deep-agents-orchestration
Orchestrate subagents, plan multi-step tasks, and require human approval for sensitive operations.
- Delegate work to specialized subagents via the
tasktool; custom subagents support isolated tool sets and system prompts, while the default "general-purpose" subagent inherits main agent configuration - Plan and track complex workflows with
write_todos, organizing tasks across pending, in-progress, and completed states; requires a thread_id for persistence across invocations - Implement human-in-the-loop approval gates on specific tools with three decision types: approve, reject (with feedback), or edit (modify arguments before execution); requires a checkpointer and thread_id for resumption
- All three capabilities are automatically included in
create_deep_agent()and work together to support task delegation, planning, and compliance workflows
- SubAgentMiddleware: Delegate work via
tasktool to specialized agents - TodoListMiddleware: Plan and track tasks via
write_todostool - HumanInTheLoopMiddleware: Require approval before sensitive operations
All three are automatically included in create_deep_agent().
Subagents (Task Delegation)
| Use Subagents When | Use Main Agent When |
|---|---|
| Task needs specialized tools | General-purpose tools sufficient |
More from langchain-ai/langchain-skills
deep-agents-memory
INVOKE THIS SKILL when your Deep Agent needs memory, persistence, or filesystem access. Covers StateBackend (ephemeral), StoreBackend (persistent), FilesystemMiddleware, and CompositeBackend for routing.
7.7Klanggraph-fundamentals
INVOKE THIS SKILL when writing ANY LangGraph code. Covers StateGraph, state schemas, nodes, edges, Command, Send, invoke, streaming, and error handling.
7.1Klangchain-fundamentals
Create LangChain agents with create_agent, define tools, and use middleware for human-in-the-loop and error handling.
6.7Klangchain-rag
INVOKE THIS SKILL when building ANY retrieval-augmented generation (RAG) system. Covers document loaders, RecursiveCharacterTextSplitter, embeddings (OpenAI), and vector stores (Chroma, FAISS, Pinecone).
6.5Klanggraph-persistence
INVOKE THIS SKILL when your LangGraph needs to persist state, remember conversations, travel through history, or configure subgraph checkpointer scoping. Covers checkpointers, thread_id, time travel, Store, and subgraph persistence modes.
6.5Klanggraph-human-in-the-loop
INVOKE THIS SKILL when implementing human-in-the-loop patterns, pausing for approval, or handling errors in LangGraph. Covers interrupt(), Command(resume=...), approval/validation workflows, and the 4-tier error handling strategy.
6.4K