ML monitoring & batch data quality
Experimental reference
Compares each new batch against a frozen reference distribution and emits structured summaries for inputs, categorical shifts, and score behaviour.
What buyers should infer
Shows when freshly scored batches or inputs drift away from an agreed baseline so teams react before KPIs silently rot.
Commercial fit
Position this as an add-on milestone after batch scoring is contractual—scheduled drift artefacts you own, escalation paths scripted in writing—not 24/7 vendor babysitting.
Reference overview
Compares each new batch against a frozen reference distribution and emits structured summaries for inputs, categorical shifts, and score behaviour.
Handoff notes
The browser view is only a viewer; the substantive output is repeatable batch artefacts (reports, drift JSON). Scope stays anchored to batched files you control—ideal as a maturity add-on alongside batch scoring engagements, not a generic live APM substitute.