Skip to main content

The AI layer

Two surfaces, one governance model.

SurfaceForReaches the platform as
Governed MCP endpointExternal AI agents and assistantsThe signed-in user
In-app assistantPeople using the consoleThe signed-in user

Neither holds business logic. Both are presentation over the same API that serves every other consumer, which is what makes their governance identical rather than merely similar.

The governed endpoint

An endpoint speaking the Model Context Protocol, exposing the platform's operations as tools an agent can call.

Each request carries the user's own credentials, so every one of the four enforcement layers re-evaluates. There is no service account: the endpoint has no privileged identity of its own to fall back on.

Read operations and mutating operations are both exposed, with mutations gated behind an explicit two-call confirmation — a preview, then a commit. An agent cannot mutate in a single unconsidered step.

The in-app assistant

The assistant explaining a match, beside the match-queue screen showing the same pair Asked why two records matched, the assistant reads the scoring breakdown rather than guessing: last name exact +5.28, email exact +5.20, first name mismatch −4.54, netting 5.94 — the same composite weight the screen beside it shows, in the clerical-review band because it sits between the two thresholds.

A chat surface inside the console. It answers questions about what is on screen, explains why a match scored as it did, and can carry out actions with approval.

It renders values exactly as the API returned them, including masked ones. It does not recompute scores or infer values — it shows what the platform said.

Autonomy modes

The assistant runs in one of three modes, per conversation:

ModeBehaviour
ManualEvery action is approved individually
Accept editsReversible actions proceed; destructive ones ask
AutoActions proceed without asking
Autonomy is never authorization

The mode governs whether a person is consulted. It never governs what the request is permitted to do. An agent in auto mode operating for a read-only user still cannot write — the request is refused exactly where any other unauthorized request is refused.

Every exposed mutation is reversible, which is what makes the more permissive modes defensible.

What agents cannot do

  • See anything the operating user cannot see.
  • Reconstruct a masked value. They receive the mask.
  • Escalate their own permissions.
  • Act untraceably. Everything lands in the audit log, attributed to the user.

Next


Last verified against commit 952ed91b (2026-08-03)