Creating PydanticAI Agents Quick Start Model Selection Model strings follow format: Structured Outputs Use Pydantic models for validated, typed responses: Agent Configuration Running Agents Three execution methods: Instructions vs System Prompts Common Patterns Parameterized Agent (Type-Safe) No Dependencies (Satisfy Type Checker) Verification gates Run these in order before depending on an agent in production code: 1. Smoke run — Execute (or in async code). Pass: the call completes without raising and is present. 2. Structured output — If you set , prompt for a response that should satisfy t…