You can customize their behavior, including turning them off entirely, by using the `agent.notify_when_agent_waiting` and `agent.play_sound_when_agent_done` settings keys.

### Reviewing Changes {#reviewing-changes}

Once the agent has made changes to your project, the panel will surface which files, and how many of them, have been edited.

To see which files specifically have been edited, expand the accordion bar that shows up right above the message editor or click the `Review Changes` button ({#kb agent::OpenAgentDiff}), which opens a multi-buffer tab with all changes.

You're able to reject or accept each individual change hunk, or the whole set of changes made by the agent.

Edit diffs also appear in individual buffers.
So, if your active tab had edits made by the AI, you'll see diffs with the same accept/reject controls as in the multi-buffer.

## Adding Context {#adding-context}

Although Zed's agent is very efficient at reading through your codebase to autonomously pick up relevant files, directories, and other context, manually adding context is still encouraged as a way to speed up and improve the AI's response quality.

If you have a tab open when opening the Agent Panel, that tab appears as a suggested context in form of a dashed button.
You can also add other forms of context by either mentioning them with `@` or hitting the `+` icon button.

You can even add previous threads as context by mentioning them with `@thread`, or by selecting the "New From Summary" option from the top-right menu to continue a longer conversation, keeping it within the context window.

Pasting images as context is also supported by the Agent Panel.

### Token Usage {#token-usage}

Zed surfaces how many tokens you are consuming for your currently active thread in the panel's toolbar.
Depending on how many pieces of context you add, your token consumption can grow rapidly.

With that in mind, once you get close to the model's context window, a banner appears below the message editor suggesting to start a new thread with the current one summarized and added as context.
You can also do this at any time with an ongoing thread via the "Agent Options" menu on the top right.

## Changing Models {#changing-models}

After you've configured your LLM providers—either via [a custom API key](./configuration.md#use-your-own-keys) or through [Zed's hosted models](./models.md)—you can switch between them by clicking on the model selector on the message editor or by using the {#kb agent::ToggleModelSelector} keybinding.

## Using Tools {#using-tools}

The new Agent Panel supports tool calling, which enables agentic editing.
Zed comes with [several built-in tools](./tools.md) that allow models to perform tasks such as searching through your codebase, editing files, running commands, and others.

You can also extend the set of available tools via [MCP Servers](./mcp.md).

### Profiles {#profiles}

Profiles act as a way to group tools.
Zed offers three built-in profiles and you can create as many custom ones as you want.

#### Built-in Profiles {#built-in-profiles}

- `Write`: A profile with tools to allow the LLM to write to your files and run terminal commands. This one essentially has all built-in tools turned on.
- `Ask`: A profile with read-only tools. Best for asking questions about your code base without the concern of the agent making changes.
- `Minimal`: A profile with no tools. Best for general conversations with the LLM where no knowledge of your code base is necessary.

You can explore the exact tools enabled in each profile by clicking on the profile selector button > `Configure Profiles…` > the one you want to check out.

#### Custom Profiles {#custom-profiles}

You can create a custom profile via the `Configure Profiles…` option in the profile selector.
From here, you can choose to `Add New Profile` or fork an existing one with a custom name and your preferred set of tools.