Features
Explainability
Capture the rationale, not just the output — so any decision can be explained months or years later.
Explainability is the capability that makes sure an advice decision is intelligible after the fact. It captures the inputs the model saw, the reasoning the model returned, the parts of that reasoning the human reviewer agreed with, and the parts they overrode. When a customer (or a regulator) asks “why did your firm recommend this?” the answer is on file.
What gets captured
- Sanitised input summary (no raw PII)
- Model rationale text and structured features
- Reviewer's annotations and overrides
- Final decision text shown to the customer
Evidence produced
- Explainability blob attached to the ledger entry
- Customer-facing explainer included in the certificate PDF
FCA mapping
- PRIN 7 — Communications with clients
- PRIN 2A.5 — Consumer support outcome
- COBS 9.2 — Suitability assessment record