Summarising KYC and credit notes
Listen to this lesson
Nigerian voice narration
Fictional training case. At Falcon Trust Bank's Ibadan branch, relationship manager Tunde hands credit analyst Blessing nine pages of handwritten SME loan notes for Adaeze Foods Ltd, a frozen-food distributor requesting a fictional ₦18,000,000 working capital facility. The credit committee meets in two hours and wants one page. Work through the example, identify the evidence needed and practise the method with cleared or synthetic inputs. Any additional figures in the explanation are separate practice examples, not claimed rows in a downloadable file.
Worked example
Blessing uses fictional cleared note excerpts and prompts: 'Summarise under: Business profile, Request, Repayment source, Risks, Mitigants, Recommendation. Keep each section under 40 words.' The AI produces a clean draft stating turnover of ₦3.2 million. Blessing checks the source notes and finds the actual monthly turnover is ₦4.1 million — the AI had averaged two different months incorrectly. She corrects the figure and recalculates the Debt Service Coverage Ratio herself: Net Operating Income ₦950,000 ÷ Monthly Obligation ₦620,000 = DSCR 1.53, which she inserts manually since AI summaries cannot be trusted with ratios.
The method
Structuring a credit brief into fixed headings (Business profile, Request, Repayment source, Risks, Mitigants, Recommendation) makes every brief comparable across analysts. Never let AI calculate or restate financial ratios like DSCR from a summary — always recompute from the original ledger or statement, because a single rounding or averaging error can misstate a committee's risk view by a wide margin.
Worked practice and common mistakes
For the worked case, DSCR is ₦950,000 divided by ₦620,000, or about 1.53. In practice, ₦700,000 divided by ₦480,000 is about 1.46. These are fictional calculation exercises, not approval thresholds. Keep periods consistent: monthly income must be compared with monthly obligations. A mitigant addresses a risk; it does not remove that risk automatically. The authorised committee supplies the decision.
Review before using the result
Blessing's final brief corrected the turnover figure from ₦3.2m to the verified ₦4.1m, added a manually computed DSCR of 1.53, and flagged a mitigant the AI omitted: a fictional ₦2,000,000 fixed deposit lien. The authorised committee reviews the brief; no ratio in this example automatically grants approval.
Your workplace practice
Use the recommended free assistant with this lesson's fictional example. Ask for the output described in the worked example. Keep a copy of the input and draft. Compare the result with the verification steps above, record any correction, and retain placeholders where evidence is missing. The expected result is a checked draft for human review, not an automatically approved decision. Course examples and practice responses are fictional; amounts, dates, rules and thresholds are not official guidance or supplier quotations.
Why this tool: Can structure cleared credit-note excerpts; check all material facts and omitted risks against the source.
Hit a free limit? Switch to ChatGPT or Gemini and continue — the prompt works in any assistant.