Skip to content

Scoped Catalog Context in Microsoft Copilot and Teams

Business users live in Teams, not in the catalog. This recipe publishes a catalog-context agent into Microsoft Copilot and Teams, scoped to one domain’s glossary and tables. The scoping is the recipe: a tightly scoped agent at one enterprise reached 100% on its evaluation set and was demoed by the CEO from a phone; unscoped agents over the whole catalog rarely get close.

Estimated cost0.5–0.75ACUper question

Two to three metered actions. Tight scoping also trims stray tool calls per question. At 0.25 ACU per metered action; confirm actual spend on the Usage page.

  1. Pick the scope

    One domain, its glossary, and on the order of 100 tables. Smaller scope means better answers; you can always add a second agent for another domain.

  2. Clone and constrain the agent

    Clone Catalog Context Search. Configure its search tools with a custom base_signature restricted to your Domain, so the agent physically can’t wander into unrelated metadata. The same filter can exclude deprecated objects via flag_types.

  3. Evaluate before publishing

    Build an eval set from the questions the target team actually asks, and iterate on metadata until it passes.

  4. Publish via Copilot Studio

    Follow the Copilot Studio setup guide to connect the agent over MCP, then publish to Teams.

  • Chart rendering doesn’t work in Copilot/Teams; keep the agent’s answers textual.
  • Viewer-role users see agent-building affordances in Alation they can’t use — set expectations or hide the entry point in your rollout comms.
  • Evaluations involving cross-database SQL can loop when run against the Alation Analytics connector; pin the agent to the domain’s primary data source.