Introduction
AI Functions in Oracle Analytics Cloud (OAC) let workbook authors apply large language models directly to row-level data. Instead of exporting data to a separate application, authors can generate labels, summaries, classifications, filters, and group-level narratives inside analytics content.
AI Functions in Oracle Fusion Data Intelligence (FDI) can add practical generative-AI enrichment directly to trusted business data, from text classification and tag generation to summaries and group-level narratives.
This article highlights suitable FDI use cases, model-source considerations, and patterns for choosing and applying the right AI Function responsibly.
Examples for FDI Prebuilt Subject Areas
The following recommendations apply to prebuilt FDI subject areas. Exact subject-area availability, preview status, folder names, and column names vary by release and enabled functional area.
For prebuilt FDI subject areas, use an OCI-sourced Generative AI model registered in Oracle Analytics. Oracle Autonomous AI Lakehouse profile assets can process only datasets sourced from the same database through the same connection.
| FDI Subject Area | Function | Example |
| HCM – Talent Acquisition | AI_GENERATE | Extract required skills from each requisition. |
| HCM – Talent Acquisition | AI_AGG | Summarize hiring-demand themes by department or job family. |
| HCM – Workforce Absence Management | AI_AGG | Summarize absence patterns by department and month without identifying workers. |
| HCM – Performance Management | AI_GENERATE | Categorize goals into themes such as growth, efficiency, or customer experience. |
| HCM – Goals and Career Development | AI_AGG | Identify common development priorities across a business unit. |
| HCM – Learning Items and Enrollments | AI_GENERATE | Generate consistent professional-skill tags from learning items. |
| HCM – HR Helpdesk Requests Overview | AI_GENERATE | Classify request summaries into a controlled topic list. |
| Financials – GL Detail Transactions | AI_GENERATE | Standardize or categorize journal-line descriptions. |
| Financials – GL Detail Transactions | AI_AGG | Explain period activity drivers by account, cost center, or ledger. |
| Financials – EXM Employee Expenses | AI_GENERATE | Categorize expense purposes or normalize merchant descriptions. |
| Procurement – Requisitions | AI_GENERATE | Suggest a purchasing category from an item description. |
| Procurement – Spend | AI_AGG | Summarize spend themes by supplier or purchasing category. |
| PPM – Project Costs | AI_AGG | Summarize project cost drivers and recurring expenditure types. |
Example: Summarize GL activity drivers
AI_AGG(
‘Source: ‘ || JOURNAL_SOURCE ||
‘; Category: ‘ || JOURNAL_CATEGORY ||
‘; Description: ‘ || JOURNAL_LINE_DESCRIPTION ||
‘; Net amount: ‘ || CAST(NET_AMOUNT AS VARCHAR(40)),
‘Summarize the principal activity drivers for this account and period. Identify recurring descriptions and unusually large categories. Don’t claim fraud or error. Return no more than four sentences.’,
<MODEL_ID>
)
Group the workbook by ledger, fiscal period, natural account, cost center, or another business grain. Filter to a manageable transaction set before invoking the model.
Example: Categorize expense purposes
AI_GENERATE(
‘Expense type: ‘ || EXPENSE_TYPE ||
‘; Merchant: ‘ || MERCHANT_NAME ||
‘; Business purpose: ‘ || BUSINESS_PURPOSE,
‘Classify the expense into exactly one category: Airfare, Lodging, Ground Transport, Meals, Office Supplies, Training, Professional Services, or Other. Return only the category.’,
<MODEL_ID>
)
Use the generated category as an analytical tag, not an automated approval or rejection decision.
Choose the Right AI Function
AI_GENERATE: Create one text result per row
Use it for enrichment, summarization, classification, rewriting, explanation, and tag generation.
AI_GENERATE(COMMENT_TEXT,
‘Classify this comment as positive, negative, or neutral. Return one lowercase word.’,
<MODEL_ID>)
AI_FILTER: Keep rows that satisfy a semantic condition
Use it when the condition is easier to express in natural language than with deterministic rules.
AI_FILTER(‘Is this request urgent?’, REQUEST_TEXT, <MODEL_ID>)
AI_AGG: Generate a response across a group of rows
Use it for grouped summaries or themes. Keep the group size and input text controlled to manage latency and token use.
AI_AGG(REVIEW_TEXT,
‘Summarize these reviews in two sentences. Return only the summary.’,
<MODEL_ID>)
Call to Action
Start with a narrow enrichment use case and validate it on a small workbook sample. Once reliable, expand the pattern to data flows, preparation, and semantic-model calculations on your instance.
See the full documentation set for FDI on Oracle Help Center. For AI model configuration and registration in OAC, refer to the Step-by-Step Guide to Using AI Functions in Oracle Analytics Cloud and Tips and Troubleshooting for Using AI Functions in Oracle Analytics Cloud for troubleshooting.
To learn more about AI Functions in OAC, watch the demo video.
If you have questions, post them in the Oracle Analytics Community and we’ll follow up with answers.