The name is the button.

An agent writes the code now, and a human thumb hovers over Accept all a hundred times a day. The honest question of this decade is what, exactly, you just accepted. So I read the diff.

Eight years as a backend engineer in Stockholm, back in Tokyo since 2023, and I still ship something small most nights, usually badly. My one rule: the only real review of a model is the thing you built with it. That is why there is no leaderboard on this site.

Around a hundred and forty sources come through — the labs' own posts, the papers, the tools, the runtimes and languages nobody is watching yet, the chip under the demo, and the newsletters people actually forward. What is moving gets counted so the week reads at a glance, and every few days I explain one mechanism in plain words.

A story here is a headline, a short excerpt, one image and the link to whoever wrote it. We never reproduce the post; the images belong to their authors. A post written in Japanese appears in Japanese, exactly as it was published, and the link goes to the original.

— Yuki Halvorsen, Tokyo

← Accept All Archive

Meta EngineeringLabs

The Thin Orchestrator: How We Made Our AI Agents More Reliable by Giving the Router Less to Do

10.19

Sometimes, giving an AI agent all of the knowledge it needs is the wrong approach. At Meta, we’ve seen notable improvements in efficiency and accuracy by keeping the orchestration layer of our data…

Agents & vibe coding

Read at Meta Engineering ↗

One letter a week, starting soon.

Latest

The Thin Orchestrator: How We Made Our AI Agents More Reliable by Giving the Router Less to Do

Related

LabsSecuring the agentic insider The Official Microsoft Blog

Will developing nations be able to handle millions of AI agents? Rest of World

LabsGoogle named a Leader in the 2026 IDC MarketScape for Agentic AI Platforms Google Cloud AI

ToolsHow Legora runs 2,000 parallel agent evals on Modal Sandboxes Modal

GitHubThree developer tasks worth handing to an agent GitLab Blog

ResearchGrounding AI agents in biological reality: Building blocks for autonomous wet labs Google Research