Skip to main content
This guide walks you through creating your first deep agent with planning, file system tools, and subagent capabilities. You’ll build a research agent that can conduct research and write reports.

​
Prerequisites

Before you begin, make sure you have an API key from a model provider (e.g., Anthropic, OpenAI).
Deep agents require a model that supports tool calling. See customization for how to configure your model.

​
Step 1: Install dependencies

pip install deepagents tavily-python
This guide uses Tavily as an example search provider, but you can substitute any search API (e.g., DuckDuckGo, SerpAPI, Brave Search).

​
Step 2: Set up your API keys

export ANTHROPIC_API_KEY="your-api-key"
export TAVILY_API_KEY="your-tavily-api-key"

​
Step 3: Create a search tool

import os
from typing import Literal
from tavily import TavilyClient
from deepagents import create_deep_agent

tavily_client = TavilyClient(api_key=os.environ["TAVILY_API_KEY"])

def internet_search(
    query: str,
    max_results: int = 5,
    topic: Literal["general", "news", "finance"] = "general",
    include_raw_content: bool = False,
):
    """Run a web search"""
    return tavily_client.search(
        query,
        max_results=max_results,
        include_raw_content=include_raw_content,
        topic=topic,
    )

​
Step 4: Create a deep agent

# System prompt to steer the agent to be an expert researcher
research_instructions = """You are an expert researcher. Your job is to conduct thorough research and then write a polished report.

You have access to an internet search tool as your primary means of gathering information.

## `internet_search`

Use this to run an internet search for a given query. You can specify the max number of results to return, the topic, and whether raw content should be included.
"""

agent = create_deep_agent(
    tools=[internet_search],
    system_prompt=research_instructions
)

​
Step 5: Run the agent

result = agent.invoke({"messages": [{"role": "user", "content": "What is langgraph?"}]})

# Print the agent's response
print(result["messages"][-1].content)

​
How does it work?

Your deep agent automatically:
  1. Plans its approach using the built-in write_todos tool to break down the research task.
  2. Conducts research by calling the internet_search tool to gather information.
  3. Manages context by using file system tools (write_file, read_file) to offload large search results.
  4. Spawns subagents as needed to delegate complex subtasks to specialized subagents.
  5. Synthesizes a report to compile findings into a coherent response.

​
Examples

For agents, patterns, and applications you can build with Deep Agents, see Examples.

​
Streaming

Deep agents have built-in streaming for real-time updates from agent execution using LangGraph. This allows you to observe output progressively and review and debug agent and subagent work, such as tool calls, tool results, and LLM responses.

​
Next steps

Now that you’ve built your first deep agent:
Edit this page on GitHub or file an issue.
Connect these docs to Claude, VSCode, and more via MCP for real-time answers.