> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gourmand.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Quick Start

> Get started with Gobi's Agent mode to automatically implement code changes, fix bugs, and run commands using AI-powered tools that can modify your codebase based on natural language instructions

Agent mode equips the Chat model with the tools needed to handle a wide range of coding tasks, allowing the model to make decisions and save you the work of manually finding context and performing actions.

<Accordion title="Learn how to choose the right mode" icon="lightbulb">
  <Columns cols={3}>
    <Card title="Chat Mode" icon="comments">
      *Learn and discuss without changing code.*

      **Mental Model:** Talking to a knowledgeable colleague

      **Best For:** Explaining concepts, comparing approaches, code review discussions.
    </Card>

    <Card title="Plan Mode" icon="binoculars">
      *Safely explore and plan with read-only tools.*

      **Mental Model:** Architect surveying before renovation

      **Best For:** Understanding a codebase, bug investigation, planning implementations.
    </Card>

    <Card title="Agent Mode" icon="hammer">
      *Make actual changes with full tool access.*

      **Mental Model:** Contractor executing approved blueprints

      **Best For:** Implementing features, fixing bugs, running tests and commands.
    </Card>
  </Columns>
</Accordion>

### How to Use Agent Mode

You can switch to `Agent` in the mode selector below the chat input box. The mode selector offers three options:

* **Chat mode**: No tools available, pure conversation
* **Plan mode**: Read-only tools for safe exploration and planning
* **Agent mode**: All tools available for making changes

<img src="https://mintcdn.com/gourmand/lfYeqLX2hvXkgz5p/images/mode-select-agent.png?fit=max&auto=format&n=lfYeqLX2hvXkgz5p&q=85&s=e8f0e1ce68925b0284337d0cad9ff1df" alt="How to select agent mode" width="186" height="124" data-path="images/mode-select-agent.png" />

<Info>
  If Agent mode or Plan mode is disabled with a `Not Supported` message, the selected
  model or provider doesn't support tools, or Gobi doesn't yet support tools
  with it. See [Model Blocks](/customization/models) for more information.
</Info>

<Tip>
  Use the keyboard shortcut `Cmd/Ctrl + .` to quickly cycle between modes.
</Tip>

### How to Chat with Agent mode

Agent mode lives within the same interface as [Chat](/ide-extensions/chat/how-it-works) mode, so the same [input](/ide-extensions/chat/quick-start#how-to-start-a-conversation) is used to send messages and you can still use the same manual methods of providing context, such as [`@` context providers](/ide-extensions/chat/quick-start#how-to-use--for-additional-context) or adding [highlighted code from the editor](/ide-extensions/chat/quick-start#how-to-include-code-context).

#### How to Use Natural Language with Agent mode

With Agent mode, you can provide natural language instruction and let the model do the work. As an example, you might say

> Set the @typescript-eslint/naming-convention rule to "off" for all eslint configurations in this project

Agent mode will then decide which tools to use to get the job done.

## How to Give Agent Mode Permission

By default, Agent mode will ask permission when it wants to use a tool. Click `Gobi` to allow Agent mode to proceed with the tool call or `Cancel` to reject it.

<img src="https://mintcdn.com/gourmand/HGSXhgUNM88nD3iS/images/ide-extensions/agent/images/agent-permission-c150919a5c43eb4f55d9d4a46ef8b2d6.png?fit=max&auto=format&n=HGSXhgUNM88nD3iS&q=85&s=660583fbf0838c462cf249ec102763e7" alt="agent requesting permission" width="1432" height="702" data-path="images/ide-extensions/agent/images/agent-permission-c150919a5c43eb4f55d9d4a46ef8b2d6.png" />

You can use tool policies to exclude or make usage automatic for specific tools. See [MCP Tools](/customization/mcp-tools) for more background.

## How to View Tool Responses

Any data returned from a tool call is automatically fed back into the model as a context item. Most errors are also caught and returned, so that Agent mode can decide how to proceed.

<img src="https://mintcdn.com/gourmand/HGSXhgUNM88nD3iS/images/ide-extensions/agent/images/agent-response-c7287c82aac93fb4376f9d85b352b2d7.png?fit=max&auto=format&n=HGSXhgUNM88nD3iS&q=85&s=156913435132dd544d24955d426fdada" alt="agent response" width="1454" height="1038" data-path="images/ide-extensions/agent/images/agent-response-c7287c82aac93fb4376f9d85b352b2d7.png" />
