Skip to main content

​
What is a Workspace?

A Workspace is where you build one analytics agent. It combines, in a single versioned surface:
  • The Data Model — which tables and columns the agent can see, what they mean, and who can query what (row-level security)
  • The agent’s context — knowledge base files, skills, system prompts, per-user memory, and golden assets
  • Testing — a Playground where you chat with the agent as one of your project users
  • Deployment — an embed snippet and preview links for putting the agent in your product
The Data Model and the agent are no longer separate concepts with separate version histories. A workspace is its data model — you create one workspace per agent, and a saved version captures the schema and the agent’s context together, so the two can never drift apart.
The New workspace dialog with its connection list open, ending in No database (use APIs and MCP servers only)

​
Creating a Workspace

Workspaces live inside a project. Open your project and you’ll see Your Workspaces — the list replaces the separate Data Models and Agents tabs.
A project page listing its workspaces with version and production badges, and a New workspace button
  1. Click New workspace
  2. Enter a name (and an optional description)
  3. Select the connection to base it on, or No database
  4. Click Create
Creating the workspace reads the connection’s tables and columns straight away, so they’re ready to curate. Workspace setup then opens, and the Builder agent offers to configure the workspace for you: it describes your data, writes starter skills, prompts and knowledge, and designs a theme. Click I’ll configure it myself to skip it. See Complete Setup Guide for both paths.
A workspace with No database answers through the APIs and MCP servers your project connects, instead of SQL. Its Data Model and Metrics pages stay empty until you give it a database in Workspace settings → Connection.

​
The Workspace Sidebar

Opening a workspace swaps the app sidebar to the workspace’s own sections, grouped by the part of the lifecycle they belong to: Workspace settings sits at the foot of the sidebar rather than among the pages. Read-only members see only Home and the Playground; see Roles & Permissions.
Workspace settings with General, Connection, Data access, AI models, CI, Rules & Actions and Danger zone tabs, on General with the name, description and default view
The header is a breadcrumb — Project / workspace — and both steps are switchers: the workspace picker also offers Create workspace, and the project picker Create project, so you never have to navigate back to make the next thing.

​
Draft, versions and production

The version bar lives on the workspace, above every page, and it is the one place that says where your work stands:
  • Draft — every page edits the same working copy, and edits autosave, so there is nothing to save page by page; the version selector shows when the draft was last written.
  • Save version — freezes the draft as a new numbered version, capturing the schema, the prompts, the skills and the assets together. A saved version reaches nobody until it is promoted (or, with environments, deployed).
  • Promote to production — a saved version can be promoted, and production is what deployed users and embeds are served. This replaces the old “set this data model version / agent version as production” two-step: one workspace, one production switch.
  • Reset — throw away draft changes and return the working copy to the last saved version.
Selecting a saved version in the bar makes every page read-only for that version, so you can inspect exactly what shipped. View changes beside the selector diffs the draft against the latest saved version across the whole workspace.

​
Deploying a Workspace

The Deploy page produces everything you need to put the agent in your product:
The Deploy page: a status strip saying which version the embed serves, numbered steps for frontend setup, the iframe embed code, and a preview link generator
  1. Set it up with your coding assistant — a link to create an API key, and a setup prompt carrying this organization’s, project’s and workspace’s ids and the properties the production version’s row-level security reads. Paste it into Claude Code, Cursor or another assistant working in your product’s codebase.
  2. Or set it up yourself — the same ids with copy buttons, the backend call (POST /v1/api/projects/embed-token) and the iframe (/share/workspace/{projectId}/{workspaceId}?jwt=<token>).
  3. Preview it as one of your users — generate a real, short-lived preview link (valid for one hour) and open the embed exactly as a project user would see it, before writing any integration code.
A status strip at the top answers the first question you’ll have: which version the embed currently serves. Until a version is production, the embed has nothing behind it. See Embed Upsolve in your product for the full setup.

​
Legacy Agents

Projects that were built before workspaces keep their existing agents on a legacy page, where they remain fully readable and editable. New agents cannot be created there — new work should happen in a workspace, where the data model and the agent ship together.

​
Next Steps