• AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
• eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.

Evals designed for a fixed graph stop measuring anything once the loop runs free.

• videoThe Last Human Code Review: Building Trust in AI-Generated Code — Itamar Friedman, Qodo
• videoPrototyping as Leadership: How a CTO Ships with AI Agents — Hursh Agrawal, The Browser Company
• videoIT Admin for the AI Workforce — Sarthak Aggarwal, Decawork
• videoThe Era of Compound Engineering — Kieran Klaassen, Every/Cora

• videoDesigning Agents (The Floor Is the Frontier) — Ben Hylak, RaindropAI Engineer
• videoThe Future of Evals: From LLM as a Judge to Agent as a Judge — Aparna Dhinakaran, Arize AIAI Engineer
• clipHow the eval target has changed since 2023AI Engineer

Sign in to comment.

Loading comments…