All skills
Agents & Frameworks

Pydantic AI

Type-safe agents with automatic validation

What it is

Pydantic framework for building AI agents with structured outputs automatically validated via Python types. Eliminates malformed JSON issues: define a Pydantic schema and the agent always returns conforming data. Supports all major models (OpenAI, Anthropic, Gemini) with the same interface.

How to use it, step by step

  1. 1

    Install: pip install pydantic-ai (Python 3.9+).

  2. 2

    Define a Pydantic model (BaseModel) describing the structure of the data you want as output.

  3. 3

    Create an Agent specifying the LLM model and result_type equal to your Pydantic schema.

  4. 4

    Run agent.run_sync('your request'): the output comes already validated and typed, not raw text.

  5. 5

    Access fields with dot notation (result.output.field), like a normal Python object.

💡Practical tips

  • Perfect when you need reliable output to feed other code (no more fragile JSON parsing).
  • Use tools decorated with @agent.tool to give the agent functions it can call.
  • Switching provider (OpenAI to Anthropic) leaves your code almost identical.

💰Pricing

Open-source and free. You only pay for model usage.

Go to Pydantic AI

The official site opens in a new tab.