Linear's Tom Moor: Code Isn't the Bottleneck — Context Is What Agents Miss
AI Engineer · youtube · 2026-11-09
In an AI Engineer talk, Linear co-founder Tom Moor argues writing code is no longer the bottleneck; the hard problem is keeping a product coherent as agents ship more of it, because agents can't see the history around the code. He walks through how Linear carries context from intake to merge: a triage agent enriches issues with customer and incident context; a context-aware review agent checks changes against past decisions, reverts and regressions, catching issues standard reviewers miss; and a daily automation turns review feedback into lessons stored in the codebase. The framing: context moves to the outer loop, built around verification.
More from coding & agent
- ha-mcp hits 5,500 stars: control Home Assistant with Claude and ChatGPT via MCP — homeassistant-ai · 2026-11-09
- YC chief Garry Tan open-sources gbrain agent brain, hits 32k GitHub stars — garrytan · 2026-11-09
- Peer-reviewed paper applies truth maintenance systems to LLM memory belief revision — letandrewcook · 2026-11-09
- System One models are back: decision/extraction APIs cut insurance claim flow from 61.7s to 19.3s — max_gladysh · 2026-11-09
- User builds a 'chief of staff' Grok agent that runs projects and sends one weekly brief — RachelVT42 · 2026-11-09
- 10 Open-Source Tools for Building Trustworthy AI Apps, from Langfuse to TruLens — Shruti_0810 · 2026-11-09