Drift Watch Agent
Monitors every published asset against the operating envelope declared in its manifest and its reference distributions. When a threshold is breached it opens a re-certification or retirement case immediately, rather than waiting for the renewal date, and proposes a costed retrain to the owner.
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
- MLOps Engineer
- Action class
- advisory
- Decisions / 30d
- 1.2K
- Safe-state returns / 30d
- 2
Processes covered
- Drift watch and re-certification trigger
- Retrain proposal with costed compute
- Low-usage retirement review
Memory
Rolling 90-day telemetry window per asset; older aggregates archived to the audit store.
Safe state
Raises a 'telemetry gap' alert to MLOps and pauses drift verdicts for the affected asset when telemetry stops arriving.
Reviewer time per case: 0 min with this agent, 30 without.
Tools
- Model telemetry (PSI, accuracy, latency)
- Operating-envelope reader
- Retrain cost estimator
- Re-certification case writer
- Owner notifier
Data access scope
- Read-only: production telemetry and reference distributions
- Write: drift alerts, re-certification cases and retrain proposals
- No access to inference inputs or outputs beyond aggregated statistics
Guardrails
- Never starts a retrain or rolls back a version; the owner accepts the cost first
- A breach on a High-risk asset pauses new entitlements until the owner responds
- Alerts carry the threshold, the observed value and the window, never a bare warning
Human-in-the-loop
- Model owner accepts the retrain cost before any job starts
- Owning entity confirms retirement when usage has collapsed
Orchestration
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: ~5.1s.
Owning entity
Updated 2026-07-27. 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.