PydanticAI Instrumentation

LangWatch integrates with PydanticAI through its built-in OpenTelemetry support to capture traces of agent runs and model interactions.

Installation

pip install langwatch pydantic-ai

uv add langwatch pydantic-ai

Usage

The LangWatch API key is configured by default via the LANGWATCH_API_KEY environment variable.

Initialize LangWatch and create your PydanticAI agent. PydanticAI’s built-in OpenTelemetry support will automatically send traces to LangWatch.

from pydantic_ai import Agent
import langwatch

langwatch.setup()

agent = Agent(
    "openai:gpt-6-luna",
    instructions="Be funny, but not too funny.",
)

if __name__ == "__main__":
    result = agent.run_sync("Tell me a joke")
    print(result.output)

LangWatch automatically captures all PydanticAI agent runs and model interactions through PydanticAI’s built-in OpenTelemetry support. Use @langwatch.trace() decorators to add custom traces and metadata as needed.

Check it worked

Run the example. Then open your project in LangWatch: a new trace appears in the traces list within a few seconds. Open it to see the PydanticAI agent run and its model calls. If no trace appears, check that LANGWATCH_API_KEY is set in the environment the script runs in.

Capturing RAG - Learn how to capture RAG data from retrievers and tools
Capturing Metadata and Attributes - Add custom metadata and attributes to your traces and spans
Capturing Evaluations & Guardrails - Log evaluations and implement guardrails in your PydanticAI applications

Last modified on October 29, 2026

Overview

Tools

PydanticAI Instrumentation

Installation

Usage

Check it worked

​Installation

​Usage

​Check it worked

​Related

Installation

Usage

Check it worked

Related