Let Your Agent Cook: Using Skills to Evaluate and Improve Your App — Ankur Duggal, Arize AI
A financial agent invents answers, repeats tool calls and produces summaries that its own evaluations flag as wrong.
Proof1 independent outlet
Key points
- Ankur Duggal connects those failures to a coding agent through Arize's CLI and skills, then asks it to investigate traces, change the application and run experiments.
- Questions cover local experiment execution, judge models, evaluation costs, sampling and the risk that a coding agent spends its effort on linting instead of the actual defect.
- 1:58 - Traces reveal an agent's actual decisions
- 7:27 - CLI and skills as the interface
Sources (1)
- [1]Let Your Agent Cook: Using Skills to Evaluate and Improve Your App — Ankur Duggal, Arize AIAI Engineer (YouTube) · Oct 11, 06:30 PM
A financial agent invents answers, repeats tool calls and produces summaries that its own evaluations flag as wrong.
Ankur Duggal connects those failures to a coding agent through Arize's CLI and skills, then asks it to investigate traces, change the application and run experiments.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 11, 2026openai/openai-python v3.29.0
- Oct 11, 2026Agent Speedrun — Elizabeth Fuentes Leone & Sandhya Subramani, AWS
- Oct 9, 2026openai/codex rust-v0.162.1: 0.162.1
- Oct 8, 2026openai/codex rust-v0.162.0: 0.162.0
- Oct 8, 2026Understanding Jev, the new model everyone is talking about
- Oct 7, 2026[AINews] Claude Haiku 5.5 — better than GPT-6 Luna at the same pricing
