Some personal (very belated*) news, I've moved to the bay area!

Let me know if you're in SF or Palo Alto and want to get coffee.

Also, last reminder that we have the inaugural Py AI meetup with @pydantic.dev in SF on Tuesday. Register now: luma.com/gjtfecc7

* I actually got here in the summer.

Just putting this here. Not much more to say.

@pydantic.dev

Pull request to add support for OpenAI's Agent SDK is already up in @logfire.pydantic.dev.

github.com/pydantic/log...

Amazing week in the US at AI Engineer and in SF.

Interest in @pydantic.dev AI and @logfire.pydantic.dev was phenomenal

Turns out developers want to take a bet on Pydantic's track record of developer experience, engineering correctness and open standards, not lock-in and crazy expression languages!

New starter project just landed in @logfire.pydantic.dev

Uses pydantic.run to let you send data to logfire without leaving your browser.

(and yes, I deleted that write token before posting this 😉)

Do I know anyone from @github.com who can help with something urgent?

We moved to github enterprise, which seems to have introduced a $1k billing limit for actions runners which I can't change without support.

Right now that means the entire @pydantic.dev team is blocked.

I forgot to mention when introducing pydantic.run:

* it's open source and MIT licensed
* you can run it yourself with just @cloudflare.social workers
* obviously it's based on the amazing work of Pyodide to run Python in the browser

github.com/pydantic/pyd...

Example of generating mermaid diagrams directly from graphs.

I'm shocked by how easy it is to run PydanticAI with a model running logically.

Here we have Ollama running llama3.2 locally, being used by @pydantic.dev AI extracting structured data from an input.

I take enormous pleasure in this: "uv run" is 6 characters same as "python", so you can switch between them and there's no jump.

One of uv's best features.

ai.pydantic.dev/examples/