What an agent workspace is, why teams are moving their AI agents out of chat windows and onto a shared visual surface, and what makes a workspace agent-ready.
Chat gave AI a voice. A workspace gives it a place to work. An agent
workspace is a shared visual surface of files, canvas, and running apps
where AI agents operate as part of the team instead of behind a chat box.
The distinction matters because the output changes. In chat, an agent's work
is a message you copy somewhere else. In a workspace, its work is the
artifact: the prototype running on the canvas, the diagram next to the brief,
the design system the next agent builds on. People and agents see the same
surface, so steering happens by pointing at things, not by re-describing
them.
Three properties separate a real agent workspace from a chat UI with
plugins:
A shared file system. Agents read and write the same files the team
sees (plans, code, assets) rather than emitting text into a transcript.
Visible, running output. The agent's work renders live (an actual
app, not a screenshot), so review happens at a glance.
Bring-your-own agent. The workspace is the surface, not the model.
You connect the coding agent you already pay for, usually over MCP, and
it works with the same tools a human would.
This pillar is where we document the category as it forms: how teams run
agents on a shared canvas, what changes about design and product work, and
the architecture underneath it.
Frequently asked questions
What is an agent workspace?
An agent workspace is a shared environment where AI agents work alongside people, with the same files, the same canvas, and visible output. Instead of a chat window that produces text, agents in a workspace produce real artifacts: running apps, diagrams, plans, and design systems the whole team can see and edit.
How is that different from an AI chat assistant?
Chat is single-player and ephemeral, so the output lives and dies in a transcript. A workspace is multiplayer and persistent: the agent's work lands on a shared surface, side by side with the team's, where it can be reviewed, branched, and built upon.
Do I need a specific AI model or subscription?
No. The workspace and the agent are separate choices. You bring the agent you already use (Claude Code, Codex, Cursor, Copilot) and connect it to the workspace, typically over MCP.