Pydantic Blog
Articles about Pydantic Blog
Announcement: Pydantic v2.14 Release
Pydantic v2.14 supports Python 3.15 lazy imports and TypeForm, stabilizes the MISSING sentinel, adds frozendict support, and speeds up schema generation.
Would you deploy an agent you don't control?
Claude Agent SDK puts Claude Code inside your application. If your product is not a coding agent, that convenience comes with architectural decisions you did not make.
Building production agents: the observability layer
Agents are still software, but traditional monitoring can't see what they actually do. A practitioner's case for treating observability as a first-class layer, and how we do it with Logfire.
Debug production from Cursor with the Logfire MCP server
Connect Pydantic Logfire's MCP server to Cursor, Claude Code, or Codex and let your coding agent query real production traces, then build the dashboard and the alert that catch the next one.
Pydantic AI agents on Jev, traced in Logfire
Pydantic AI can run an agent on TypeSafe's Jev, a model that answers typed questions instead of writing text. Pydantic Logfire now shows each question, answer, and probability in Live view.
TypeSafe Jev in Pydantic AI Gateway
Bring your TypeSafe key to Pydantic AI Gateway and call Jev through the System One API, with metered cost, guardrails, and the same gateway key you use for every other model.
Cheap AI scoring with Jev and Pydantic Evals
Use Jev for categorical judgments, probabilities, and numeric rubric scores in Pydantic Evals, then track the results in Logfire without a per-score fee.
How we redesigned Pydantic Logfire dashboards
A new look for Pydantic Logfire dashboards: chart colors from 1980s computer graphics, readable for colorblind users, and rows of big numbers that line up.
Generate images with Pydantic AI
Image generation is now part of Pydantic AI. Here's how to use it, why we added it, and the contributor conversations that helped it happen.