PydanticAI & PydanticGraph — Type-Safe AI Agents & Graph Workflows

Build production-grade AI agents and graph-based state machines with PydanticAI and PydanticGraph. Agent creation, function tools, dependency injection, structured output, streaming, and graph control flow.

Why Install This Skill

When your agent loads this skill, it becomes a PydanticAI expert who can:

Create type-safe agents — one-line agent creation with structured output validation
Build function tools with dependencies — RunContext for dependency injection
Stream outputs — text, events, and graph node streaming
Use built-in capabilities — Thinking, WebSearch, MCP, Hooks, and 20+ more with on-demand loading
Create graph state machines — PydanticGraph with BaseNode, GraphBuilder, parallel map/broadcast, joins with reducers
Test systematically — TestModel, FunctionModel, Pydantic Evals
Deploy to production — multi-agent patterns, MCP servers, durable execution

What You Get

Directory	Purpose
`SKILL.md`	Quick reference, when-to-load table, common pattern gallery
`references/`	8 reference files: core agents, capabilities/hooks, graph, models/output, patterns, testing/evals, examples, API reference, hybrid LangGraph patterns
`templates/`	Runnable template implementations

Triggers

Load this whenever building agents, tool-using LLM workflows, or graph-based state machines in Python.

Requirements

Python 3.10+ with pydantic-ai or pydantic-ai-slim package.

Quick Start

Start with the setup and first workflow in SKILL.md, then use the linked resources for the specific task you need to complete.

1.7 KiB Raw Blame History