> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-opensw-1772748614-696205f.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Build your first deep agent in minutes

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).

<Note>
  Deep agents require a model that supports [tool calling](/oss/javascript/langchain/models#tool-calling). See [customization](/oss/javascript/deepagents/customization#model) for how to configure your model.
</Note>

### Step 1: Install dependencies

<CodeGroup>
  ```bash npm theme={null}
  npm install deepagents langchain @langchain/core @langchain/tavily
  ```

  ```bash yarn theme={null}
  yarn add deepagents langchain @langchain/core @langchain/tavily
  ```

  ```bash pnpm theme={null}
  pnpm add deepagents langchain @langchain/core @langchain/tavily
  ```
</CodeGroup>

<Note>
  This guide uses [Tavily](https://tavily.com/) as an example search provider, but you can substitute any search API (e.g., DuckDuckGo, SerpAPI, Brave Search).
</Note>

### Step 2: Set up your API keys

```bash theme={null}
export ANTHROPIC_API_KEY="your-api-key"
export TAVILY_API_KEY="your-tavily-api-key"
```

### Step 3: Create a search tool

```typescript theme={null}
import { tool } from "langchain";
import { TavilySearch } from "@langchain/tavily";
import { z } from "zod";

const internetSearch = tool(
  async ({
    query,
    maxResults = 5,
    topic = "general",
    includeRawContent = false,
  }: {
    query: string;
    maxResults?: number;
    topic?: "general" | "news" | "finance";
    includeRawContent?: boolean;
  }) => {
    const tavilySearch = new TavilySearch({
      maxResults,
      tavilyApiKey: process.env.TAVILY_API_KEY,
      includeRawContent,
      topic,
    });
    return await tavilySearch._call({ query });
  },
  {
    name: "internet_search",
    description: "Run a web search",
    schema: z.object({
      query: z.string().describe("The search query"),
      maxResults: z
        .number()
        .optional()
        .default(5)
        .describe("Maximum number of results to return"),
      topic: z
        .enum(["general", "news", "finance"])
        .optional()
        .default("general")
        .describe("Search topic category"),
      includeRawContent: z
        .boolean()
        .optional()
        .default(false)
        .describe("Whether to include raw content"),
    }),
  },
);
```

### Step 4: Create a deep agent

```typescript theme={null}
import { createDeepAgent } from "deepagents";

// System prompt to steer the agent to be an expert researcher
const researchInstructions = `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.
`;

const agent = createDeepAgent({
  tools: [internetSearch],
  systemPrompt: researchInstructions,
});
```

### Step 5: Run the agent

```typescript theme={null}
const result = await agent.invoke({
  messages: [{ role: "user", content: "What is langgraph?" }],
});

// Print the agent's response
console.log(result.messages[result.messages.length - 1].content);
```

## How does it work?

Your deep agent automatically:

1. **Plans its approach** using the built-in [`write_todos`](/oss/javascript/deepagents/harness#to-do-list-tracking) 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`](/oss/javascript/deepagents/harness#file-system-access), [`read_file`](/oss/javascript/deepagents/harness#file-system-access)) 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](https://github.com/langchain-ai/deepagents/tree/main/examples).

## Streaming

Deep agents have built-in [streaming](/oss/javascript/langchain/streaming/overview) 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:

* **Customize your agent**: Learn about [customization options](/oss/javascript/deepagents/customization), including custom system prompts, tools, and subagents.
* **Add long-term memory**: Enable [persistent memory](/oss/javascript/deepagents/long-term-memory) across conversations.
* **Deploy to production**: Learn about [deployment options](/oss/javascript/langgraph/deploy) for LangGraph applications.

***

<div className="source-links">
  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/deepagents/quickstart.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>

  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>
</div>