Agent engineering: Pydantic AI

A developer built a news reader agent using Pydantic AI, the agent framework from the Pydantic team, which leverages Pydantic's validation to create a FastAPI-like experience with decorators and type annotations. This is the fifth iteration of the project, following versions built with Claude Agent SDK and Pi SDK.

This is the fifth take on the same news reader. The Claude Agent SDK version https://roman.pt/posts/agent-sdk-rewrite/ was a single Python file with tools and sub-agents. The Pi SDK version https://roman.pt/posts/pi-sdk-version/ was a single TypeScript file with an event-based session. This time I used Pydantic AI https://ai.pydantic.dev/ , the agent framework from the Pydantic team. Pydantic AI’s pitch is that since every AI library already depends on Pydantic for validation, you might as well build agents directly on it. The result feels like FastAPI for agents: decorators, type annotations, and automatic schema generation.