Agent SDK Patterns
Production patterns for building AI agents with the Claude Agent SDK: the loop, subagents, permissions, context management, MCP, and hooks — plus when to use the SDK vs the raw API.
Last updated
After this section you can
- Decide between an agent SDK and the raw API for a given job
- Name the five things a harness has to get right that a hand-rolled loop usually misses
- Take an agent through the operational checklist before deploying it
Agent SDK: Production-Ready Patterns
The raw Messages API gives you one call. Real agents need the loop, tool orchestration, subagents, permissions, context management, and hooks around it. The Claude Agent SDK is that harness — when to reach for it, and the patterns that matter.
Everything so far — the loop, tool use, memory, delegation — you can hand-build on the Messages API, and understanding how is the point of this guide. But rebuilding the harness for every project is wasted motion. The Claude Agent SDK (the engine extracted from Claude Code) packages the battle-tested pieces: the agent loop, tool execution, subagents, permission gating, context compaction, MCP connectivity, and lifecycle hooks. The FDE skill isn’t “can you use the SDK” — it’s knowing which layer to build at, and what production concerns the harness has to solve no matter who writes it.