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 choose another agent, go to the plus button in the top-right of the Agent Panel and pick either one of the [external agents](./external-agents.md) installed out of the box or a new [Text Thread](./text-threads.md).
 31
 32### Editing Messages {#editing-messages}
 33
 34Any message that you send to the model is editable.
 35You can click on the card that contains your message and re-submit it with an adjusted prompt and/or new pieces of context.
 36
 37### Queueing Messages
 38
 39If you want to queue a message while the agent is going through a generation, you can do so through the `cmd/ctrl-shift-enter` keybinding.
 40A queued up message gets sent as soon as the current generation wraps up.
 41
 42### Checkpoints {#checkpoints}
 43
 44Every time the model 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.
 45
 46The checkpoint button appears even if you interrupt the thread midway through an edit, 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.
 47
 48### Navigating History {#navigating-history}
 49
 50To quickly navigate through recently updated 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.
 51Doing that will open a dropdown that shows you your six most recently updated threads.
 52
 53To view all historical conversations, reach for the `View All` option from within the same menu or via the {#kb agent::OpenHistory} binding.
 54
 55### Following the Agent {#following-the-agent}
 56
 57Zed is built with collaboration natively integrated, and this naturally extends to collaboration with AI models.
 58To follow the agent as it reads and edits in your codebase, click on the "crosshair" icon button at the bottom left of the panel.
 59
 60You can also do that with the keyboard by holding down the `cmd`/`ctrl` modifier when submitting a message.
 61
 62### Get Notified {#get-notified}
 63
 64If you send a prompt to the Agent and then put Zed in the background, you can choose to be notified when its generation wraps up via:
 65
 66- a visual notification that appears in the top right of your screen
 67- a sound notification
 68
 69These notifications can be used together or individually, and you can use the `agent.notify_when_agent_waiting` and `agent.play_sound_when_agent_done` settings keys to customize that, including turning both off entirely.
 70
 71### Reviewing Changes {#reviewing-changes}
 72
 73Once the agent has made changes to your project, the panel will surface which files, how many of them, and how many lines have been edited.
 74
 75To 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 special multi-buffer tab with all changes.
 76
 77You can accept or reject each individual change hunk, or the whole set of changes made by the agent.
 78
 79Edit diffs also appear in singleton buffers.
 80If your active tab had edits made by the AI, you'll see diffs with the same accept/reject controls as in the multi-buffer.
 81You can turn this off, though, through the `agent.single_file_review` setting.
 82
 83## Adding Context {#adding-context}
 84
 85Although 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 encouraged as a way to not only improve the AI's response quality but also to speed up its response time.
 86
 87In Zed's Agent Panel, all pieces of context are added as mentions in the panel's message editor.
 88You can type `@` to mention files, directories, symbols, previous threads, rules files, and diagnostics.
 89
 90Copying images and pasting them in the panel's message editor is also supported.
 91
 92When you paste multi-line code selections copied from a buffer, Zed automatically formats them as @-mentions with the file context.
 93To paste content without this automatic formatting, use {#kb agent::PasteRaw} to paste raw text directly.
 94
 95### Selection as Context
 96
 97Additionally, 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.
 98
 99## Token Usage {#token-usage}
100
101Zed surfaces how many tokens you are consuming for your currently active thread near the profile selector in the panel's message editor.
102
103Once you approach the model's context window, a banner appears above the message editor suggesting to start a new thread with the current one summarized and added as context.
104You can also do this at any time with an ongoing thread via the "Agent Options" menu on the top right, where you'll see a "New from Summary" button, as well as simply @-mentioning a past thread in a new one..
105
106## Changing Models {#changing-models}
107
108After 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 their models by clicking on the model selector on the message editor or by using the {#kb agent::ToggleModelSelector} keybinding.
109
110> The same model can be offered via multiple providers - for example, Claude Sonnet 4 is available via Zed Pro, OpenRouter, Anthropic directly, and more.
111> 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.
112
113### Favoriting Models
114
115You can mark specific models as favorites either through the model selector, by clicking on the star icon button that appears as you hover the model, or through your settings via the `agent.favorite_models` settings key.
116
117The great thing about favoriting models is that you can cycle through them with {#kb agent::CycleFavoriteModels} without opening the model selector, enabling quick experimentation with the models you're already most comfortable with.
118
119## Using Tools {#using-tools}
120
121The new Agent Panel supports tool calling, which enables agentic editing.
122Zed 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.
123
124You can also extend the set of available tools via [MCP Servers](./mcp.md).
125
126### Profiles {#profiles}
127
128Profiles act as a way to group tools.
129Zed offers three built-in profiles and you can create as many custom ones as you want.
130
131#### Built-in Profiles {#built-in-profiles}
132
133- `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.
134- `Ask`: A profile with read-only tools. Best for asking questions about your code base without the concern of the agent making changes.
135- `Minimal`: A profile with no tools. Best for general conversations with the LLM where no knowledge of your code base is necessary.
136
137You 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.
138
139Alternatively, 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.
140
141#### Custom Profiles {#custom-profiles}
142
143You can also create a custom profile through the Agent Profile modal.
144From there, you can choose to `Add New Profile` or fork an existing one with a custom name and your preferred set of tools.
145
146It's also possible to override built-in profiles.
147In the Agent Profile modal, select a built-in profile, navigate to `Configure Tools`, and rearrange the tools you'd like to keep or remove.
148
149Zed will store this profile in your settings using the same profile name as the default you overrode.
150
151All custom profiles can be edited via the UI or by hand under the `agent.profiles` key in your `settings.json` file.
152
153### Tool Approval
154
155Zed'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.
156
157You can change that by setting this key to `true` in either your `settings.json` or via the Agent Panel's settings view.
158
159### Model Support {#model-support}
160
161Tool calling needs to be individually supported by each model and model provider.
162Therefore, despite the presence of tools, some models may not have the ability to pick them up yet in Zed.
163You should see a "No tools" label if you select a model that falls into this case.
164
165All [Zed's hosted models](./models.md) support tool calling out-of-the-box.
166
167### MCP Servers {#mcp-servers}
168
169Similarly to the built-in tools, some models may not support all tools included in a given MCP Server.
170Zed's UI will inform you about this via a warning icon that appears close to the model selector.
171
172## Text Threads {#text-threads}
173
174["Text Threads"](./text-threads.md) present your conversation with the LLM in a different format—as raw text.
175With text threads, you have full control over the conversation data.
176You can remove and edit responses from the LLM, swap roles, and include more context earlier in the conversation.
177
178For 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.
179We 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".
180
181## Errors and Debugging {#errors-and-debugging}
182
183In 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.
184
185You 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.
186
187## Feedback {#feedback}
188
189Zed supports rating responses from the agent for feedback and improvement.
190
191> Note that rating responses will send your data related to that response to Zed's servers.
192> 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.
193> **_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.
194
195The 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.
196
197You can provide feedback on the thread at any point after the agent responds, and multiple times within the same thread.