Guides
Step-by-step tutorials that walk you through building agent capabilities from scratch. Start here if you're new to agent development.
Build Your First Agent
Go from zero to a working agent mental model (the loop, one tool, and termination) in a single page.
Design a Custom Tool
How to build a production-ready agent tool from scratch: schema, concurrency class, behavioral flags, and dispatch wiring.
Manage Conversation Context
How to keep your agent's context window from overflowing. Covers recognizing the symptoms, applying cheap trims before expensive summarization, and tracking token budgets.
Add MCP to Your Agent
How to connect an external MCP server and make its tools available to your agent. Covers transport selection, tool bridging, and dispatch integration.
Build a Multi-Agent System
How to split a single agent into a coordinator and specialized workers. Covers the delegation pattern, context isolation, tool partitioning, and result synthesis.
Implement Permission Controls
How to add a permission layer to your agent. Covers the cascade model, permission modes, bypass-immune checks, and session grants.
Debug Your Agent
How to find out what your agent is doing wrong. Covers structured event logging, cost tracking, session tracing, and the signatures of common failure patterns.
Stream Agent Responses
How to add streaming to your agent loop so users see output as it generates. Covers typed events, the producer-consumer pipeline, and backpressure handling.
Extend with Hooks
How to add lifecycle hooks to your agent without modifying core loop code. Covers the four execution modes, condition-based filtering, and error isolation.