Pydantic | The end-to-end AI engineering stack Skip to main content Pydantic AIAI GatewayAI Build agents you’ll actually ship to production The risk-free way to get started with AI Observability and Agent Evals is Pydantic Logfire. Bring your agents written in PythonPydantic AI is the best framework for building agents in Python, and we think you’ll love it. Logfire can observe, secure, and optimize agents written in any major framework. or TypeScriptLogfire lets you monitor, secure, and optimize agents written in TypeScript, Rust, Go, .NET, or any other language.. Continuously improve your agents with insights from your traces and evals. Protect your data and control your spend with Logfire AI Gateway. Start Free Start Free Let's talk Enterprise Let's talk Enterprise Onboard with your coding agent Companies that trust Pydantic AI Software Development Lifecycle Meet the Pydantic Stack Build OSS Agent FrameworkGraphsMCP OSS Data ValidationType Hints Iterate OSS EvalsAssertionsCode-first Logfire Agent Optimization OpenTelemetryTraces Deploy & Monitor Logfire Agent Monitoring OpenTelemetryLogsTracesMetrics Logfire Infrastructure Monitoring OpenTelemetryLogsMetrics LogfireOSSSaaS OpenTelemetryLogsTracesMetrics Logfire AI GatewaySaaS SaaS LLM RoutingFinOpsBYOKOpenTelemetry Case Studies Logfire and Pydantic Evals give Evergreen.ai end-to-end observability and continuous evaluation for financial-services AI agents. See how Evergreen.ai runs observable financial-services AI agents→ AutonomyAI gives coding agents Logfire via MCP to check production after merge and file follow-ups. Learn how AutonomyAI caught 12 no-op deployments in five weeks→ Qualio uses Pydantic AI and Evals to turn plain-language quality criteria into auditable release gates. Learn how Qualio gates every release with 300 evaluations→ Pydantic AI grounds STCC's clinical RAG in triage decision trees; Logfire makes every answer reviewable. Learn how STCC reached 0% hallucinations in clinical triage→ See all case studies See all case studies End-to-end AI Engineering Stack Build end-to-end type-safe applications with Pydantic Validation, Pydantic AI, Pydantic Logfire and Pydantic Evals. Respected builders of open source, for Python & beyond Pydantic is built on the pillars of open source: transparency, collaboration and excellence. Our origins inform every product we craft. Whether it’s a community project or enterprise solution, developer experience is our cornerstone. Explore open source packages OUR MISSION Driven by curiosity, frustration and coffee Learn more about the creators of Pydantic, our mission and open source ethos. And see how you can get involved. about us Our articles All articles All articles /Pydantic Monty Hack Monty Round 3 & Round 2 results Samuel Colvin 2026/08/12 /Pydantic AI Snowflake + Pydantic AI: governed agents on your data Priya Joseph 2026/08/10