Publish workspace context for agents

Agents need structure, but dumping full schemas into every prompt doesn't scale. Workspace Context stores things like your data model once; queries pick it up automatically. List what's there, push when the join graph changes, cross-check against live tables, and keep throwaway exploration in local files instead of promoting half-baked ideas to shared docs.

How it works

Step 1: See what already exists

What shared docs are stored for this workspace? If there’s a data model, show the whole thing.

Step 2: Edit locally, push when the join graph changes

Pull the data model down so I can edit it on disk, then publish my edits back to the workspace.

Step 3: Pair with live schema

hotdata tables list is ground truth for columns. Context explains relationships and intent (context:DATAMODEL). Context names follow the same rules as SQL identifiers.

I want to compare our written data model to what’s live in the catalog. Show a slice of current tables and then show the DATAMODEL context so I can see definitions next to real columns.

Step 4: Keep scratch local, publish what's stable

Keep throwaway exploration in local files on disk. When something should guide the whole workspace, not just today's thread, publish it into DATAMODEL (or another stem) with context push. See Workspace context.

Keep my quick exploration note in a local file, then publish my updated DATAMODEL from disk so scratch stays local and the team gets the stable definitions.

Who uses this

• Teams shipping agents against one shared semantic description.
• Engineers maintaining join docs next to what catalog discovery turns up.
• Anyone keeping glossary or policy text beside technical mappings.