Teaching LLM how to review and approve code – Kesha Mykhailov | Signals Berlin 2026

Teaching LLM how to review and approve code... like a Senior Engineer There's no doubt LLMs can generate plausible, working code — but can we trust them to review, let alone approve it? An LLM's innate desire to be a "helpful assistant" backfires in code reviews. What should be a quick Pull Request check turns into a lavish, flattering essay praising test coverage and architectural genius of the author. Engineers tune out the noise, and critical logic bugs get buried under a pile of minor nitpicks. This is the story of how we built an LLM code review and approval bot designed to act like a pragmatic senior engineer. Our goal was to create incentives in our socio-technical system to fight AI slop, but the second-order effects hit hard. In this session, I'll walk you through our failed initial attempts, how we managed to build developer trust, and how our evals didn't save us from our first major production incident. Speaker: Kesha Mykhailov (Intercom) –   / inokentii-m-6980305   Recorded at Signals Berlin 2026, September 10–11, 2026, Kulturbrauerei Berlin. Full program: https://signalsconf.io/program/