How top teams run production evals for frontier models.
19:00 – 22:00 CDT
Chicago Innovation Hub, downtown
47% filled
How top teams run production evals for frontier models. Expect focused talks, small-group discussion, and time to meet other builders working on the same problems.
Doors & networking
Coffee, snacks, name tags.
Opening talk
GPT-5 Evals Deep Dive — the state of the art.
Hands-on session
Small groups, real problems.
Lightning talks + Q&A
Mingling & wrap-up
Tomás Vidal
Staff Engineer, Chicago
Ships production ML at scale.
Lena Novak
Engineer, Chicago
Building the next wave of AI tooling.