AI Engineer summit: the job shifted to managing agent sessions and hidden assumptions
TheTuringPost · x · 2026-11-19
After the AI Engineer summit in San Francisco, the author reflects on how the profession changed in a year, as agents write, run, and fix code autonomously:
- Simon Willison (interview dropping this week): GPT-5.1 and Claude Opus 4.5 made daily autonomous coding real; engineers gained freedom for other tasks, but the new challenge is handling countless small, unspoken decisions.
- Lydia Hallie (Anthropic, Claude Code): agents miss edge cases like keeping active users logged in during auth updates; the job shifts to spotting hidden assumptions, turning them into tests, and managing dozens of parallel sessions.
- Lauren Tan: her team shipped 11,000 changes to Grok Bot in October while making it faster.
Related event: AI Engineer conference: engineers shift as agents write the code(2 posts)→
More from coding & agent
- Running an agent fleet across 15 repos: the bottleneck turned out to be the human — yi_ding · 2026-11-19
- Local MCP server lets Claude search your PDFs, old emails, voice memos and photos offline — IndependentBook5854 · 2026-11-19
- harness-to-api: turn your Codex subscription into an OpenAI-compatible endpoint, skip API bills — gethackteam · 2026-11-19
- Are agents bad at software design because human software is bad? — hargup13 · 2026-11-19
- VS Code docs: how to manage agent sessions in Chat view and Agents window — adnan_hashmi · 2026-11-19
- One prompt built a full Call of Duty clone — thisdudelikesAI · 2026-11-19