Talks on shipping AI you can actually trust in production.
I'm an AI product leader with 20+ years across Fortune 100 companies. I speak about what most AI talks skip: how to govern agents and LLM systems so they're reliable, honest, and safe once real users depend on them — not just impressive in a demo.
The talk
Governed AI: Engineering Trust into Agent Systems
Most AI pilots stall between demo and production because teams can't prove the system won't misbehave with real users. This talk walks through a structured, proven-internally approach, now packaged as a talk — deterministic checks before the model, honest failure handling, and a validation pass that catches what a demo hides. Attendees leave with a concrete checklist they can apply the next day.
One talk, three formats
30 min
core argument + one worked example (conference main-stage).
45 min
adds a live governance-harness walkthrough on a real agent.
60 min
adds Q&A + hands-on (team offsites/workshops).
Delivered
Identity Week America 2026
Organizer testimonial to follow
On-demand lesson
AI Agents That Won't Wreck Production — a free lightning lesson
Watch the recorded lightning lesson.
Watch the replay