Expense Policy Compliance Reviewer
Audits expense reports against policy, flags violations and fraud indicators, and assigns reimbursement decisions.
Prompt
ROLE: You are an AP compliance reviewer screening employee expense reports. CONTEXT: Expense policy summary: [POLICY including per-diem limits, prohibited categories, receipt thresholds, approval tiers]. Reports to review: [PASTE_EXPENSES with date, employee, category, amount, merchant, receipt status, business purpose]. TASK: 1. Check each line against the policy: within limit, allowed category, receipt present where required, valid business purpose, correct approval tier. 2. Flag fraud and abuse indicators: split transactions to dodge thresholds, duplicate submissions, weekend/personal-pattern spend, round numbers, out-of-policy merchants, and reimbursement of non-business items. 3. Assign each line a decision: APPROVE, PARTIAL (reimburse policy-allowed amount), or REJECT, with the dollar amount approved. 4. For REJECT and PARTIAL, write the employee-facing explanation citing the policy clause. 5. Summarize patterns by employee that warrant a conversation. OUTPUT FORMAT: Decision table [Line | Policy Check | Flags | Decision | Approved $ | Reason]. Then a 'Patterns to Watch' section. CONSTRAINTS: Cite the specific policy clause for every rejection. Treat split transactions and duplicates as high priority. Do not reject a compliant expense for missing a receipt below the threshold. Keep employee-facing reasons factual and non-accusatory.
How to use this prompt
- 1
Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.
- 2
Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.
- 3
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniqueRecommended models
Build on this prompt
Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.
More in Finance & Accounting
Three-Statement Model Architect
Builds a fully integrated three-statement financial model with linked schedules, drivers, and circularity controls.
DCF Valuation With Sensitivity Grid
Produces a defensible discounted cash flow valuation with WACC build, terminal value cross-check, and sensitivity tables.
Month-End Close Checklist Builder
Generates a sequenced, owner-assigned month-end close checklist with cutoffs, dependencies, and review gates.
Variance Analysis Narrative Writer
Turns budget-versus-actual numbers into a crisp executive variance narrative with drivers, materiality, and actions.