Pydantic
Pydantic benchmark: code mode roughly halves cost on long agent tasks
Letting a model write a short program instead of calling tools one at a time cut cost by 58% and wall time by 51% on long tasks, according to a benchmark published by…
Pydantic maintainer wins AAIF award for MCP Python SDK work
A Pydantic developer who maintains the MCP Python SDK has received the Outstanding Technical Contribution Award from the Agentic AI Foundation. The award was presented…
Pydantic Cuts CI Bill From $18,200 to $5,700 by Moving to RunsOn
Pydantic says it cut its monthly CI cost from $18,200 in August to $5,700 in September after moving Logfire's GitHub Actions workflows to RunsOn, which launches…
Pydantic: Graph Libraries Are a Mistake, Because Code Is the Graph
Pydantic argues that graph libraries for AI agents are a mistake and that the only workable graph is code itself. In an article titled "The code is the graph", the…
Pydantic v2.14 stabilizes MISSING sentinel and adds Python 3.15 support
Pydantic v2.14 was released on October 8th, adding official support for Python 3.15 and dropping Python 3.9. According to the Pydantic team, the release stabilizes the…
Pydantic AI Gateway adds Jev, TypeSafe's classification model
Pydantic has made Jev, TypeSafe's classification model, available through Pydantic AI Gateway. Applications can call it with the same gateway key they use for language…