Skip to content

CONCEPT Cited by 1 source

Agent governance via identity

The principle that AI agents should be governed by the same identity and access-control boundary as the humans they act on behalf of, rather than holding separate bulk credentials or bypassing the catalog with shared backend tokens.

Mechanism

Identity flows end-to-end:

  1. User authenticates via enterprise IdP (e.g. Azure AD)
  2. Agent receives a scoped token via OAuth 2.0 token exchange (on-behalf-of)
  3. Agent calls tools/data through Data Hub or MCP server
  4. Unity Catalog (or equivalent governance layer) makes the final authorization decision against the user's identity
  5. If the user lacks access to a table, masked column, or governed view, the agent receives the same boundary

"An agent can reason over the same product context a user sees, and it can call tools on the user's behalf, but it cannot become a production writer or bypass Unity Catalog with a shared backend credential." (Source: sources/2026-07-21-databricks-why-rd-data-belongs-in-the-lakehouse-and-why-agents-need-it)

Structural property

The operating model separates production ownership (engineers change pipelines/product definitions through reviewed code and governed deployment paths) from consumption (agents and users query data through governed surfaces). Agents are consumers, not producers.

Seen in

Last updated · 590 distilled / 1,788 read