Alliance AI Platform: The Group's platform for building, governing and reusing AI

Prompt template

3 variables

Write the reasons for a credit decision so that a customer can understand them, based only on the reason codes from the scorecard below.

Decision: {decision}
Product: {product}
Top reason codes (from retail-credit-scorecard or sme-credit-rating):
{reason_codes}

Rules: give no more than four reasons, in plain language, most important first. Never mention protected attributes, the model's internal score, or anything not in the reason codes. Tell the customer how to request a review and what they could do to improve a future application.

{decision}{product}{reason_codes}

Playground

Simulated sandbox

{decision}{product}{reason_codes}

Example input & output

Example input

{decision}: Declined
{product}: Personal financing, MYR 30,000 over 5 years (application LN-2026-051774)
{reason_codes}: RC07 debt service ratio above policy (71%); RC12 two missed payments on an existing facility in last 6 months; RC03 credit history under 12 months

Example output

We are unable to approve your application for personal financing at this time. The main reasons are: 1. Your existing monthly commitments are high compared with your income, so the new repayment would take you above the level our lending policy allows. 2. Our records show two missed payments on an existing facility in the last six months. 3. Your credit history is shorter than 12 months. You can ask us to review this decision within 30 days by visiting any branch or calling our contact centre. Reducing existing commitments and keeping all repayments up to date for six months would help a future application.

Ownership and sensitivity

Owned by

Group Risk Management Credit Risk

Accountable owner: Rajesh Kumar

Who approves access

Owner, Credit Risk, Rajesh Kumar
Data Governance Office, Ahmad Faizal
Model Risk Management, Dr. Kavitha Subramaniam

In Credit decisioning (Tier 1)

Strictly Confidential

Customer-level data under banking secrecy and PDPA, and models that decide on customers.

Named-user entitlement with the data owner's consent and a stated purpose; reviewed on expiry.

Credit decision: Outputs feed a decision on a customer's credit; fairness and explainability tests apply.
Banking secrecy: Customer account information protected under the Financial Services Act 2013.
Customer PII: Contains or processes personal data about customers (PDPA 2010).
GenAI: Generates text; prompt screening for customer data and output review apply.

Community · 0 threads

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

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

Credit Decision Explainer