AI Credit Scorecard Template — Google Sheets + Notion

Prompts are the surface layer. Underneath sits the scorecard — the thing your credit committee actually signs. This is that scorecard, built to be read, tuned, and defended, with AI doing the qualitative heavy lifting in exactly the right places and staying out of the quantitative ones.

WHAT'S INSIDE

• Excel scorecard (.xlsx) with 6 sheets: Scorecard (3 pre-loaded example applicants + 97 blank rows), Weights (configurable), Thresholds (A/B/C/D grade boundaries), Decision Rules (grade-to-action mapping), AI Prompts (reference prompts), README.

• A setup guide (PDF + Markdown) walking through configuration, customisation, and scoring.

• The exact AI-assist prompts for the qualitative cells — see them, modify them, replace them.

• Decision-rules appendix: grade-to-action mapping, deviation thresholds, override criteria.

SEVEN SCORING DIMENSIONS

Identity & KYC integrity · Employment & income stability · Affordability & leverage · Credit history · Behavioural signals · Narrative risk (AI-augmented) · Collateral / co-applicant uplift.

WHERE THE AI HELPS

Exactly two cells. One for employment-stability summary, one for narrative-risk paragraph. Everything else is arithmetic. That deliberate scoping is the difference between a scorecard your credit committee trusts and one they reject.

HONEST CAVEAT

This is a heuristic + AI-augmented scorecard, not a statistical scorecard trained on default data. If you have 10,000+ loans of history and a data scientist, build the latter. If not, this beats spreadsheet-by-vibes every time.

WORKS IN

Excel 2016+, Google Sheets (via File → Import), Apple Numbers (some conditional-formatting loss).

14-day refund, no questions.