DataFramed #316 Enterprise AI Agents with Jun Qian, VP of Generative AI Services at Oracle
93 snips
Aug 18, 2025 Jun Qian, Vice President of Generative AI Services at Oracle, dives into the transformative potential of AI agents and chatbots. He discusses the evolution from traditional chatbots to advanced systems that utilize large language models and enterprise knowledge. Exploring the challenges of managing knowledge bases, Jun emphasizes the need for effective governance before deployment. He also addresses metrics for measuring AI effectiveness and future innovations in coding and robotics, highlighting Oracle's ambitious Stargate project.
AI Snips
Chapters
Books
Transcript
Episode notes
Slack RAG Bot Replaced Many Support Tickets
- Oracle built a Slack RAG bot that answered laptop and login support questions, replacing many human tickets.
- The simple RAG support implementation saved significant support effort and delivered quick wins.
Use Deflection And User Signals As Metrics
- Track support-specific KPIs like deflection rate to judge chatbot effectiveness.
- Use user actions (clicks, 'talk to human') as strong signals of success or failure.
Partner With Compliance From Day One
- Work with security, legal, and compliance teams early and use existing enterprise policies for AI governance.
- Integrate agents with current entitlement and authentication systems to avoid overexposure of data.
