Claude SDK & Cowork — Platform Overview
Claude Agent SDK and Claude Cowork are two expressions of the same underlying agent runtime. The SDK gives developers programmatic control over the loop; Cowork gives non-developers a delegation interface over the same runtime.
Relationship
Claude Agent Runtime (agent loop, tools, hooks, sessions)
↙ ↘
Claude Agent SDK Claude Cowork
(custom applications, (desktop delegation,
code, API, MCP tools) files, connectors, skills)
Both share the same fundamental design concerns: bounded tool use, session management, context budget control, and human review at decision points.
SDK: for builders
The SDK is for embedding the agent loop into custom applications. The maturity ladder for SDK learning:
query()— understand the message stream before adding tools- Tool permissions and PreToolUse hooks — control what the agent can do
- Streaming UI — turn loop messages into product interfaces
- AskUserQuestion / human input — build approval workflows
- Custom MCP tools — connect domain APIs
- Subagents — decompose complex workflows into specialist roles
Key rule: read-only first, approved writes second, autonomous writes last.
Cowork: for delegators
Cowork is for users who want to hand off complete work packages. The effective pattern:
- Name the deliverable, inputs, scope, and definition of done
- Use the smallest folder that contains the work
- Use plan mode for complex or risky work
- Review final artifacts like a colleague’s draft
- Convert recurring work into skills and projects
Key rule: manage Claude like a capable colleague, not a chat partner. Scope is control.
Shared failure modes
| Failure | SDK manifestation | Cowork manifestation |
|---|---|---|
| Unbounded tools | Broad shell access, data mutation | Oversized connected folders |
| Context rot | Long session state drift | Stale history from prior tasks |
| Missing validation | No result check against criteria | No human review of final artifact |
| Vague scope | Unclear deliverable in the prompt | Re-prompting and rework |
Key insight across both
Context is an operating budget — for cost and for reasoning quality. Token management, prompt caching, context compaction, and session lifecycle are not DevOps concerns; they are product design decisions that determine whether an agent is trustworthy in production.
Related
- AgentLoop — the shared runtime underneath both
- ContextBudget — managing context in both SDK and Cowork
- BoundedAgent — the design principle guiding both
- ClaudeAgentSDK — SDK entity page
- ClaudeCowork — Cowork entity page