Skip to content
Looking for someone to build your mobile app?See my mobile work
← All posts
Series10 parts1 of 10 publishedIn progress

Deep Agents

Building a website auditor with deepagents, one harness layer per post: tools, filesystem, permissions, sandbox, context, skills, and delegation.

Start with part 01
  1. 01What an agent harness is (and when not to use one): deepagents vs LangGraph7 Aug 2026 · 14 min read
  2. 02Your first deep agent: create_deep_agent with frontier and open-weight modelsComing soon
  3. 03Custom tools and MCP in deepagents: Python functions, LangChain tools, and MCP serversComing soon
  4. 04Threads, checkpointers, and human-in-the-loop in deepagents: approving tool calls before they runComing soon
  5. 05The deepagents virtual filesystem and its backends: the agent's working memoryComing soon
  6. 06Permissions and tool surface in deepagents: an auditor that only writes to /reportsComing soon
  7. 07Sandbox and interpreter in deepagents: when the agent needs a real shellComing soon
  8. 08Context management in deepagents: summarization, offload, and prompt cachingComing soon
  9. 09Skills and memory in deepagents: SKILL.md, AGENTS.md, and a GEO audit skillComing soon
  10. 10Delegation, streaming, and production in deepagents: parallel subagents and LangSmithComing soon