Setting the chapter. One moment.
Skills
Chapter 4 of 22
Scaffold a minimal local Deep Agent in Python by following the official quickstart, using provider-native web search instead of Tavily.
1 minute · 232 words · 2 sections
Follow the live docs — do not invent an alternate API from memory:
https://docs.langchain.com/oss/python/deepagents/quickstart (opens in a new tab)
Fetch that page (Docs MCP or HTTP) and implement the research-agent shape it shows (create_deep_agent, research system prompt, invoke with a research question like “What is LangGraph?”).
Apply these on top of the quickstart (they keep setup minimal and model-agnostic):
Ask which provider/model to use. Showcase that Deep Agents are model-agnostic. Suggested prompt:
Which model should this agent use? Pass a
provider:modelstring — e.g.openai:gpt-5.5,anthropic:claude-sonnet-5,google_genai:gemini-3.5-flash. Default if you’re unsure:anthropic:claude-sonnet-5.
We’ll use that provider’s built-in web search (no separate search API key).
Create a new directory (e.g. deep-agent/) and do all work there — do not pollute the open project.
Do not use Tavily (or any second search vendor). Replace the quickstart’s internet_search / Tavily tool with the chosen provider's built-in web search. Look up the current tool shape on that provider's LangChain chat docs (examples as of writing — re-check if needed):
| Provider | Built-in search tool |
|---|---|
| Anthropic | {"type": "web_search_20260209", "name": "web_search", "max_uses": 5} |
| OpenAI | {"type": "web_search"} |
{"google_search": {}} |
Prefer Anthropic / OpenAI / Google so provider search is available. Only secret: that provider’s API key in .env (gitignored). Skip LangSmith tracing unless they ask.
Install deepagents (+ python-dotenv) and the provider package for their model — not tavily-python.
Run the research example, show output, then stop. Point to deep-agents-core / customization / Managed Deep Agents for next steps.
Install this repository
npx skills add langchain-ai/langchain-skills/plugin marketplace add langchain-ai/langchain-skillsSkills install per repository, not per chapter — the CLI has no documented per-skill form, so we do not print one.
Scaffold a minimal local Deep Agent in Python by following the official quickstart, using provider-native web search instead of Tavily. Use when the user wants to quickly build or try a Deep Agent locally.
The verbatim description from this skill’s front matter — the string an agent matches on to decide whether to load it.
main, last pushed 7 August 2026.SKILL.md, not by matching a directory convention. One layout observed: config/skills/*/SKILL.md.h1 and no skipped levels:.claude-plugin/marketplace.json by LangChain, declaring 1 plugin. It is read for editorial metadata only — never as the skill index, which is always the repository tree./langchain-ai/langchain-skills.md, and each chapter at its own .md URL.