Chat

The chat sits in the right sidebar of a workspace. Hide it with Hide chat in its top row and bring it back from the same corner.

Workspace chat and project chat

What the chat talks to depends on the page you are on:

• On the workspace canvas, it is the workspace agent. Use it to research the repositories, write notes onto the canvas, or arrange material before you start a project.
• On a project's page, it is that project's agent. Use it to refine the spec, ask about the work, or answer its questions.

See agents for what each one may do.

Your chats and everyone else's

Chats belong to a person. The tabs at the top list your own chats first, each named by how it started, then everyone else's by name; a dot shows a chat where the agent is working. Everyone with access can read every chat, live.

The workspace opens on your own chat. A project opens on yours if you have written there, otherwise on the one that was active last.

If you write in someone else's chat, Yard asks first: "This is …'s chat". Choose Start my chat and your message goes to a new chat of your own, on your agent account. Their messages so far are passed to it as text, so it knows the context; their agent session is not shared. Viewers can read chats but not write in them.

Several conversations, and clearing one

You can have several chats of your own, in the workspace and in each project. Each is a separate conversation: the agent in one knows nothing of what was said in the others, and they can work at the same time.

• New chat (the + after the tabs, or /new) opens an empty chat in a new tab.
• Clear conversation (the bin in the chat's top row, or /clear) empties the chat you are looking at. Yard asks first; after that the agent no longer knows what was said.
• The × on a tab closes that chat. Its tab goes away for everyone. A chat with messages asks first. When you close your last one, a new empty chat takes its place.

Files and changes the agent made stay in all three cases. A chat cannot be cleared or closed while its agent is working: stop it first. Only you can clear or close your chats.

Context

The line above the composer shows what the agent will look at:

• With blocks selected on the canvas, each one is a chip. Remove a chip with its × to leave it out.
• With nothing selected on the workspace canvas, only the pinned blocks are the context: the line reads "2 pinned", or "nothing selected" when nothing is pinned. The agent is not given the rest of the canvas. On a canvas with sheets, these are the pins of the sheet that is open, and the agent is told which sheet it is.
• With nothing selected in a project, it reads "whole project" and the agent gets a list of everything linked to the project.
• Pinned blocks are always part of the context, in every chat and every new project. Pin a block from its menu on the canvas; it shows a striped border and a PINNED marker.

Note text is passed in full; for repositories, the lines you highlighted are marked as worth particular attention.

Attachments

Attach files with the Attach files button in the composer, by pasting, or by dropping them on the composer. They upload into the workspace and the agent can open them. Files already in the workspace or a project are attached with Add to chat after picking them in the sidebar's Files section; nothing is uploaded, the agent is told where they are.

Commands, files and dictation

• Type / at the start of a message for commands: /stop stops the agent's turn, /model opens the agent and model picker, /attach opens the file picker, /spec <what it should do> starts a project with that text and the selection as context, /new starts another chat in a new tab, /clear clears the conversation, and /discard empties the message, its attachments and context.
• Type @ and part of a name to attach a file from the chat's directory: the workspace, or the project with its worktrees.
• The microphone button dictates into the message. With a Mistral key connected under Integrations (yours, or your organization's) it records until you press it again, then the text appears; any browser that can record works. Without one it uses your browser's speech recognition (Chrome, Edge, Safari; the browser may send the audio to its own service), and where there is none the button is not shown.

↑/↓ move through the list, Enter or Tab picks, Esc closes it.

Sending, queue and stop

Enter sends; Shift+Enter starts a new line. A chat runs one message at a time. While the agent works, Send becomes Stop, and anything you send meanwhile waits in a Queued list above the composer, where you can take it back with ×. When the runner is busy with other turns, the chat shows your place in its queue ("Queued · position 1 on the runner"). Start now next to it runs your turn right away, on top of what the runner is already doing. Change limit opens the runner's settings, where Agents at once says how many turns it runs before the next ones wait; the link shows for people who manage the runner (organization admins, or its owner for a personal runner). On a runner shared by every organization, turns start in order and only an instance admin sees either link.

When the runner's machine is overloaded (its CPU or memory is over the threshold set in the runner's settings), new turns wait too, and the chat says so: "The runner is under heavy load (CPU 94%). Your message is queued (position 3) and will start automatically." The line keeps your place up to date and changes to "Runner load is back to normal. Your message has started." when it starts. The queued line and the composer show Runner busy meanwhile. Start now still works, but asks first, because it adds to the load. When the runner pauses a workspace that nobody is using to free the machine, its chat says so, and again when it restarts by itself.

If your agent account runs out of AI usage, the turn does not fail: the message waits (it shows as "Waiting for AI usage" in the queue), and so do your other messages on that account, in every chat. They start by themselves when the limit resets, or press Resume in the chat once usage is back.

A reply that ended with an error has Retry: it sends the same message again, and the agent carries on from the conversation so far. Settings → Resources lists the workspace's turns on its runner (running, waiting, failed), with Retry all failed.

The work goes on when you close the page. When the runner's connection drops for a moment (its machine slept, the network blinked), the agent keeps working, and the chat picks it up again once the runner is back, for up to five minutes. A turn that is cut off anyway (the runner or Yard restarted, or the runner stayed away longer) carries on by itself once the runner is back, ahead of anything sent meanwhile; a turn you stopped does not. Messages that were already queued when the runner went offline run once it is back. While the runner is offline, the chat is read-only.

Replies

A reply shows the agent's text and, folded underneath, the steps it took (files read and changed, commands run) and its plan. When the agent looked at a picture, its step shows that picture. File names in a reply that exist in the workspace open in Files, at the line when one is given.

Agents name repository files, pull requests, issues and commits by their address on GitHub, so what they write still works when it is copied out of Yard. A link to one of the workspace's repositories shows as a chip: a file with its lines, a pull request or issue with its state, a short commit. Resting on a chip shows a card with the details (title, author, branches, changed lines). A file chip opens the file in Yard, in the project's worktree when it has one; hold ⌘ or Ctrl to open it on GitHub instead. The same chips appear in notes and specs, where the link stays an ordinary Markdown link.

If your agent account was signed out, the reply says so with Sign in again.

Pushes and pull requests in the chat

A project's chat records what happens to its branches, as short lines between the messages: a push (with how many commits and who pushed), a pull request opened, merged, closed or reopened, and a pull request that now conflicts with its base. The pull request number opens it on GitHub. It does not matter where it happened: the Done bar, a worktree's Git card, the agent or a terminal pushing, or someone merging on GitHub. Each change is recorded once. The line goes into every open chat of the project that has messages, and the agent reads these lines too, so it knows a pull request was already merged.

Questions and action cards

When an agent cannot continue without you, it ends with questions. They show as a form: pick one option, tick several, or type an answer, then choose Submit. In a project, the project shows Needs your input until you answer, and the person who started the work is notified.

An agent can also end with an action card:

• Connect cards lead to what is missing (an agent, GitHub, storage or a runner) and say "Connected ✓" once it is.
• Suggest this to the Yard team opens a short form, pre-filled, that sends a feature request to the people who run Yard. The same goes for an integration Yard does not have yet ("Suggest it"). See feedback.
• Create spec cards come from the workspace agent when the work needs a project, for example a change to a repository. Select on canvas selects the blocks it names; Create spec… opens the Create spec dialog already filled in with its instructions, those blocks, the repositories to work in and any files to attach. Check it and choose Create project. A block that is no longer on the canvas is left out, and the card says so.

Keeping a conversation

A project's chat can be put on the workspace canvas as a chat log block with Add chat log to canvas in the chat's header. See projects and specs.