AAR Corp. is a global aviation services company that operates in more than 100 countries. It works with both government and commercial customers, and fields requests that range from aircraft maintenance and parts orders, to fleet logistics and even airlift services. With many different customers depending on its expertise, and with millions of transactions flowing through its systems every day, AAR knows that it needs to make intra-company communication and access to information and processes as easy as possible for its employees. Rather than replacing a mix of legacy back-end systems, or using significant IT resources to create new analytics and communications dashboards, AAR is building prototype chatbots using Oracle Mobile Cloud Enterprise (MCE). These intelligent chatbots use natural language processing and artificial intelligence to understand employee inquiries in context, respond to employees with relevant answers based on information provided from connections with AAR's current back-end systems of record, and then learn from the questions they were asked in order to better anticipate and respond to future queries. This allows AAR employees to find answers to questions through their preferred communication channel (mobile messaging), and saves the company from quickly having to replace costly IT infrastructure in order to stay current with modern employee expectations.
Serdar Yorgancigil, VP of MRO Soultions and User Experience at AAR notes that "chatbots [are] a great opportunity to provide information to people who typically don't use our systems, like our senior management, VPs, and general managers... [they ask] unique, one-off questions that [they] may never ask again in that same context." Indeed, different users rarely will ask for information in exactly the same way so having a chatbot that can understand nuanced variations of the same question, and having one that can remember the context of an ongoing conversation, is extremely helpful. "Once you start having a chatbot conversation, and it’s established that you’re dealing with the Oklahoma facility, if a couple of questions later you just say, ‘Give me the aircraft status,’ it knows that we’re in the context of Oklahoma and applies it as a filter, as opposed to asking you again “would you like to get status for Miami, Oklahoma, Indianapolis,” says Yorgancigil.
AAR says it that at first, it will probably deploy its newly-minted prototype bots on Facebook Messenger and on its own internal system, but eventually, it plans to connect additional bots to additional back-ends and release them through additional channels. Oracle Intelligent Bots allows users to connect to back-end systems easily through APIs, and to write code only once while deploying onto many channels, making it fairly easy for a company like AAR to test and scale employee communication and information gathering as its needs change. To learn more about AAR's plans for chatbots, and about Oracle Mobile Cloud Enterprise, you can read the full Forbes article here.