IDUG NA 2026

A look at new SQL Extensions delivered in releases leading up to 12.1 along with what is new in 12.1 itself. We will take a dive into how Db2 is being extended with AI capabilities including ability to access external AI models through SQL. Learn how Db2 is being extended with vector store capabilities and integrating with both open data formats and open table formats through data lake table extensions.

After completing an assessment of IBM’s Bob, using Db2 for z/OS use cases, I was amazed and disappointed. This introductory session summarizes key items found during the assessment. I’ll demonstrate a Db2 for z/OS client and a System Profiles GUI created, both without writing a single line of code.

Twenty-one years ago, I joined IBM as a software developer. I knew nothing about AI. Today I am the AI Architect and Master Inventor of IBM Db2, leading vector search, in-database machine learning, and LLM integration.
How did the journey happen? Not the way I thought it would be. 

In this talk, I will share the blueprint I wish someone had given me earlier in my career: seven skills that took me from software engineer to AI architect. I will be honest about which ones moved me forward and which I learned too late. Some are technical. Most are not. They include learning AI from mentors, building communication as a craft, and learning to focus in an attention-fractured industry.

If you are an experienced software engineer wondering how to make the move into leading AI work, this talk is for you.

Organizations that have optimized institutional data through governance, stewardship, and quality management are AI‑ready by design. Leveraging that institutional data both internally and externally for competitive advantage opens possibilities at scale never before imagined. This session will discuss:
Tool adoption without data maturity creates risk: Weak data foundations lead to unreliable results, reduced transparency, and diminished business value.AI builds on existing data foundations: Incremental enhancements—such as data scraping, enrichment, and feature refinement—are most effective when layered on curated data stores.Efficient access to data still matters: AI tools need immediate access to data.Data curation presents as a DBA responsibility: DBAs control data curation through standard operating procedures and best practices. Decision engines still matter: AI outputs are only as effective as the decision logic, controls, and context in which they operate.AI is an evolution of data expertise, not a replacement: The role of data professionals becomes more critical, installing guardrails in automation and scalable intelligence.This session reframes AI success as the amplification of long‑standing data discipline. Attendees will gain practical insight into what they are doing today, for better or worse, that is curating data and what approaches they can apply to improve AI positioning. Best practices in database management are not a preparatory step for AI, but translate directly into sustainable AI advantage.