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](./custom-api-keys.md#providers).
  9
 10## Overview {#overview}
 11
 12After you've configured some LLM providers, you're ready to start working with the Agent Panel.
 13
 14Type at the message editor and hit `enter` to submit your prompt to the LLM.
 15If you need extra room to type, you can expand the message editor with {#kb agent::ExpandMessageEditor}.
 16
 17You should start to see the responses stream in with indications of which [tools](/ai/tools.md) the AI is using to fulfill your prompt.
 18For example, if the AI chooses to perform an edit, you will see a card with the diff.
 19
 20### Editing Messages {#editing-messages}
 21
 22Any message that you send to the AI is editable.
 23You can click on the card that contains your message and re-submit it with an adjusted prompt and/or new pieces of context.
 24
 25### Checkpoints {#checkpoints}
 26
 27Every time the AI performs an edit, you should see a "Restore Checkpoint" button to the top of your message.
 28This allows you to return your code base to the state it was in prior to that message.
 29This is usually valuable if the AI's edit doesn't go in the right direction.
 30
 31### Navigating History {#navigating-history}
 32
 33To 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 interactions with the LLM.
 34
 35The items in this menu work similarly to tabs, and closing them from there doesn't delete the thread; just takes them out of the recent list.
 36
 37You can also view all historical conversations with the `View All` option from within the same menu or by reaching for the {#kb agent::OpenHistory} binding.
 38
 39### Reviewing Changes {#reviewing-changes}
 40
 41If you are using a profile that includes write tools, and the agent has made changes to your project, you'll notice the Agent Panel surfaces the fact that edits have been applied.
 42
 43You can click on the accordion bar that shows up right above the panel's editor see which files have been changed, or click `Review Changes` ({#kb agent::OpenAgentDiff}) to open a multi-buffer to review them.
 44Reviewing includes the option to accept or reject each edit, or accept or reject all edits.
 45
 46Diffs with changes also appear in individual buffers.
 47So, if your active tab had changes added by the AI, you'll see diffs with the same accept/reject controls as in the multi-buffer.
 48
 49## Adding Context {#adding-context}
 50
 51Although Zed's agent is very efficient at reading through your code base to autonomously pick up relevant files, directories, and other context, manually adding context is still usually encouraged as a way to speed up and improve the AI's response quality.
 52
 53If you have a tab open when triggering the Agent Panel, that tab will appear as a suggested context in form of a dashed button.
 54You can also add other forms of context, like files, rules, and directories, by either typing `@` or hitting the `+` icon button.
 55
 56You can even add previous threads as context with the `@thread` command, or by selecting "Start new from summary" option from the top-right menu in the agent panel to continue a longer conversation and keep it within the size of context window.
 57
 58Images are also supported, and pasting them over in the panel's editor works.
 59
 60### Token Usage {#token-usage}
 61
 62Zed surfaces how many tokens you are consuming for your currently active thread in the panel's toolbar.
 63Depending on how many pieces of context you add, your token consumption can grow rapidly.
 64
 65With that in mind, once you get close to the model's context window, we'll display a banner on the bottom of the message editor offering to start a new thread with the current one summarized and added as context.
 66You can also do this at any time with an ongoing thread via the "Agent Options" menu on the top right.
 67
 68## Changing Models {#changing-models}
 69
 70After you've configured your LLM providers—either via [a custom API key](/ai/custom-api-keys.md) or through [Zed's hosted models](/ai/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.
 71
 72## Using Tools {#using-tools}
 73
 74The new Agent Panel supports tool calling, which enables agentic collaboration with AI.
 75Zed comes with [several built-in tools](/ai/tools.md) that allow models to perform tasks such as searching through your codebase, editing files, running commands, and others.
 76
 77You can also extend the set of available tools via [MCP Servers](/ai/mcp.md).
 78
 79### Profiles {#profiles}
 80
 81Profiles introduce a way to group tools.
 82Zed offers three built-in profiles and you can create as many custom ones as you want.
 83
 84#### Built-in Profiles {#built-in-profiles}
 85
 86- `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.
 87- `Ask`: A profile with read-only tools. Best for asking questions about your code base without the fear of the agent making changes.
 88- `Minimal`: A profile with no tools. Best for general conversations with the LLM where no knowledge of your code is necessary.
 89
 90You 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.
 91
 92#### Custom Profiles {#custom-profiles}
 93
 94You may find yourself in a situation where the built-in profiles don't quite fit your specific needs.
 95Zed's Agent Panel allows for building custom profiles.
 96
 97You can create new profile via the `Configure Profiles…` option in the profile selector.
 98From here, you can choose to `Add New Profile` or fork an existing one with your choice of tools and a custom profile name.
 99
100You can also override built-in profiles.
101With a built-in profile selected, in the profile selector, navigate to `Configure Tools`, and select the tools you'd like.
102
103Zed will store this profile in your settings using the same profile name as the default you overrode.
104
105All custom profiles can be edited via the UI or by hand under the `assistant.profiles` key in your `settings.json` file.
106
107### Model Support {#model-support}
108
109Tool calling needs to be individually supported by each model and model provider.
110Therefore, despite the presence of tools, some models may not have the ability to pick them up yet in Zed.
111You should see a "No tools" disabled button if you select a model that falls into this case.
112
113We want to support all of them, though!
114We may prioritize which ones to focus on based on popularity and user feedback, so feel free to help and contribute.
115
116All [Zed's hosted models](./models.md) support tool calling out-of-the-box.
117
118### MCP Servers {#mcp-servers}
119
120Similarly to the built-in tools, some models may not support all tools included in a given MCP Server.
121Zed's UI will inform about this via a warning icon that appears close to the model selector.
122
123## Text Threads {#text-threads}
124
125["Text threads"](./text-threads.md) present your conversation with the LLM in a different format—as raw text.
126With text threads, you have full control over the conversation data.
127You can remove and edit responses from the LLM, swap roles, and include more context earlier in the conversation.
128
129For 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.
130We 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".
131
132### Text Thread History {#text-thread-history}
133
134Content from text thread are saved to your file system.
135Visit [the dedicated docs](./text-threads.md#history) for more info.
136
137## Errors and Debugging {#errors-and-debugging}
138
139In 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.
140
141This action exposes the entire thread in the form of Markdown and allows for deeper understanding of what each tool call was doing.
142
143You 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.
144
145## Feedback {#feedback}
146
147Every change we make to Zed's system prompt and tool set, needs to be backed by an eval with good scores.
148
149Every 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.
150
151> Note that rating responses will send your data related to that response to Zed's servers.
152> See [AI Improvement](./ai-improvement.md) and [Privacy and Security](/ai/privacy-and-security.md) for more information about Zed's approach to AI improvement, privacy, and security.
153> **_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.
154
155The 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.
156In case of a thumbs down, a new text area will show up where you can add more specifics about what happened.
157
158You can provide feedback on the thread at any point after the agent responds, and multiple times within the same thread.