 3), ExCeL London Chatbots and digital assistants are hot and emerging technologies, and best practices are still evolving. How will real users interact with a chatbot? What are the differences between chatbots and digital assistants? How do you identify the top use cases? How do you extract conversational design from LOB stakeholders who may never have interacted with chatbots before? In this session learn how to ensure a successful digital assistant implementation, including how to identify use cases, design top-notch conversational flows, target functionality for your key users, and integrate your digital assistant with your back-end applications. Discover the secrets to successful implementations and how you can reap real business benefits.   Beyond the Screen: From Chatbots to Your Own Digital Assistant January 16th @ 12:10-12:45, Arena 4 (Level 3), ExCeL London In the past two years, AI technologies have transformed the way we interact with systems and devices across channels. Chatbots have become widely adopted, and Oracle has evolved them into digital assistants that can complete complex user tasks. A digital assistant is able to leverage AI to make recommendations, possess many skills, initiate conversations, and use cognitive services to provide an ambient human experience. In this session see how Oracle Digital Assistant can transform enterprises with next-generation conversational AI technologies.   Oracle Cloud: The Next Big Things January 16th @ 12:10-12:45, Arena 1 (Level 3), ExCeL London Learn about the cutting-edge solutions that will accelerate your business. From Machine learning to speech-based analytics, trust fabric, automated application development (leveraging AR and VR), to digital assistants. Experience transformational cloud platform and application solutions that will enhance productivity, lower costs, and accelerate innovation across the enterprise.   From Zero to Chatbot to Digital Assistant in Under Two Hours January 16th @ 15:00-17:00, HOL Summit Room (Level 3), ExCeL London Chatbots are one of the first widespread uses of artificial intelligence and natural language processing. As chatbots have evolved in enterprise use, so has the emergence of Digital Assistants. In this hands-on-lab (*your own laptop is required*,) you will get your hands dirty with this new technology. You will first “educate” your Digital Assistant with a rich set of available application skills from Oracle, without writing any code. You will then develop and train a new skill defining intents, utterances, and entities. You will then design the conversation flow, connect the skill to a back-end API, and enhance it with QnA functionality. Finally, you will add the new skill to your Digital Assistant and publish it to a chat client.   If you can't make it to London next week, we also are hosting Oracle Cloud Days in New York and Atlanta, GA where you also can learn more about Oracle Digital Assistant, and registration is still open!  We'll be hosting additional Cloud Days and OpenWorld events throughout 2019 so come and see what the buzz is all about.

  Traveling to London next week for Oracle OpenWorld - Europe, or just happen to be in town on Wednesday January 16th and Thursday, January 17th?  Curious about how Oracle is innovating for the...

I have three voice activated, virtual assistants at home:  Google Home Max. It’s a pricey and comparatively large and hefty but sounds great Apple HomePod. Also pricey. Beautiful, elegant, and sounds great, but Siri is meh… Three Amazon \ devices, various generations, relatively inexpensive with decent sound            Anecdotally, based on how often my family uses them (wife, 2 young boys, a dog, and a beta fish) Amazon is the winner. I know Google has the depth and breadth to be very smart, but we kept having too many misses and glitches. The Echo/Alexa was being called upon for jokes, stories, timers, information, and more importantly - music, even though the better sounding Google Home Max was in the same room.  Perhaps being creatures of habit, we became accustomed to calling out to Alexa? First mover advantage? But then again, Siri had the first mover advantage on the iPhone, and was always available - but Siri’s abilities are clearly behind both Amazon and Google. It’s unfortunate as I really like the design and sound of the HomePod. I have noticed Siri getting smarter, perhaps since they poached one of the AI experts from Google. But unfortunately for Apple, Siri is still not yet competitive.   So what does any of this have to do with Oracle? This is the continued consumerization of IT. No more AI science lab projects. This is the consumerization of AI for the enterprise. The phrase "consumerization of IT", imho, was primarily driven by the introduction of the iPhone, back in 2007. With the iPhone, consumers fell in love with their smartphones and asked their IT departments to support them. Back then, Blackberries (aka crackberries) ruled the mobile enterprise. I recall my time at Verisign/Symantec, IT resisted iPhones due to security concerns, but eventually relented. From my observation, with executive influence (thanks Enrique S.) owning an iPhone and iPad, well, that’s the way IT rolled.       With all these mobile smartphones and devices, it becomes easy to see how conversational interfaces will work their way into the enterprise. That brings me to specifically call out our chatbot technology, Oracle Digital Assistant. A digital assistant is more than a simple chatbot. For details, check this excellent post by Eric Rogge delving into more depth on newly release features for Oracle Digital Assistant.    With the growing popularity of conversational interfaces (text/voice) in the enterprise, this nascent market is full of new tools and solutions vying for your attention. And as the market matures, most of which will simply go away or be acquired by a larger player. Remember all the internet companies? The e-commerce companies? Mobile companies? It's darwinism at work.     Easy, easy, and...wait for it....     Who survives and flourishes? I’ve alway felt that there are 3 things that make a product successful - inspired by the old real estate adage (location, location, location) - what makes a product successful is: easy, easy, and wait for it…easy!  Remember plug-and-play? Of course, the product still has to get the job done, but he who makes it easy to adopt, easy to use, easy to live with, usually wins. Why do you think UX experts and UI designers are in such high demand?        Oracle Digital Assistant Combining Multiple Skills   For Oracle Digital Assistant, the Oracle SaaS teams are working on easy, by building their own related digital assistant “skills" that plug and play with the Oracle Digital Assistant platform. Imagine a digital assistant skill for ERP, assistant for procurement, assistant for reports, an assistant for supply chain management, an assistant for HR, expense reports, whatever the customer needs are. Now imagine these assistants, readily available in a Skill Store, or Catalog - akin to the Apple AppStore or Google Play, easily available to add to your own Digital Assistant.  Now make them so that they can be customized to your needs, easy. Provide the platform to manage their lifecycle - easy. Provide proven, serious enterprise security skills by default - easy. Given the potential of multiple digital assistants, Oracle Digital Assistant can bring them together under one comprehensive assistant.    TL;DR - Oracle Digital Assistant makes it easy to bring chatbot capabilities to your enterprise applications in a unified platform. Again, a great read is Eric Rogge’s recent blog post on this topic. https://blogs.oracle.com/mobile/oracle-digital-assistant-version-1843-introduces-skill-chatbot-capability    Your next steps: Oracle Cloud Day in New York next week, Jan 15. I’ll be presenting at the “One Bot to Rule them All” session. If you’re there, match this blog, and see me at the event, ping me and I’ll buy you an adult beverage of your choice.   Oracle OpenWorld Europe, Jan 16-17, in London, If you’re across the pond, catch Suhas Uliyar’s must see presentations, Beyond the Screen: From Chatbots to Your Own Digital Assistant, and other related sessions.  OpenWorld Middle East, Feb 11-12, in Dubai OpenWorld Asia, Mar 26-27, in Singapore.     Can’t make any of these? Call you’re Oracle sales rep or partner. I’m sure they’d love to chat.  No more excuses. cloud.oracle.com/digital-assistant    

I have three voice activated, virtual assistants at home:  Google Home Max. It’s a pricey and comparatively large and hefty but sounds great Apple HomePod. Also pricey. Beautiful, elegant, and...

Digital assistants are the future of chatbots. Up to now, chatbots have focused on narrow scope user initiated conversations to automate simple business tasks like in customer service or marketing interactions. Digital assistants, like a human assistant, are user oriented in that they can assist with many different tasks rather than being constrained to a narrow user case. This is a huge step forward towards true conversational assistants that so far we’ve only known from science fiction. Oracle Digital Assistant (ODA) is Oracle's next generation bot platform that enables project teams to follow a modular approach in building composite chatbots published to multiple conversation channels. Like a good and trusted friend, Oracle Digital Assistant chatbots assist users in a variety of tasks, which could span a single or multiple business domains. This article provides a technical overview of Oracle Digital Assistant as it had been released in November 2018. It explains the concept and features, explores the development environment and introduces the overall architecture.

Digital assistants are the future of chatbots. Up to now, chatbots have focused on narrow scope user initiated conversations to automate simple business tasks like in customer service or marketing...

It happens in a chatbot interaction that a user scrolls the conversation history displayed in the messenger client and selects a list or button action that is no longer in scope for the current conversation. For example, in a travel booking chatbot, a user may have selected a destination and provided the name to be printed on the tickets When asked to select a free gift voucher, she then scrolls the message history and selects a different destination. Changing a travel destination should not be a problem, you may think, and for most of the time you are right. But changing the travel destination may have an impact to other parts of a conversation. For example, a selected destination may not qualify for a voucher, or in the process of booking the travel, the user selected a local agency for an airport pick-up. Chatbots don't control the messenger and therefore cannot prevent users from selecting out-of-scope actions. So the best thing it can do is to find a solution that doesn't upset the user and also does not mess with the business task at hand. In Oracle Digital Assistant, out-of-scope actions are referred to as an out-of-order messages. While there is a default implementation for how a skill bot handles out-of-order messages, there also is an option for bot designers to customize the behavior, either for the bot as a whole or just for the current state in a conversation. In this article I explain how out-of-order messages are handed in Oracle Digital Assistant and how you can customize the behavior.

It happens in a chatbot interaction that a user scrolls the conversation history displayed in the messenger client and selects a list or button action that is no longer in scope for the...

We are delighted to announce that the next major release of our AI powered Digital Assistant platform, version 18.4.3, is now generally available. This release represents a major evolution of our chatbot platform; it enables our customers to not only create and deliver multiple chatbots, but they can now organize them as multiple skills that are available via a single digital assistant. Users then access a suite of chatbot capabilities as if they were one composite service. The skill bots can also coordinate together to offer synchronized services. For example, instead of just booking an airplane ticket, a digital assistant built with this new version of our platform could coordinate the flights, rental cars, hotels and restaurants for a business trip. New capabilities of this release include: Create and deploy digital assistants that orchestrate access to multiple skill bots. Create and deploy individual skill chatbots. Coordinate activity routing between multiple chatbots. A skill store for pre-built Oracle SaaS service skill chatbots, e.g. ERP, CX, HCM. Initiate conversations with users proactively. Usage and performance analytics. Digital Assistants With this release, our chatbot platform now supports deployment of digital assistant (DA) chatbots that orchestrate multiple skill bots as a single integrated service. DA bots automate registration of skill bots via one-click selection and assembly from a skill bot store and catalog. Once registered, the DA bot intelligently (via AI and other algorithms) rout user requests to the right skill bots. Requests by users for help or about the DA’s capabilities are handled by built-in services which deliver synopses of each skill chatbot’s capabilities. Figure 1. Digital Assistant and Skill chatbots   With DA bots, users can access multiple services delivered by specialized skill bots from within one conversation. For example, a new employee in need of on-boarding could procure a laptop, register for training courses, set up their health benefits and order business cards. Just as with a human service provider, the DA bot intelligently handles each of these requests in sequence, even if they are all requested at once. More details here. Skill Chatbots Skill chatbots in this release are an evolution of the stand-alone chatbots available in previous versions of our chatbot platform (AMCe). All previous capabilities are carried forward. Skill chatbots can still be deployed stand-alone with this release if needed. New features include: Additional skill chatbots now have a built-in node container in which to execute custom code to support purpose-built logic and for integration with back-end applications, SaaS, databases and other services. Slot filling is now simplified. Only one dialog component, System.ResolveEntities, is required to handle all possible slot filling scenarios for an intent. For example, when ordering a pizza, the one component can handle prompting for crust type, pizza size, toppings and extra cheese. Composite bag entities now support validation logic, multiple random prompting and the ability to prompt for non-entities (strings, attachments, geo coordinates.) Users can now go back to previous list responses in a dialog and re-select list options to direct a dialog in a different direction. With new support for Webviews, a skill chatbot can now call out to an external web application while passing input data to and received output data from that app. Enterprises with existing web apps can now access them from within skill chatbots. AI-driven User Request Routing Along with Digital Assistant and skill chatbots, this release includes an AI-driven user request routing capability that enables a digital assistant to route incoming user requests to the most appropriate skill bots registered with the digital assistant. This capability requires no coding and no specific initial configuration and it’s available OOTB. Not only does it handle initial user requests, but it can also handle non-sequitur (unexpected user statements), allowing the digital assistant to momentarily pause a conversational thread, respond to the user’s non-sequitur, then return to and complete the prior interaction. For example, a new employee could start a conversation to procure a laptop, then realize they forgot their office location. They could then interrupt the procurement conversation with a request for their office location address. The digital assistant would then route the user’s address request to a location skill chatbot, then bring them back to finish the laptop procurement request once they know their office address. Experience designers can also tune and optimize intent routing and non-sequitur handling via a small set of hyper-parameters if needed.   Figure 2. User request routing Skill Store and Catalog Included in this release is a Skill Store from which administrators can add new skill chatbots to digital assistants to improve their capabilities. As new skill chatbots are added to a digital assistant, it gets smarter and more capable. Over the next 12 months and into the future, Oracle will be adding new skill chatbots to the Skill Store that correspond to Oracle’s SaaS service offerings. These skill chatbots will be available to any licensee of the Oracle Digital Assistant. Additionally, a skill catalog will allow customers, partners and others to create and add their own new skill chatbots that can be then versioned and reused across multiple stand-alone and digital assistant use cases. Figure 3. Skill Store and Skill Catalog App-initiated Conversations Digital Assistant and skill chatbot now allow conversations with chat-bot users to be initiated by back-end systems. A back-end system sends an event notice to specific chatbot, which then reaches out to one or more users to start conversations. Events are sent to a chatbot via a RESTful API provided by the Oracle Digital Assistant cloud service. Initiated conversations can optionally receive data from the source of the event or even other sources. For example, with this new feature, a user could be alerted by a procurement bot that the new laptop they ordered is no longer available and then offer alternative equivalent laptops that could be substituted. Currently available via Twilio. Figure 4. App-initiated Conversations Usage and Performance Analytics Delivering a superior conversational experience requires on-going monitoring of user activity to assure all dialog flows result in successful completion. This release of the Oracle Digital Assistant platform now includes Bot Insights which provides analytics to track skill chatbot behavior and performance that can be used to tune performance and head off possible issues. Administrators can monitor conversation trends over time, track execution paths, determine the accuracy of your intent resolutions, and use moderated self-learning to augment bot efficiency. Analytic capabilities include: Overview report: Depicts utilization statistics, conversation trends, engagement channels as well as completed/abandoned conversations and intents, based on the time period, channels, and locale selected. Intents report: Shows the accuracy of intent resolution and identifies areas for improvement. For instance, the number of conversations where an intent was guessed but did not quite meet the threshold of being resolved. Pathing reports: Shows user journeys through the bot. Use this to see where users are abandoning the conversation and the reasons. Conversational debugging: Inspect conversations transcripts to assess conversational efficacy. Retraining capabilities: Use moderated self-learning to improve the bot. Automatically detect outlier phrases and suggest options to tune the bot. Data collection is automatic; reports are populated during bot execution. Fully integrated with the existing Tester UI, so you can generate analytics events during testing. Figure 5. Bot Insights Overview Report Additional information on the Oracle Digital Assistant platform can be found here: Product overview: https://cloud.oracle.com/en_US/digital-assistant Product launch blog: Introducing Oracle Digital Assistant Documentation: https://docs.oracle.com/en/cloud/paas/autonomous-digital-assistant-cloud/index.html Tutorial videos: https://www.youtube.com/playlist?list=PL2ux0DjE-RYc5TZhb-20jY4kJQGbqXr_f    

We are delighted to announce that the next major release of our AI powered Digital Assistant platform, version 18.4.3, is now generally available. This release represents a major evolution of our...

In a previous blog pos, I explained how to crate custom component service for deployment to the local component container in Oracle Digital Assistant skill bots in minutes. This tutorial is a follow up of the previous blog post and explains how you can debug custom component services you deploy later to the local custom component container.

In a previous blog pos, I explained how to crate custom component service for deployment to the local component container in Oracle Digital Assistant skill bots in minutes. This tutorial is a...

For many, chatbots are a synonym for artificial intelligence and service automation using voice and free text input. Oracle Digital Assistant is Oracle's next generation bot platform that enables developers to follow a modular approach in building composite chatbots for exposure on multiple conversational channels and messenger clients. In regards to supporting voice, Oracle Digital Assistant does not provide its own voice-to-text transformation but relies on 3rd party technology. This article explains how to use Oracle Digital Assistant with Amazon Alexa. The code samples provided in the text and for download also give you an idea how webhooks can be usd to integrate other voice technologies with Oracle Digital Assistant.

For many, chatbots are a synonym for artificial intelligence and service automation using voice and free text input. Oracle Digital Assistant is Oracle's next generation bot platform that...

Mastering custom components is an important, if not critical skill to have. This first tutorial on custom components in Oracle Digital Assistant guides you through the creation of your first custom component service.

Mastering custom components is an important, if not critical skill to have. This first tutorial on custom components in Oracle Digital Assistant guides you through the creation of your first...

Oracle Digital Assistant supports different types of entities that are extracted from user input by the NLP (natural language processing) engine. Value list is a popular type in which you define a list of values and synonyms to be extracted from user input. In Oracle Digital Assistant, value list entities can be defined as static or dynamic values. Value list entities, however, can be used to create list of values for a bot user to select from. In this article I explain two solutions for building such a list and how you can use common synonyms to turn lists into smart filtered lists.

Oracle Digital Assistant supports different types of entities that are extracted from user input by the NLP (natural language processing) engine. Value list is a popular type in which you define a...

You've heard it alluded to on this blog for the past several weeks, but today, it's finally here: at Oracle OpenWorld 2018 this morning, Oracle launched Oracle Digital Assistant!  While we've been investing in chatbots for some time now, Oracle Digital Assistant represents the next generation of conversational AI for the enterprise that will allow employees to work smarter and more productively! While simple chatbots can engage users by understanding the intent of the conversation and help them with one specific task, one Oracle Digital Assistant can be trained to support chatbot "skills" from multiple backend knowledge domains (e.g. CRM and HCM applications, as opposed to one or the other) and allow end users to engage with these domains simultaneously in a conversational manner.  This allows users access all the data they need in one conversation without having to engage multiple chatbots, and also allows users to switch topics mid-conversation (as people often do when chatting with each other) without having to worry that the assistant fail to understand the context of their questions. Many current chatbots also engage only when they are spoken to, placing the responsibility of accessing timely information squarely on the user.  Oracle Digital Assistant changes this by proactively initiating conversations with the user based on previously scheduled events such as alerts or appointments.  “This is the next evolution of chatbots and a major milestone in delivering a smart digital assistant for the enterprise,” said Suhas Uliyar, Vice President of AI, Bots, Mobile, Product Management, Oracle. “Oracle Digital Assistant has the power to transform organizations, helping our customers achieve greater productivity and enriched user experiences.” You can read the full press release from Oracle here, and for additional media coverage, check out these articles here and here. To learn more about Oracle Digital Assistant, visit oracle.com/da and to sign up for a free trial, go to cloud.oracle.com/digital-assistant.

You've heard it alluded to on this blog for the past several weeks, but today, it's finally here: at Oracle OpenWorld 2018 this morning, Oracle launched Oracle Digital Assistant!  While we've been...

On October 22nd, as you walk into Moscone Center for OpenWorld 2018, you might wonder how you'll be able to choose from all the fantastic sessions that are scheduled this year.  Fortunately, we're here to help! First, check out the Oracle Focus On: Digital Assistants and Mobile web document that lists all of the exciting Digital Assistant and Mobile presentations, hands-on labs, and demos at #OOW18.  This document will be a fantastic reference for you while you're at OpenWorld.  Between sessions, don't forget to stop by our three demo booths located in the "Oracle" area of The Exchange on the lower level of Moscone South, where you'll be able to learn about, and try out, our latest mobile and conversational AI products! Next, check out the nine sessions that you won't want to miss: Monday, Oct. 22nd, 2018 PRM4587: Beyond The Screen: From Chatbots to Your Own Digital Assistant Location: Moscone West – 3020 Time: 3:45pm Speakers/Customers: SRF Limited Get excited: Oracle VP Suhas Uliyar highlights Oracle's AI and Digital Assistant strategy, and then will be joined on stage by Indian diversified manufacturing company SRF, where they will discuss how AI and intelligent, conversational interfaces will transform the enterprise. PRM5766: Oracle's Multichannel Mobile Cloud Strategy & Roadmap Location: Moscone West – 3020 Time: 5:45pm Speakers/Customers: Los Angeles Unified School District Get excited: Learn how Los Angeles schools are using Oracle's Mobile Cloud to digitally transform the education sector in Southern California.   Tuesday, Oct. 23rd, 2018 PRM5775: Oracle Digital Assistant, Chatbots, Conversational AI: Strategy and Roadmap Location: Moscone West – 3020 Time: 11:15am Speakers/Customers: Eric Rogge, Oracle Product Management - Digital Assistant Manish Parekh, Oracle Sr. Director of Software Development Get excited: Learn about all of the exciting new, and upcoming features of Oracle Digital Assistant. Eric and Manish will dive into how Digital Assistant has evolved from Oracle Intelligent Bots, and how it will power the next wave of innovation within the enterprise. CAS4590: Oracle Digital Assistant/Intelligent Bots Customer Panel Location: Moscone West – 3020 Time: 4:45pm Speakers/Customers: Mutua Madrid Open SRF Limited Fishbowl Solutions Get excited: Hear from Oracle customers Mutua Madrid Open and SRF Limited, and from Oracle partner Fishbowl Solutions, as they describe in detail how they used the Oracle Intelligent Bots / Oracle Digital Assistant to solve real-world business problems. CAS3373: Exelon's Best Practices fora 10 Customer Chatbot Implementation Location: Marriott Marquis - Yerba Buena Level, Nob Hill C/D Time: 4:45pm Speakers/Customers: Exelon Get excited: Exelon is the largest electric power utility in North America, with 10 million customers. In this session, learn best practices for how Exelon quickly deployed chatbots from Oracle Cloud Platform across multiple channels, such as Facebook Messenger, Siri, and Alexa. CAS2468: Delivering Modern Customer Experience by Successfully Adopting Chatbots and AI Location: Park Central Hotel – 3rd Floor, Stanford Room Time: 5:45pm Speakers/Customers: Rubicon Red/University of Adelaide Get excited:  Oracle partner Rubicon Red will discuss how Oracle customer University of Adelaide was able to leverage the chatbot feature in Oracle Mobile Cloud to provide a real-time, scalable, and intelligent messaging platform to handle peak call loads and improve customer experience for prospective students.   Wednesday, October 24th, 2018 CAS4588: Oracle Mobile Cloud Customer Panel Location: Moscone West – 3020 Time: 11:15am Speakers/Customers: American Red Cross Exelon eProseed/Connexxion Get excited:   Hear from customers who have used Oracle Mobile Cloud to create compelling mobile applications that have transformed their businesses! KEY3879: Oracle Cloud - Simply Better Location: Moscone North – Hall D Time: 2:00pm Speakers/Customers: Larry Ellison, Executive Chairman & CTO, Oracle Get excited:   Come hear Larry Ellison speak about the benefits of Oracle Cloud, and keep your eyes peeled for a very cool, and relevant, demo! PRM6676: OneBot - A Comprehensive Case Study on Enterprise Digital Assistants Location: Moscone West – 3016 Time: 3:45pm Speakers: CapGemini Get excited:   In this session see a case study on how an enterprise benefits from a digital assistant. OneBot is designed to support and help employees on their daily professional life, be it onboarding, HR queries and activities, IT help, meeting scheduling, or just simply booking their timesheets globally in different languages.   Follow us on Twitter @OracleMobile throughout #OOW18 for the latest updates, and for more information on Oracle Mobile Cloud and Oracle Digital Assistant, don't forget to check out oracle.com/mobile and oracle.com/da.

On October 22nd, as you walk into Moscone Center for OpenWorld 2018, you might wonder how you'll be able to choose from all the fantastic sessions that are scheduled this year.  Fortunately, we're...

It seems these days that hardly a week goes by without an interesting announcement surrounding artificial intelligence.  From creating better photos to fighting cancer, AI is continuing to change lives, not only from a consumer standpoint, but also in terms of how businesses, and specifically enterprise businesses, interact with both consumers and their own employees.  Enterprises need to move quickly in order to take advantage of the automation and augmentation benefits that AI has to offer, but in moving quickly, AI can raise just as many questions and can catch enterprises in just as many pitfalls as it can offer transformational business solutions.  So how can a business navigate the ever-expanding world of artificial intelligence in the workplace?  By listening to this podcast, businesses can learn where AI currently is in the enterprise, and how it is likely to evolve, thus preparing them well as they continue their digital transformation journey. In only 15 minutes, Oracle Principal Product Marketing Director Kellsey Ruppel and Oracle Vice President of AI, Bots & Mobile Suhas Uliyar answer: What does the world of AI currently look like in the enterprise space?  Is it a strategic initiative or is it being ignored, and how can enterprises get value out of AI? What's next and exciting in the world of AI and chatbots?  Are chatbots limited in scope and capability? If so, how can employees use chatbots efficiently when a business might have deployed several dozen to serve different functions? How can the concept of a digital assistant help? How secure is using a digital assistant in your enterprise?  How does security work when using a digital assistant? Why should businesses consider (or even listen to) Oracle when it comes to AI, chatbots, and digital assistants? You can listen to the full podcast here, and if you are going to Oracle OpenWorld 2018 in San Francisco, you can check out "Beyond the Screen: From Chatbots to Your Own Digital Assistant" in Moscone West, Room 3020 at 3:45pm on Monday, October 22nd. Don't forget to follow @OracleMobile on Twitter for announcements throughout Oracle OpenWorld.

It seems these days that hardly a week goes by without an interesting announcement surrounding artificial intelligence.  From creating better photos to fighting cancer, AI is continuing to change...

Permission changes to Facebook Messenger preventing access to user firstname and lastname

Permission changes to Facebook Messenger preventing access to user firstname and lastname

Authored by Suhas Uliyar, Oracle Vice President - AI, Bots & Mobile   The meteoric rise of chatbots, and proof in the last year that this rise is not a fad, has given end users a natural way to engage with business via a conversational user interface and has given brands new purpose in providing better customer service. As the brand-customer relationship has grown and has become even more intertwined, enterprises are beginning to see success with the deployment of these bots. For example, Bank of America released Erica – a chatbot for consumer banking in early March, 2018 that had an adoption of 1 million users in the first 3 months of going live.  Mutua Madrid Open, an Oracle customer, became the first ATP World Tour Masters 1000 and Premier WTA tournament to incorporate an AI-equipped chatbot to improve communication with tennis fans. Implemented with Oracle Cloud Platform, the chatbot, named “MatchBot,” used AI to maintain natural conversations that provided fans with information on the event, players, and results, as well as details on hospitality services, discounts on merchandise, ticket sales, access, and parking. The University of Adelaide, another Oracle customer, created a chatbot on Oracle’s cloud platform to ease students’ pain during the university application process. On just the first day the bot was live, prospective students conducted an estimated 2,100 unique conversations with the chatbot, which led to a 40 percent reduction in calls to the University’s customer service line – and more impressively, a 47 percent drop in calls during the critical first three hours.  In turn, this reduced the wait time for queries made via telephone – from an average of 40 minutes down to about 90 seconds, and 60% of student users rated their experience as “awesome.”. These are just several such examples of successful business implementations using first generation, AI-powered, conversational interfaces.   So what’s next? The next generation of conversational interaction is Conversational Intelligence. Today’s conversational interactions are either user-initiated conversations or notifications about pre-programed actions (e.g. Alexa notifying you that your order has been delivered or Siri waking you up in the morning because you have pre-set an alarm.) Conversational Intelligence, however, is the ability for an interface to “know” a user, learn and understand their moments, actions, behaviors and preferences, and recommend, predict or act on behalf of the user – essentially functioning as your own digital assistant. To put this in more simple terms, let’s draw an analogy to part of my job, which includes traveling to meet customers. In my role as VP for Product Management, I have the pleasure of meeting our global customers and partners, and that's by far the best part of my travel experience. The reason, of course, is that the logistics associated with business travel can be difficult and time-consuming so any help is good. When my admin started several years ago, she didn’t know any of my travel preferences and I often had to initiate a conversation with her to book my travel. She would ask me my preferred airline, hotel, check on any personal commitments I had, schedule prep calls with local sales teams, make sure I had the correct customer briefing documents, and then would book my travel. On the day I left, I would ask her to book Lyft to the airport and so on. These conversations occurred a few times, but soon enough, she knew what to look for in my emails, which schedules to check (personal and business) and which flights and hotels to book based on my preferences, leaving me only to confirm her choices. As more time passed she did not even need me to confirm her selections as they were pretty perfect. In this example, my admin learned to take actions on my behalf by observing my traits, behaviors, and habits, which she learned first by talking to me, and then by incorporating both her knowledge of our conversations and my validations of her actions into an overall understanding of my preferences that was accurate enough for both of us to trust each other when making travel decisions. Today, end users are having similar conversations with bots that may seem simple, but these conversational interactions are creating important data. Over time the incorporated AI built into these bots will learn from these data-heavy interactions, from aggregated data across, and from outside of, the enterprise will use this accumulated “knowledge” to become a functioning “digital” assistant. This is the future of where AI-powered chatbots are headed; a Digital Assistant for every consumer and every employee of a company. What is needed to have a Digital Assistant for every consumer / employee?   Naturally Conversational: Language is incredibly complex and the assistant needs to understand user goals/intentions in every part of the conversation – real meaning, contextual, personalized & human like. Knowledge, Memory & Reasoning – Users expect the assistant to behave like humans. The assistant’s "brain" needs to have semantic understanding of various knowledge domains, needs to understand events, needs to have long/short term memory, and needs to be able to make decisions and execute/orchestrate actions. The Assistant is for THE User – It needs to know users really well, their roles, behaviors, traits, preferences, their interactions and activities across various apps/channels. The assistant also needs to know how and when it should communicate with the user, and recommend actions based on their real-time needs. Proactive – The assistant should watch out for things the user cares about and either take actions autonomously or communicate with the user. Oracle's platform will provide capabilities to enable an assistant’s skills to be truly intelligent and proactive. Act as True Agents– The assistant should know how to get things done with minimal help – e.g. create a plan dynamically based on current situation/context, reason with data to decide and execute actions. Multi-Channel - The assistant needs to work seamlessly across various channels. This includes the ability to identify the same user in multiple channels, maintain state across channels and have a conversation with a user using multiple channels at the same time (e.g. for voice use cases where the medium itself is limited/constrained.) Digital Assistant Platform for Skills Development – Skill developers are a critical part of the ecosystem to make the assistant successful. We need developers to be able to develop skills that are intelligent, can detect complex situations, retrieve context from the assistant and be proactive in nature.   In my next blog, we will explore in detail how the Oracle Digital Assistant delivers on these requirements.  First however, please go and listen to my podcast on the topic of Digital Assistants, which will be released on Wednesday, October 10th, here.  It's short, easily digestible, and gives further context on Digital Assistants and where AI is going in the Enterprise.

Authored by Suhas Uliyar, Oracle Vice President - AI, Bots & Mobile   The meteoric rise of chatbots, and proof in the last year that this rise is not a fad, has given end users a natural way to engage...

In Oracle Digital Assistant (formerly known as Oracle Intelligent Bots), user input can be validated in two forms - Based on variables that are based on entities - manually for variables that are not entity bound In this article I explain how to use Apache FreeMarker template expressions to validate user input.

In Oracle Digital Assistant (formerly known as Oracle Intelligent Bots), user input can be validated in two forms - Based on variables that are based on entities - manually for variables that are not...

Oracle Digital Assistant allows you to define error handlers on individual dialog flow states in a conversation, or globally, as a default transition in the dialog flow header. In this article I'll show you how you can get the best of two worlds: A global error handler that allows you to handle local state errors.

Oracle Digital Assistant allows you to define error handlers on individual dialog flow states in a conversation, or globally, as a default transition in the dialog flow header. In this article...

A webhook is a programming interfaces implemented by a system on the web for other programs subscribe and to receive automated notification in case anything of interest happens. One such system is chatbot. Users "register" for a chatbot through a messenger client and by sending messages to the bot. The bot then resolves the request, processes it and returns a response that the original sender receives. Webhook clients are like adapters that dispatch and manage conversation between a user and a remote system. In Oracle Intelligent Bots, channels allow bot designers to expose the bot functionality to a specific type messenger client. Underneath channels are webhooks. Channels, like Facebook, Web, iOS, Android, WeChat (upcoming) and more that are in development, are referred to as "native channels" Native channels are webhook implementations that exist and that you, as the bot designer, don't have to code for. For integrating messengers that Oracle Intelligent Bots doesn't have a native channel for, you use the generic Webhook channel. The Webhook channel in Oracle Intelligent Bots opens up the Oracle bots platform for any messengers client. All you need to do is to write the webhook implementation. In this article, I explain the basic steps of creating a webhook client using the Oracle Bots Node.js SDK available on GitHub and npmjs. In future articles I will use this article as a starting point for explaining how to integrate Oracle Intelligent Bots with Messenger services like Alexa and Google Hangouts.

A webhook is a programming interfaces implemented by a system on the web for other programs subscribe and to receive automated notification in case anything of interest happens. One such system is...

In the Oracle Intelligent Bots dialog flow editor, how often is it that you find yourself in the need to copy one or more context variables names to the System.ResetVariables or System.CopyVariables components. Especially, the System.ResetVariables component is frequently used to ensures context variables are reset before rerunning a conversation of parts of it. So instead of copying one context variable name after the next, which is cumbersome to do, you can use the ctrl-key and a double click.

In the Oracle Intelligent Bots dialog flow editor, how often is it that you find yourself in the need to copy one or more context variables names to the System.ResetVariables or System.CopyVariables...