Before You Build the Agent, Fix the Data: What Broke and What We Fixed.
About this session
Everyone is racing to ship AI agents. Very few people talk about what happens when those agents sit on top of fragmented, ungoverned data. I have spent the last several years building enterprise data pipelines at Amazon for HR systems. More recently, my team re-architected several of those pipelines to feed AI and agentic workloads, and that work exposed problems we thought we had solved: validation gaps we papered over years ago, compliance checks that broke silently once volume grew, and a painful week spent tracing lineage after a model gave a wrong answer nobody could explain. In this session I will walk through what it actually took to make our data AI-ready, covering ingestion, validation, governance, and cost visibility, and share the checklist I wish I had at the start.
Speaker
Key takeaways
- How to spot the failure signals that mean your data foundation is not ready for AI agents: silent validation gaps, untraceable lineage, and compliance checks that break at scale
- How to design ingestion, validation, and lineage in pipelines that feed AI and agentic workloads, based on real production failures and fixes
- A practical AI-readiness checklist you can apply to your own data platform before investing in agents, not after