Answering audit queries with evidence
Listen to this lesson
Nigerian voice narration
Fictional training case. An audit query asks why two payments to the same vendor within one month were split into two separate amounts. This lesson shows how to structure a factual, evidence-backed response using AI to organise — not invent — your answer. 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
Chioma receives the query and first gathers the actual documents: two vouchers, the vendor invoice, the approval memo, and the relevant bank statement entries. She asks AI to structure her response under Background, Query restated, Response with evidence references, Corrective action, and Person responsible, keeping the tone strictly factual and non-defensive. The draft response references 'Voucher No. 0452 and 0453, approved under separate purchase orders dated 3 days apart for operational reasons' — a fact Chioma supplies herself, not one AI guessed — and proposes a corrective action requiring future multi-part payments to the same vendor in one month to be flagged for a single consolidated approval.
The method
Collect the actual supporting documents — vouchers, invoices, approvals, bank statements — before drafting any response, since the response's facts must come from these, not from AI's assumptions. Use a fixed structure: Background, Query, Response with evidence references, Corrective action, Person responsible. Request a professional, non-defensive tone explicitly, since audit responses are read as evidence of control, not excuses.
Worked practice and common mistakes
Create an evidence index, such as A1 invoice, A2 approval and A3 payment entry. Link each material claim to a source. If approval is missing, say so and identify the approved follow-up rather than invent an attachment. A corrective action needs an owner and review date. Distinguish a proposal from a control already implemented so the reply remains honest.
Review before using the result
Gather the real evidence documents before drafting; AI organises your facts, it doesn't supply them. A fixed structure — Background, Query, Response, Corrective action, Responsible person — reads as professional and complete. A stated corrective action signals control, not guilt.
Your workplace practice
Use the recommended free assistant with this lesson's fictional example. Draft a factual response to this audit query using these headings: Background, Query, Response with evidence references, Corrective action, Person responsible. Tone: professional, non-defensive. Query: [paste] 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.
Open Claude (free tier) and paste this prompt there. Careful, evidence-based tone for audit responses that must hold up.
Draft a factual response to this audit query using these headings: Background, Query, Response with evidence references, Corrective action, Person responsible. Tone: professional, non-defensive. Query: [paste]
Why this tool: Careful, evidence-based tone for audit responses that must hold up.
Hit a free limit? Switch to ChatGPT or Gemini and continue — the prompt works in any assistant.