Skip to main content
The Agent makes it easier to explore your Peec AI data without jumping between pages or stacking multiple filters. Ask a question in plain language, and it works through your tracked data to return the answer with a chart or list already built.
Agent only works with your own Peec data, so it isn’t a general-purpose chatbot. It’s also separate from Agent Analytics, which tracks AI crawler activity on your website, and Chats, which contains the raw AI responses generated from your tracked prompts.

​
How to ask

Image Switch the sidebar to the Agent tab to open the panel next to whatever you’re viewing. You can also start from where you are: click Ask AI on a chart, or press ⌘K / Ctrl+K and hit Tab to turn your search into a question. Type your question in plain language. There’s no special syntax or commands to learn. The Agent understands the context of the page you’re viewing, including the selected brand, domain, prompt, date range, and filters. This means you can ask questions like “Why did this drop?” without having to explain what you’re referring to. Three shortcuts in the composer help you add context or start from something already available:
  • / Opens the Skills catalog. Choose a skill to use as the starting point for your conversation.
  • @ References a chart, metric, or table directly in your question.
  • + Opens the same options in browse mode, starting with Skills and Charts & metrics.
An @ reference hands the Agent that chart along with its data, so you don’t need to describe which one you mean. The Agent can also see what’s on your current page, so you can ask about what’s on screen without adding a reference.
Skills are ready-made analyses that answer common questions about your Peec data. Browse them as cards or in a list, search for the one you need, then pick one to start a conversation with that analysis. You can also create your own skills for analyses you run often.

Use the arrow keys to browse the options, Enter to select one, and Esc to dismiss.

​
Choosing a quality tier

The Quality picker in the composer sets how much work the Agent puts into a chat:
  • Normal: The fastest responses at the lowest usage. This is the default.
  • High: More reasoning, at about twice the usage.
  • Max: The most capable model, at about three to five times the usage.
The tier is saved with the chat, and your last choice becomes the default for your next new chat.

​
How the Agent responds

The answer appears as the Agent works through your question, showing its progress, the steps it’s taking, and the tools it’s using along the way. Results can appear in different formats depending on your question:
  • Charts: Visualized from the data the Agent queried.
  • To-do lists: Turn the answer into a list of next steps.
  • Multiple choice: Lets you choose between options when the Agent needs more input to continue.
While the Agent is working, the send button becomes Stop. On the latest answer, use the controls beneath it to copy the response or retry the question.
Conversations started in the panel can be opened on the full-page view with Open in Agent when you need more space. Your sessions are saved, so you can return to them later.

​
Managing approvals

The Agent can read and analyze your data without approval. Any action that makes a change, such as creating a brand, prompt, topic, or tag, is shown to you first and only happens once you click Approve. There are two ways to reduce approval steps when you want to work faster:
  • Auto: The toggle in the composer approves actions for the rest of the current chat. Always allow, in an approval’s options menu, turns on the same toggle.
  • Auto-approve actions: On the Behavior page in the sidebar, this makes Auto the starting point for your new chats.
Auto-approve covers every action that would otherwise ask, including connector tools set to Ask. Tools set to Never stay unavailable to the Agent. Leave it off if you’d rather see every change before it lands.

​
Giving the Agent context

Context is what the Agent knows before you type anything, so you don’t have to repeat it in every chat. Set it on the Context page in the sidebar, at three levels:
  • User context: Notes about you that follow you into every project. Add, edit, or delete them, up to 100.
  • Project context: Applies to this project only. Only project owners can edit it.
  • Company context: Applies to everyone in your company, across every project. Only company owners can edit it.
The Agent follows project and company context unless you tell it otherwise in the chat. Each holds up to 4,000 characters, and its switch turns it off without deleting it.
The Agent saves notes about you on its own during a chat, without asking. If you own the project or the company, it can also propose an update to that context when you share a lasting fact or instruction about it, and the update goes through an approval like any other change.

​
Connecting your tools

Connectors Connectors let the Agent use tools from products you already work in, such as Notion, Linear, HubSpot, PostHog, or Webflow. To add one:
  1. Open Connectors in the sidebar, then search for the product or browse the catalog by category.
  2. Pick it, choose where it’s Available in: All my projects or only the current project, and click Continue.
  3. Sign in with your own account for that product.
Once it’s connected, the product’s dialog shows your account and its tools:
  • Each tool is set to Always allow (runs without asking), Ask (asks before each use), or Never (hidden from the Agent). Read-only tools start on Always allow and the rest on Ask.
  • The connection’s menu changes which projects it’s available in, reconnects it, or disconnects it.
Connections are personal. Each one uses your own login, and nobody else in the company can use yours. You can have up to 10.

​
Using the Agent outside of Peec

The Agent uses the same tools as the Peec MCP server, so you can use or automate the same analyses outside the platform. Follow the MCP documentation to set it up in Claude, Cursor, or any other MCP client.