Partner with us

Get your ticket

Call to action

Your text goes here. Insert your content, thoughts, or information in this space.

Button

Back to speakers

Vanchhit

Khare

Solutions Developer

Vanchhit Khare is a Solutions Developer. He has written 8+ research papers and reviewed 40+ more. He won Best Paper at IEMTRONICS 2025. He teaches kids at TechBridge AI4ALL, who usually ask better questions than he does. All day he thinks about Claude Code. At night he thinks about it again. Then he sleeps, and his agents keep going without him, which is either very helpful or mildly creepy. He wakes up, reads what they found, and writes it in his diary. When he's not working he's on a plane somewhere with bad WiFi.

Button

19 August 2026 12:00 - 12:30

Panel | Eval in the wild: What actually breaks when you test agentic AI on real financial data

Eval frameworks that work in research don't always survive contact with production financial data. This session brings together panelists covering what they measure, what they have stopped measuring, how they handle non-determinism at scale, and what broke before they got it right. What this session will cover: - Why standard benchmarks fail on production financial datasets - How teams are handling non-determinism in multi-step agent pipelines - Observability tooling being used in live financial environments - What good eval hygiene looks like six months into production Bring your own war stories, this one tends to turn into a comparison of notes.