IDUG NA 2026

Discover how Db2’s new DiskANN‑powered vector index delivers fast, scalable similarity search while integrating seamlessly into existing database workflows. We’ll walk through expected performance gains using AWS benchmark results and share practical tuning strategies to help you get the most out of vector search in Db2.

Interested in exploring IBM SQL Data Insights without the effort of installing it on your system or building models from scratch? This session introduces Industry Starter Kits designed to help Db2 for z/OS users quickly evaluate and experience the power of AI-driven insights using pre-built models, sample industry data, and ready-to-run AI queries.
The session features real-world use cases across industries such as finance and insurance, demonstrating how SQL Data Insights can analyze Db2 table data to uncover hidden relationships, detect anomalies, identify unusual transactions, and generate meaningful business insights that may be difficult to find using traditional SQL techniques alone. Attendees will learn how to deploy and load pre-built AI models, execute AI-driven SQL queries, and understand and interpret the results returned by those queries using familiar Db2 workflows and interfaces.
By walking through the industry use cases included in the starter kits, attendees will gain a clearer understanding of what SQL Data Insights is capable of and how AI-driven SQL analysis can be applied to their own Db2 environments. The session is intended to spark ideas for new use cases and help users envision how their existing Db2 data can be analyzed in entirely new ways.
Whether you are new to SQL Data Insights or looking for an easier way to get started, this session provides a practical, hands-on approach to jump-starting your AI journey on Db2 for z/OS.

In this session we will show you how application building with a serverless database gives you superpowers. Serverless databases are built for the AI Era handling the workloads of the future and turning you into a 10X Engineer. We will show you how to develop applications for Db2 from prompt to production and demonstrate how a serverless database tackles AI and Machine driven workloads all while reducing cost and effort. Join us for this groundbreaking session and experience the future of Db2 SaaS services!

The role of the DBA has evolved over the years. As businesses across the globe embrace digital transformation, and customer expectations increase, the traditional rules of engagement must be reconsidered, and the DBA remains a key lynch-pin in the Agile journey to DevOps. This presentation will review the old rules of engagement, and express the importance of communication, trust, embracing change, and automation tools in modern software development in the age of AI.

Db2 now has a complete AI application stack — Vector Storage, Vector Similarity Search, Vector Index, and LLM Integration. Once you know what this stack can do, the natural next question is: what can you build with it? That is exactly what this session addresses. Drawing on industry research and global enterprise adoption data, we examine AI use cases that organisations have already deployed at scale and validated in production. For each, we explain the business problem it solves, how Db2's AI stack maps to the solution, and what implementation looks like — using data most Db2 customers already have. Business leaders will leave with a clear, evidence-backed starting point for AI investment. Developers and architects will leave with a concrete path from proven use case to working implementation. The stack is ready. The use cases are proven. Come find out which ones to build next.

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.

Db2 professionals manage complex and mission-critical data environments where troubleshooting, performance analysis, and knowledge discovery can be time-consuming. In this session, we explore how GenAI can assist Db2 professionals by helping understand database structures, maintain environments and accelerate problem diagnosis. Through practical examples, we demonstrate how AI can act as a partner, augmenting expertise and helping teams work more efficiently while maintaining the reliability expected from enterprise Db2 systems.

SQL Data Insights (SQL DI) in Db2 13 for z/OS brings built‑in AI directly into the database, enabling organizations to discover patterns, detect anomalies, and generate insights using familiar SQL—without moving data or building complex pipelines.
This session provides practical guidance on getting started with SQL DI, beginning with Db2 instrumentation data as a high‑value entry point. It will also demonstrate how to extend insights by ingesting VSAM data through Data Virtualization Manager.
In addition, the session highlights recent SQL DI enhancements, including a unified embedding model, SQL-based AI access, and incremental training capabilities—enabling teams to seamlessly embed AI into existing Db2 workflows.
The session concludes with an overview of Industry Starter Kits, featuring prebuilt datasets, vector tables, and AI queries that accelerate adoption and help organizations quickly realize high‑value use cases.

Whether you’re evaluating data movement paths for your Db2 databases or are interested in efficiently operating your already migrated Db2 databases on Amazon RDS, we’ve got you covered. In this session, learn about data movement paths, including those with minimal downtime, for Db2 databases. Explore real-world examples to learn best practices that help ensure high availability, optimize performance, and meet your compliance needs. Bring your questions and challenges—this interactive talk offers you the opportunity to hear directly from AWS experts and collaborate with your peers. Plus, see how to supercharge your applications by integrating AWS AI/ML services like Amazon Bedrock, Amazon Sagemaker directly with RDS for Db2. Join us to turn your database into a launchpad for innovation.

While Db2 12.1 has been out for some time with great new content, most companies are still using Db2 11.5 which has tremendous business value. Prior to upgrading to Db2 12.1 clients should take advantage of what is in 11.5 and get the most ROI with what they already have. In this session we'll go through an overview of the high value capabilities of Db2 11.5 - covering 11.5.0 through 11.5.9. This will include availability, recoverability, performance, warehouse, security, multi-model, AI capabilities and more.

Discover how AI coding assistants transform DB2 development. This live demonstration showcases Bob, an AI-powered tool that automates schema design, generates optimized SQL queries, debugs complex issues, and tunes performance—all through natural language. See real-time examples of migration planning, query optimization, and troubleshooting that reduce development time by 60%. Learn practical integration strategies for your DB2 workflows.

In this session we'll take a look at the capabilities that have been added to Db2 over the past years to prepare Db2 to meet client demands of today and the future. This will include modern deployment options such as cloud and containerized deployments - but - we'll spend more time on modern workloads such as data virtualization, multi-model support, NoSQL support, how to handle mixed workloads and, of course, AI. Many clients are using Db2 for traditional OLTP, operational and analytic workloads - but - are you getting the full value of your Db2 investment and footprint ? All these high value capabilities are there and included in your current license base. Lets unpack what they are.

Enterprises are under pressure to deliver faster insights, streamline operations, and reduce the complexity of managing large Db2 environments. Generative AI is emerging as a practical accelerator across development, administration, and performance engineering. This session will show how teams can harness AI to translate natural language questions into accurate Db2 queries, explore schemas and dependencies without digging through documentation, and diagnose performance issues with recommendations that mirror seasoned experts. We will walk through real use cases that demonstrate how GenAI can simplify workloads, cut troubleshooting time, and improve SQL efficiency, giving developers, DBAs, and performance analysts a powerful new set of tools to boost productivity and unlock the full value of Db2.

When a Db2 or IMS issue occurs, resolution often relies on time-critical manual analysis. This session explores how agentic AI is evolving the operational model for IMS and Db2—moving beyond scripted automation toward more adaptive, AI-assisted approaches for handling complex runtime scenarios. Through a live demo grounded in real client feedback from a large financial services organization, we demonstrate how these approaches can reduce time to resolution and improve operational efficiency. We also examine how AI-assisted decisioning can support routine maintenance, ensuring actions are recommended within defined rules, governance boundaries, and measurable value.
Co-presented with Anshul Agrawal, this technically focused session will also be submitted to IBM TechXchange.

I have a passion for all things mainframe especially Db2 for z/OS.
I like to tell non-technical folks what I do is make the mainframe & its databases a little easier to work with—and maybe a little less intimidating for the next generation of users.”
“honestly—when people hear ‘mainframe,’ they don’t always think modern, developer-friendly, and easy to integrate with.
But that’s exactly what we’re going to challenge today.”
“What I’m hoping to show you is that modernization isn’t about replacing the mainframe—it’s about unlocking more value from it, making it easier to use, and integrating it seamlessly into how we already build and deliver applications today.”
“So whether you’re deeply familiar with the platform, or just curious about how it fits into a modern development lifecycle—there should be something useful here for you.”

AI agents are moving beyond chatbots and code suggestions. The next frontier is agentic AI — systems that autonomously plan multi-step tasks, invoke tools, handle branching logic, and execute end-to-end workflows with minimal human intervention. This session shows how that capability applies directly to Db2 for z/OS operations today, using tooling already available in your environment.
The architectural foundation is simpler than it appears: a well-documented CLI is already an agent interface. The Zowe CLI ecosystem — including its Db2 plugin and the richer vendor-supplied extensions published to the Zowe conformance catalog — gives an AI agent a complete, auditable means to act on the mainframe. The agent does not wait for step-by-step instructions; it reasons over the task, selects the right tool from its available plugin set, chains the necessary operations, and executes.
This session presents a layered agent architecture purpose-built for Db2 workflows in production environments:
Execution layer: A base skill encoding the Zowe CLI interface — translating agent intent into exact, logged commands with safe defaults enforcedDomain layer: A Db2-specific reasoning layer encoding your object model, naming conventions, environment topology, and operational runbooks — the institutional knowledge that typically lives in a senior DBA's headGuardrail layer: Explicit constraints on what the agent executes autonomously versus what requires human sign-off, scoped by environment, subsystem, or operation classWe will demonstrate this using vendor-supplied database management plugins available in the Zowe ecosystem. By exposing operations like DDL generation, schema comparison across subsystems, validation, deployment, and object migration through a CLI interface, an agent can autonomously execute workflows that previously required manual expert coordination — generating DDL for a target object, comparing it against a reference subsystem, validating dependencies, and staging the deployment artifact as a single orchestrated task.
We will also show how the compounding architecture scales across your full mainframe stack. Institutional knowledge encoded once — for Db2, for your SCM tool, for your CICS or MQ environment — becomes a reusable agent capability. Each domain layer builds on the same execution foundation, and the agent chains them together as the workflow demands.
Attendees will leave with a concrete architecture for deploying agentic AI on Db2 z/OS, practical guardrail patterns that make autonomous execution safe in production, and a clear understanding of how the depth of the Zowe plugin ecosystem — open-source and vendor-supplied alike — becomes a direct multiplier for what an AI agent can accomplish.

IBM Db2 offers a wide range of AI features, both built-in and external tools, for creating AI systems and solutions. These include over 200 built-in AI stored procedures and tools that work seamlessly with open-source AI ecosystems. In this workshop, participants will explore Db2’s AI support and use a selection of these features to implement practical AI models. The workshop consists of two parts. In the first module, participants will learn how to develop a supervised AI model using Db2’s built-in AI stored procedures. The entire model development and usage will be done using SQL within the database. In the second module, participants will learn how to create a Python model using popular Python packages outside of the database, and then deploy that model back into a Db2 database. By the end of the workshop, participants will have gained fundamental skills and hands-on experience in utilizing these AI capabilities. They will be able to apply these skills to their future AI projects. This workshop is designed to be beginner-friendly and does not require participants to have extensive knowledge in AI. Basic SQL skills and some Python programming skills are sufficient for attending and benefiting from this workshop.

As AI capabilities expand on IBM Z, database operations are evolving from manual, expertise-driven practices to more automated, simpler, and faster management. This hands-on lab session provides experience with Database Assistant capabilities which transform Db2 administration through agent-assisted intelligence.
Experience how the solution combines AI-driven system insights, context-aware dashboards, and AI agents to enable:

Faster understanding of system behavior
Accelerated troubleshooting
Clearer assessments of operational impact
More confident decision-making

The benefit is reduced manual effort, improved consistency, faster issue resolution, and enhanced operational efficiency across complex enterprise environments.
Make sure to bring your laptop!

Are you ready to move beyond managing infrastructure and start innovating with your data? This hands-on workshop provides a deep dive into migrating and modernizing IBM Db2 workloads using Amazon RDS for Db2. Participants will gain practical experience in executing seamless migrations from platforms like Linux, AIX, or z/OS while ensuring high availability and optimized performance.Beyond the migration, you will explore how to unlock the value of your data by integrating AWS AI/ML services. You'll learn to build intelligent applications using Amazon Bedrock powered by your live RDS for Db2 data. By the end of this session, you will have a clear blueprint for transforming your legacy databases into a modern, AI-ready data foundation.

This hands-on lab will explore how Db2 integrates vector data with structured relational data to support AI-driven use cases. Through guided exercises, attendees will combine unstructured text-derived vectors with traditional data and apply similarity search across both. The lab shows queries that merge SQL filtering with vector similarity to enable semantic search, recommendations, and intelligent data retrieval.