1# Agent Panel
  2
  3The Agent Panel allows you to interact with many LLMs and coding agents that can help with various types of tasks, such as generating code, codebase understanding, and other general inquiries like writing emails, documentation, and more.
  4
  5To open it, use the `agent: new thread` action in [the Command Palette](../getting-started.md#command-palette) or click the ✨ (sparkles) icon in the status bar.
  6
  7## Getting Started {#getting-started}
  8
  9If you're using the Agent Panel for the first time, you need to have at least one LLM provider or external agent configured.
 10You can do that by:
 11
 121. [subscribing to our Pro plan](https://zed.dev/pricing), so you have access to our hosted models
 132. [using your own API keys](./llm-providers.md#use-your-own-keys), either from model providers like Anthropic or model gateways like OpenRouter.
 143. using an [external agent](./external-agents.md) like [Gemini CLI](./external-agents.md#gemini-cli) or [Claude Code](./external-agents.md#claude-code)
 15
 16## Overview {#overview}
 17
 18With an LLM provider or an external agent configured, type at the message editor and hit `enter` to submit your prompt.
 19If you need extra room to type, you can expand the message editor with {#kb agent::ExpandMessageEditor}.
 20
 21You should start to see the responses stream in with indications of [which tools](./tools.md) the model is using to fulfill your prompt.
 22From this point on, you can interact with the many supported features outlined below.
 23
 24> Note that for external agents, like [Gemini CLI](./external-agents.md#gemini-cli) or [Claude Code](./external-agents.md#claude-code), some of the features outlined below may _not_ be supported—for example, _restoring threads from history_, _checkpoints_, _token usage display_, and others. Their availability varies depending on the agent.
 25
 26### Creating New Threads {#new-thread}
 27
 28By default, the Agent Panel uses Zed's first-party agent.
 29
 30To change that, go to the plus button in the top-right of the Agent Panel and choose another option.
 31You can choose to create a new [Text Thread](./text-threads.md) or, if you have [external agents](./external-agents.md) connected, you can create new threads with them.
 32
 33### Editing Messages {#editing-messages}
 34
 35Any message that you send to the AI is editable.
 36You can click on the card that contains your message and re-submit it with an adjusted prompt and/or new pieces of context.
 37
 38### Checkpoints {#checkpoints}
 39
 40Every time the AI performs an edit, you should see a "Restore Checkpoint" button at the top of your message, allowing you to return your code base to the state it was in prior to that message.
 41
 42The checkpoint button appears even if you interrupt the thread midway through an edit attempt, as this is likely a moment when you've identified that the agent is not heading in the right direction and you want to revert back.
 43
 44### Navigating History {#navigating-history}
 45
 46To quickly navigate through recently opened threads, use the {#kb agent::ToggleNavigationMenu} binding, when focused on the panel's editor, or click the menu icon button at the top right of the panel to open the dropdown that shows you the six most recent threads.
 47
 48The items in this menu function similarly to tabs, and closing them doesn’t delete the thread; instead, it simply removes them from the recent list.
 49
 50To view all historical conversations, reach for the `View All` option from within the same menu or via the {#kb agent::OpenHistory} binding.
 51
 52### Following the Agent {#following-the-agent}
 53
 54Zed is built with collaboration natively integrated, and this design pattern extends to collaboration with AI. To follow the agent as it reads and edits in your codebase, click on the "crosshair" icon button at the bottom left of the panel.
 55
 56You can also do that with the keyboard by pressing the `cmd`/`ctrl` modifier with `enter` when submitting a message.
 57
 58### Get Notified {#get-notified}
 59
 60If you send a prompt to the Agent and then move elsewhere, putting Zed in the background, you can be notified when its response is finished via:
 61
 62- a visual notification that appears in the top right of your screen
 63- a sound notification
 64
 65These notifications can be used together or individually, according to your preference.
 66
 67You 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.
 68
 69### Reviewing Changes {#reviewing-changes}
 70
 71Once the agent has made changes to your project, the panel will surface which files, and how many of them, have been edited.
 72
 73To 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.
 74
 75You're able to reject or accept each individual change hunk, or the whole set of changes made by the agent.
 76
 77Edit diffs also appear in individual buffers. 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.
 78
 79## Adding Context {#adding-context}
 80
 81Although Zed's agent is very efficient at reading through your code base to autonomously pick up relevant context, manually adding whatever would be useful to fulfill your prompt is still very encouraged as a way to not only improve the AI's response quality but also to speed up its response time.
 82
 83In Zed's Agent Panel, all pieces of context are added as mentions in the panel's message editor.
 84You can type `@` to mention files, directories, symbols, previous threads, and rules files.
 85
 86Copying images and pasting them in the panel's message editor is also supported.
 87
 88### Selection as Context
 89
 90Additionally, you can also select text in a buffer and add it as context by using the {#kb agent::AddSelectionToThread} keybinding, running the {#action agent::AddSelectionToThread} action, or choosing the "Selection" item in the `@` menu.
 91
 92## Token Usage {#token-usage}
 93
 94Zed surfaces how many tokens you are consuming for your currently active thread near the profile selector in the panel's message editor. Depending on how many pieces of context you add, your token consumption can grow rapidly.
 95
 96Once you approach 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.
 97You can also do this at any time with an ongoing thread via the "Agent Options" menu on the top right.
 98
 99## Changing Models {#changing-models}
100
101After you've configured your LLM providers—either via [a custom API key](./llm-providers.md) 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.
102
103> The same model can be offered via multiple providers - for example, Claude Sonnet 4 is available via Zed Pro, OpenRouter, Anthropic directly, and more.
104> Make sure you've selected the correct model **_provider_** for the model you'd like to use, delineated by the logo to the left of the model in the model selector.
105
106## Using Tools {#using-tools}
107
108The new Agent Panel supports tool calling, which enables agentic editing.
109Zed 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.
110
111You can also extend the set of available tools via [MCP Servers](./mcp.md).
112
113### Profiles {#profiles}
114
115Profiles act as a way to group tools.
116Zed offers three built-in profiles and you can create as many custom ones as you want.
117
118#### Built-in Profiles {#built-in-profiles}
119
120- `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.
121- `Ask`: A profile with read-only tools. Best for asking questions about your code base without the concern of the agent making changes.
122- `Minimal`: A profile with no tools. Best for general conversations with the LLM where no knowledge of your code base is necessary.
123
124You can explore the exact tools enabled in each profile by clicking on the profile selector button > `Configure` button > the one you want to check out.
125
126Alternatively, you can also use either the command palette, by running {#action agent::ManageProfiles}, or the keybinding directly, {#kb agent::ManageProfiles}, to have access to the profile management modal.
127
128#### Custom Profiles {#custom-profiles}
129
130You can also create a custom profile through the Agent Profile modal.
131From there, you can choose to `Add New Profile` or fork an existing one with a custom name and your preferred set of tools.
132
133It's also possible to override built-in profiles.
134In the Agent Profile modal, select a built-in profile, navigate to `Configure Tools`, and rearrange the tools you'd like to keep or remove.
135
136Zed will store this profile in your settings using the same profile name as the default you overrode.
137
138All custom profiles can be edited via the UI or by hand under the `agent.profiles` key in your `settings.json` file.
139
140### Tool Approval
141
142Zed's Agent Panel surfaces the `agent.always_allow_tool_actions` setting that, if turned to `false`, will require you to give permission to any editing attempt as well as tool calls coming from MCP servers.
143
144You can change that by setting this key to `true` in either your `settings.json` or via the Agent Panel's settings view.
145
146### Model Support {#model-support}
147
148Tool calling needs to be individually supported by each model and model provider.
149Therefore, despite the presence of tools, some models may not have the ability to pick them up yet in Zed.
150You should see a "No tools" label if you select a model that falls into this case.
151
152All [Zed's hosted models](./models.md) support tool calling out-of-the-box.
153
154### MCP Servers {#mcp-servers}
155
156Similarly to the built-in tools, some models may not support all tools included in a given MCP Server.
157Zed's UI will inform you about this via a warning icon that appears close to the model selector.
158
159## Text Threads {#text-threads}
160
161["Text Threads"](./text-threads.md) present your conversation with the LLM in a different format—as raw text.
162With text threads, you have full control over the conversation data.
163You can remove and edit responses from the LLM, swap roles, and include more context earlier in the conversation.
164
165For users who have been with us for some time, you'll notice that text threads are our original assistant panel—users love it for the control it offers.
166We do not plan to deprecate text threads, but it should be noted that if you want the AI to write to your code base autonomously, that's only available in the newer, and now default, "Threads".
167
168## Errors and Debugging {#errors-and-debugging}
169
170In case of any error or strange LLM response behavior, the best way to help the Zed team debug is by reaching for the `agent: open thread as markdown` action and attaching that data as part of your issue on GitHub.
171
172You can also open threads as Markdown by clicking on the file icon button, to the right of the thumbs down button, when focused on the panel's editor.
173
174## Feedback {#feedback}
175
176Zed supports rating responses from the agent for feedback and improvement.
177
178> Note that rating responses will send your data related to that response to Zed's servers.
179> See [AI Improvement](./ai-improvement.md) and [Privacy and Security](./privacy-and-security.md) for more information about Zed's approach to AI improvement, privacy, and security.
180> **_If you don't want data persisted on Zed's servers, don't rate_**. We will not collect data for improving our Agentic offering without you explicitly rating responses.
181
182The best way you can help influence the next change to Zed's system prompt and tools is by rating the LLM's response via the thumbs up/down buttons at the end of every response. In case of a thumbs down, a new text area will show up where you can add more specifics about what happened.
183
184You can provide feedback on the thread at any point after the agent responds, and multiple times within the same thread.