1# Agent Panel
  2
  3The Agent Panel provides you with a way to interact with LLMs.
  4You can use it for various tasks, such as generating code, asking questions about your code base, and general inquiries such as emails and documentation.
  5
  6To open the Agent Panel, use the `agent: new thread` action in [the Command Palette](../getting-started.md#command-palette) or click the ✨ (sparkles) icon in the status bar.
  7
  8If you're using the Agent Panel for the first time, you'll need to [configure at least one LLM provider](./configuration.md).
  9
 10## Overview {#overview}
 11
 12After you've configured one or more LLM providers, type at the message editor and hit `enter` to submit your prompt.
 13If you need extra room to type, you can expand the message editor with {#kb agent::ExpandMessageEditor}.
 14
 15You should start to see the responses stream in with indications of [which tools](./tools.md) the AI is using to fulfill your prompt.
 16
 17### Editing Messages {#editing-messages}
 18
 19Any message that you send to the AI is editable.
 20You can click on the card that contains your message and re-submit it with an adjusted prompt and/or new pieces of context.
 21
 22### Checkpoints {#checkpoints}
 23
 24Every time the AI performs an edit, you should see a "Restore Checkpoint" button to the top of your message, allowing you to return your codebase to the state it was in prior to that message.
 25
 26### Navigating History {#navigating-history}
 27
 28To quickly navigate through recently opened threads, use the {#kb agent::ToggleNavigationMenu} binding, when focused on the panel's editor, or click the hamburger icon button at the top left of the panel to open the dropdown that shows you the six most recent threads.
 29
 30The 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.
 31
 32To view all historical conversations, reach for the `View All` option from within the same menu or via the {#kb agent::OpenHistory} binding.
 33
 34### Following the Agent {#following-the-agent}
 35
 36Zed is built with collaboration natively integrated.
 37This approach extends to collaboration with AI as well.
 38To follow the agent reading through your codebase and performing edits, click on the "crosshair" icon button at the bottom left of the panel.
 39
 40### Get Notified {#get-notified}
 41
 42If you send a prompt to the Agent and then move elsewhere, thus putting Zed in the background, you can be notified of whether its response is finished either via:
 43
 44- a visual notification that appears in the top right of your screen
 45- or a sound notification
 46
 47Both notification methods can be used together or individually according to your preference.
 48
 49You 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.
 50
 51### Reviewing Changes {#reviewing-changes}
 52
 53Once the agent has made changes to your project, the panel will surface which files, and how many of them, have been edited.
 54
 55To 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.
 56
 57You're able to reject or accept each individual change hunk, or the whole set of changes made by the agent.
 58
 59Edit diffs also appear in individual buffers.
 60So, 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.
 61
 62## Adding Context {#adding-context}
 63
 64Although 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.
 65
 66If you have a tab open when opening the Agent Panel, that tab appears as a suggested context in form of a dashed button.
 67You can also add other forms of context by either mentioning them with `@` or hitting the `+` icon button.
 68
 69You 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.
 70
 71Pasting images as context is also supported by the Agent Panel.
 72
 73### Token Usage {#token-usage}
 74
 75Zed surfaces how many tokens you are consuming for your currently active thread in the panel's toolbar.
 76Depending on how many pieces of context you add, your token consumption can grow rapidly.
 77
 78With 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.
 79You can also do this at any time with an ongoing thread via the "Agent Options" menu on the top right.
 80
 81## Changing Models {#changing-models}
 82
 83After 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.
 84
 85## Using Tools {#using-tools}
 86
 87The new Agent Panel supports tool calling, which enables agentic editing.
 88Zed 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.
 89
 90You can also extend the set of available tools via [MCP Servers](./mcp.md).
 91
 92### Profiles {#profiles}
 93
 94Profiles act as a way to group tools.
 95Zed offers three built-in profiles and you can create as many custom ones as you want.
 96
 97#### Built-in Profiles {#built-in-profiles}
 98
 99- `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.
100- `Ask`: A profile with read-only tools. Best for asking questions about your code base without the concern of the agent making changes.
101- `Minimal`: A profile with no tools. Best for general conversations with the LLM where no knowledge of your code base is necessary.
102
103You 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.
104
105#### Custom Profiles {#custom-profiles}
106
107You can create a custom profile via the `Configure Profiles…` option in the profile selector.
108From here, you can choose to `Add New Profile` or fork an existing one with a custom name and your preferred set of tools.
109
110You can also override built-in profiles.
111With a built-in profile selected, in the profile selector, navigate to `Configure Tools`, and select the tools you'd like.
112
113Zed will store this profile in your settings using the same profile name as the default you overrode.
114
115All custom profiles can be edited via the UI or by hand under the `assistant.profiles` key in your `settings.json` file.
116
117### Model Support {#model-support}
118
119Tool calling needs to be individually supported by each model and model provider.
120Therefore, despite the presence of tools, some models may not have the ability to pick them up yet in Zed.
121You should see a "No tools" label if you select a model that falls into this case.
122
123We want to support all of them, though!
124We may prioritize which ones to focus on based on popularity and user feedback, so feel free to help and contribute to fast-track those that don't fit this bill.
125
126All [Zed's hosted models](./models.md) support tool calling out-of-the-box.
127
128### MCP Servers {#mcp-servers}
129
130Similarly to the built-in tools, some models may not support all tools included in a given MCP Server.
131Zed's UI will inform about this via a warning icon that appears close to the model selector.
132
133## Text Threads {#text-threads}
134
135["Text threads"](./text-threads.md) present your conversation with the LLM in a different format—as raw text.
136With text threads, you have full control over the conversation data.
137You can remove and edit responses from the LLM, swap roles, and include more context earlier in the conversation.
138
139For 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.
140We 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".
141
142### Text Thread History {#text-thread-history}
143
144Content from text thread are saved to your file system.
145Visit [the dedicated docs](./text-threads.md#history) for more info.
146
147## Errors and Debugging {#errors-and-debugging}
148
149In 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.
150
151This action exposes the entire thread in the form of Markdown and allows for deeper understanding of what each tool call was doing.
152
153You 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.
154
155## Feedback {#feedback}
156
157Every change we make to Zed's system prompt and tool set, needs to be backed by an eval with good scores.
158
159Every time the LLM performs a weird change or investigates a certain topic in your codebase completely incorrectly, it's an indication that there's an improvement opportunity.
160
161> Note that rating responses will send your data related to that response to Zed's servers.
162> 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.
163> **_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.
164
165The 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.
166In case of a thumbs down, a new text area will show up where you can add more specifics about what happened.
167
168You can provide feedback on the thread at any point after the agent responds, and multiple times within the same thread.