Enabling Natural Language Queries in Oracle E-Business Suite with OCI Generative AI

Oracle’s new prototype solution integrates OCI Generative AI with Oracle E-Business Suite (EBS) 12.2 to allow users to run natural language queries (NLQ) on EBS data. It uses an Oracle APEX application embedded in EBS, which sends user questions (e.g., “show delayed work orders”) to an Autonomous Database (ADB), which in turn uses Oracle’s Select AI to call an LLM that generates the correct SQL. The SQL runs on the EBS DB and returns results instantly—no SQL knowledge needed.

Image Source: Oracle Documentation.

Key Benefits:

• Conversational Data Access: Ask questions in plain English.

• Reduced SQL Dependency: AI generates the SQL for you.

• Domain-Based Accuracy: Uses AI Profiles like HCM, Manufacturing, etc.

• Secure by Design: No EBS data leaves your environment. RBAC and VPD enforced.

• SQL Visibility: Optional “Show SQL” feature for debugging or validation.

High-Level Architecture:

• APEX UI: Embedded in EBS OA Framework, honors SSO and security.

• Autonomous DB: Hosts AI Profiles (domain-specific metadata).

• OCI GenAI: Translates natural language to SQL.

• EBS DB: Executes the final SQL using secured NLQ views.

Implementation Overview:

1. Setup Prereqs: EBS 12.2, APEX, ECC patches, OCI GenAI subscription.

2. Configure ADB: Create schema, install AI Profiles, setup REST/OAuth or DB link.

3. Deploy APEX App: Import app, set URLs, and test connectivity.

4. Integrate with EBS: Create function/menu in EBS, embed APEX page.

5. Secure Access: Use EBS roles, RBAC, VPD. No sensitive data is exposed.

This solution is a powerful step forward for self-service EBS analytics—bridging legacy ERP with modern GenAI. It’s ideal for Apps DBAs and OCI Architects looking to explore AI-assisted user experiences inside EBS.

Read more at : https://blogs.oracle.com/ebstech/post/enabling-natural-language-query-of-ebs-122-using-oracle-generative-ai-now-available

• Author
• Recent Posts

Brijesh Gogia

I’m an experienced Cloud and AI Architect with over 19 years in Oracle Applications, Databases, and Cloud ecosystems. My work spans large-scale, global projects where I’ve designed and optimized solutions across both Oracle and non-Oracle stacks—on-prem and in the cloud. Lately, my focus has shifted toward integrating AI into enterprise architectures, leveraging GenAI, automation, and data intelligence to drive performance, resilience, and modernization. I’m passionate about exploring emerging AI tools, agentic workflows, and practical use cases—and I'm fortunate that my role gives me space to experiment and share my learnings.

Latest posts by Brijesh Gogia (see all)

• GitHub Copilot Coding Agent - May 20, 2025
• Enabling Natural Language Queries in Oracle E-Business Suite with OCI Generative AI - April 20, 2025
• Agentic AI basics – A Simple Introduction - February 8, 2025