TASMU AI

Agents / mcit

Steward Agent

Agent runGovernanceGovernment-RestrictedLimited riskGov Reuse96 runs/30d

Watches every data asset for freshness, quality score and schema change on each ingestion wave, recomputes the Data Health Score, and raises a ticket to the owning entity before a downstream model is affected. Publishes the new version when nothing flags; holds it when the PII scan does.

Governs the marketplace

Agent runAll governance agents →

An agent executes the process end to end and logs what it did. No human is in the path, because there is no discretion to exercise and no consequence to carry.

Acts for
Data Steward
Action class
write
Decisions / 30d
96
Safe-state returns / 30d
4

Processes covered

  • Dataset ingestion and profiling
  • Data quality and schema watch
  • Steward ticketing

Stages:monitor

Memory

Retains schema history per dataset for change detection; no row-level retention.

Safe state

Holds the incoming wave unpublished and tickets the steward when profiling or the PII scan cannot complete.

Reviewer time per case: 0 min with this agent, 115 without.

Tools

  • Ingestion bucket watcher
  • Schema profiler
  • PII scanner
  • Data Health Score calculator
  • Ticketing

Data access scope

  • Read-only: incoming data waves and existing schemas
  • Write: health scores, new dataset versions, steward tickets
  • PII scan results are kept as counts and column names, never as values

Guardrails

  • A PII flag holds the version for the publisher's sign-off; it is never auto-published
  • Schema changes that break a consuming model open a ticket to both the steward and the model owner
  • Never deletes or overwrites a prior version

Human-in-the-loop

  • Publisher signs off when the PII scan flags anything

Orchestration

Trigger / IntakeLLM Orchestratorfanar-gov-7b-instructIngestion bucket watcherSchema profilerPII scannerData Health Score calculatorHumansign-off

Every tool call is scoped by the declared data access above; the orchestrator cannot reach systems outside it. Owning entity: MCIT.

Live demo run

Watch the agent execute a real scenario step by step, every tool call, validation, and human checkpoint is traced and auditable. Typical run: ~5.2s.

Owning entity

mcMCIT

Updated 2026-07-31. Run traces retained 24 months for audit under the platform governance policy.

Community · 0 threads

Questions, findings and requests from the entities that use this asset. Owners reply here; threads with upvotes surface to the owning entity's inbox.

No threads yet. Be the first entity to ask, or to share what you found.