How to Build an AI Code Review Agent - Daksh Gupta, Greptile

Naive review agents cost $3 to $25 per PR and drown reviewers in nitpicks. Reviewing with a different model family than the author, plus an incident-PR eval set, are specific levers to improve catch rate.

• 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.
• context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
• sandbox — An isolated environment where AI-generated code or agent actions run without being able to touch anything real.
• 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.

• videoHow to Write Your First AI Eval - SallyAnn DeLucia, Arize AI
• videoBuild Your Own Team of Managed Agents - Jack Wotherspoon, Google DeepMind
• videoHow to Build Voice Agents That Don't Fall Apart When You Interrupt - Jesse Hall, LiveKit
• videoCan Your AI Analyst Keep a Secret? - Aaron Linsky, Bridgewater & Nikhil Benesch, turbopuffer

• videoAI-Generated Code Is Already Competing With Human Code — Daksh Gupta, GreptileAI Engineer
• videoThe Death of the Code Review: What the Data Actually Says — Laurie Voss, Arize AIAI Engineer
• videoBuilding uReview, Uber’s Multi-Agent Code Review Engine — Will Bond & Ameya Ketkar, UberAI Engineer

Checking sign-in…

Loading comments…