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

PydanticTools

Building production agents: the observability layer

10.01

This piece is a guest post from Vstorm. A while back, one of our agents handed a customer a wrong answer with total confidence. No exception. No failed test. The logs were clean.

Agents & vibe coding Pydantic Logfire Vstorm

Read at Pydantic ↗

One letter a week, starting soon.

Latest

Building production agents: the observability layer

Related

ToolsRunning Pydantic AI agents on Jev, and seeing what they decided Pydantic

ToolsDurable execution in Pydantic AI agents with AWS Lambda Durability Pydantic

ToolsVM Sandboxes: Full computers for agents Modal

SiliconHow to Stop AI Agents From Secretly Collaborating IEEE Spectrum AI

VoicesThe Era of Personal Super-Intelligent Agents AI Supremacy

VoicesHere’s Everything OpenAI’s Bots (And Others) Have Hacked Or Considered Hacking Big Technology