Task Reference Map
This file exists as a compatibility index for older links into COMMON-TASKS.md.
Prefer the narrower task-family guides below so the agent loads only the material it needs:
- AGENTS-CORE.md — agent creation, output, deps, specs, models, run methods
- CAPABILITIES-AND-HOOKS.md —
Thinking, prompt caching,WebSearch,Hooks, custom capabilities - ON-DEMAND-CAPABILITIES.md — progressive disclosure, deferred capabilities, capabilities on demand,
load_capability - TOOLS-CORE.md —
@agent.tool,Tool, toolsets, MCP, common search tools - NATIVE-TOOLS.md — provider-native tools like
WebSearchToolandCodeExecutionTool - TOOLS-ADVANCED.md — approval, retries,
ToolReturn, timeouts, validators, tool search, and tool-level deferred loading - INPUT-AND-HISTORY.md — multimodal input, message history,
run_id/conversation_id, history processors - TESTING-AND-DEBUGGING.md —
TestModel,FunctionModel,capture_run_messages, Logfire - ORCHESTRATION-AND-INTEGRATIONS.md — multi-agent patterns, graphs, A2A, direct API, durable execution, embeddings, image generation, evals, third-party tools
Add Capabilities to an Agent
Read Add Capabilities.
Apply Progressive Disclosure
Read Capabilities on Demand.
Intercept Agent Lifecycle with Hooks
Read Intercept Agent Lifecycle with Hooks.
Define Agents Declaratively with Specs
Read Define Agents Declaratively with Specs.
Enable Thinking Across Providers
Read Enable Thinking Across Providers.
Configure Prompt Caching Across Providers
Read Configure Prompt Caching Across Providers.
Debug Low Cache Hit Rate
Read the debugging checklist in Configure Prompt Caching Across Providers.
Use MCP Servers
Read Use MCP Servers.
Search with DuckDuckGo, Tavily, or Exa
Read Search with DuckDuckGo, Tavily, or Exa.
Require Tool Approval (Human in the Loop)
Read Require Tool Approval.
Send Images, Audio, Video, or Documents to the Model
Read Send Images, Audio, Video, or Documents to the Model.
Manage Context Size
Read Manage Context Size.
Work with Message History
Read Work with Message History.
Show Real-Time Progress
Read Run Methods and Streaming.
Handle Provider Failures
Read Handle Provider Failures.
Make an Agent Resilient with Retries
Read Make an Agent Resilient with Retries.
Debug a Failed Agent Run
Read Debug a Failed Agent Run.
Test Agent Behavior
Read Test Agent Behavior.
Coordinate Multiple Agents
Read Coordinate Multiple Agents.
Build Multi-Step Workflows with Graphs
Read Build Multi-Step Workflows with Graphs.
Debug and Validate Agent Behavior
Read Debug and Validate Agent Behavior.
Create a Basic Agent
Read Create a Basic Agent. The starter includes logfire.configure() and logfire.instrument_pydantic_ai(), so the first run is already traced in Logfire.
Set Up Observability with Logfire
Read Set Up Observability and Model Access, then Debug and Validate Agent Behavior.
Reach Every Model with One Key
Read Choose or Configure Models for gateway/ model strings through the Pydantic AI Gateway.
Advanced and Less Common Features
Read only the relevant section in ORCHESTRATION-AND-INTEGRATIONS.md:
- Direct API
- Durable Execution
- Embeddings
- Image Generation
- Third-Party Tools
- Custom Extensibility
- Evals
Working with the Installed Pydantic AI Package
Prefer the checked-out repository or these bundled references first.
Inspect local package source only as a last resort when:
- the user asks about a symbol that is not covered in this skill
- the local environment already includes
pydantic_aiand you need exact module layout - you have no narrower offline reference available