Tessera
Folgen

Pydantic

@pydantic.dev

The end-to-end AI engineering stack AI observability at scale without fail with Pydantic Logfire. Iterate with Pydantic Evals. Build type-safe agents with Pydantic AI. Track costs with AI Gateway.

52 Posts1042 Follower11 Folgt
Pydantic@pydantic.dev · 4mo ago

"What I want most: software that helps me express, formalise, and include my opinions rather than enforcing its opinions on me." In the 3rd part of the Box Model series, @summerscope.bsky.social talks about the design process, intuition, and cargo cult prompting. pydantic.dev/articles/lie...

Design Process Is Exhaust, Not Propulsion: On Intuition, AI, and Adaptive Software

Why rigid design process survives when results don't — a critique of design methodology, a case for intuition, and a vision for software that adapts to users instead of the other way around.

pydantic.dev

Pydantic@pydantic.dev · 4mo ago

A model discovered a contradiction between the Bible and biology textbooks. It had access to a lot of compute so it consumed an entire data center's worth of it, debating the Immaculate Conception with itself. This talk is 15 mins of real production AI failures and what it took to debug them.

Bild
Pydantic@pydantic.dev · 4mo ago

"The best navigation is the kind nobody notices." On Part 2 of Lies, Damn Lies, and the Box Model, @summerscope talks about the design process behind Logfire's sidebar. The trade-offs, and what "directionally correct" means in practice. Part 3 (and final) out tomorrow.

Pydantic@pydantic.dev · 4mo ago

Pydantic models were using more memory than expected. We dug in with Memray, found the bottleneck, and replaced it with a Rust bitset. 55% less memory. Faster validation. Full deep dive on the new blogpost pydantic.dev/articles/pyd...

Reducing Pydantic's Memory Footprint by 55% Using Bitsets | Pydantic Validation

Learn how Pydantic replaced Python sets with Rust-powered bitsets to cut model instance memory usage by 55% and speed up validation. A deep dive into PEP 412, memory profiling with Memray, and the bit...

pydantic.dev

Pydantic@pydantic.dev · 5mo ago

A few weeks ago our founder announced Monty, a minimal, secure Python interpreter written in Rust, for running code written by AI agents. People got excited. @sa.muelcolvin.com just wrote up the full story on why he's excited about it and you should be too. pydantic.dev/articles/pyd...

Pydantic Monty: A Minimal Python Sandbox for AI Agents | Pydantic

Meet Monty — a secure, minimal Python interpreter written in Rust for running AI-generated code. Learn where it sits between tool calling and full computer use, and why CodeMode matters for AI agents.

pydantic.dev

Pydantic@pydantic.dev · 9mo ago

Pydantic AI Gateway is now in open beta 🚀 One API key for OpenAI, Anthropic, Google, Groq, and Bedrock. BYOK and Built-in providers. Real cost limits. Built-in observability. Zero translation delays. Free during beta. pydantic.dev/ai-gateway

Enterprise AI Gateway: Unified Access to Major AI Models

The Pydantic enterprise-grade AI Gateway provides secure & scalable single API key interface to manage models from OpenAI, Google, Anthropic, Groq & others

pydantic.dev

Qian Li@qianli.dev · 9mo ago

I added two new demos showing durable agent patterns (parallel vs sequential) with @pydantic.dev AI + @dbos.dev: - Deep Research: large fan-out parallel workflows - Twenty Questions: long sequential subagent chaining Both are long-running, so durable execution is necessary to survive crashes.

Workflow graph for the deep research agent, showing massive parallel processing (fan-out).
Qian Li@qianli.dev · 9mo ago

I wrote a tutorial on integrating DBOS with Logfire. It's super easy to set up (kudos to the @pydantic.dev team!) -> just a few lines to configure the exporter and your Logfire write token. Once it's running, you'll get a unified view of your app with logs + traces in one place.

A screenshot of using Logfire + DBOS + Pydantic AI agent.
Adam Azzam@aaazzam.bsky.social · 10mo ago

I'm teaming up with @sa.muelcolvin.com to launch a new meetup series, Py AI. Our first one is November 11 in San Francisco with talks from @pydantic.dev, @modal-labs.bsky.social, ReductoAI and @fastmcp.bsky.social. Hosted by our friends at pebblebed.com RSVP here: luma.com/gjtfecc7

Py AI Meetup · Luma

Join us for an evening of cutting-edge AI discussions featuring lightning talks from leading practitioners: Samuel Colvin (CEO of Pydantic) Reducto + Modal…

luma.com

FastAPI@fastapi.tiangolo.com · 10mo ago

Here's FastAPI 0.118.1, with compatibility for the latest @pydantic.dev. 🚀 This one had the combined effort of the community, the @pydantic.dev team, and the @fastapi.tiangolo.com team, all together. 🙌 github.com/fastapi/fast...

GitHub - fastapi/fastapi: FastAPI framework, high performance, easy to learn, fast to code, ready for production

FastAPI framework, high performance, easy to learn, fast to code, ready for production - fastapi/fastapi

github.com

Qian Li@qianli.dev · 10mo ago

Several people (thanks to @mitsuhiko.at and @sa.muelcolvin.com) noted early on that DBOS had too many dependencies. In the latest Python release, we trimmed it down to just 6 direct deps while still implementing durable workflows and queues in one library. It's lightweight (for real).

uv tree for dbos v2.0.0
Pydantic@pydantic.dev · 11mo ago

I think this might be MASSIVE: Pydantic AI is getting support for @vercel.com AI Elements streaming, making it easy to build React or Next.js frontends for Pydantic AI agents. Video demo in the PR: github.com/pydantic/pyd...

Vercel AI Elements types by samuelcolvin · Pull Request #2923 · pydantic/pydantic-ai

This adds support for Vercel AI Elements streams to Pydantic AI. There's an example frontend in a separate repo github.com/pydantic/pydantic-ai-chat the plan is to either make that into a more ...

github.com