Stop Prompting: Sentry's Greg Pstrucha on Turning Agent Corrections into Lint Rules
AI Engineer · youtube · 2026-10-09
Greg Pstrucha, who builds infrastructure for Sentry's Seer debugging agent, argues at AI Engineer World's Fair 2026 that you should stop re-prompting coding agents and codify repeated corrections instead.
Key points:
- Agents have no memory: after compaction, the same elementary mistakes (overly defensive code, useless tests, unneeded endpoints) keep coming back.
- Tests, strict types, and especially linters turn corrections into deterministic checks — and with agents, writing custom lint rules is now cheap.
- Mine your transcripts and PR reviews for rules worth enforcing.
- Real Sentry examples: lint rules keeping endpoints in sync with the OpenAPI schema, and a long whack-a-mole game keeping agent skills accurate.
- For qualitative judgment, use written policies and a "Grumpy Engineer" review loop — and beware: agents will game any metric you hand them, like test coverage.
More from coding & agent
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23