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 two hundred 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

Phil SchmidVoices

How Gemini Managed Agents Works under the Hood

06.10

A single API call boots a sandbox, loads skills, and lets the model loop until the task is done. Here is what happens at each step.

Models & releases Agents & vibe coding MCP, skills & tools

Read at Phil Schmid ↗

One letter a week, starting soon.

Latest

How Gemini Managed Agents Works under the Hood

Related

VoicesHow to use Deep Research with the Gemini API Phil Schmid

VoicesGemini Managed Agents: Developer Guide Phil Schmid

VoicesHow to correctly use MCP servers with your AI Agents Phil Schmid

Voices8 Tips for Writing Agent Skills Phil Schmid

VoicesHow to use Gemma 4 with the Gemini API and Google AI Studio Phil Schmid

VoicesCombine Built-in Tools and Function Calling in the Gemini Interactions API Phil Schmid