Reimbursement decision email prompt: free ChatGPT template
Updated · By Robert Breen
Use this when an employee submits an expense for reimbursement and you want a quick, consistent answer. The AI applies your written policy, names the rule it used, and drafts a friendly email that says what happens next. You still make the decision: the status line at the top is a suggestion you confirm before anything is sent. It suits small teams without an expense system, and it mirrors the policy check in the AI Expense Reimbursement Form lesson.
The prompt
Copy it into ChatGPT (or Claude, Gemini or Copilot) and replace every [BLANK] with your own details. It uses the four parts from Prompt Writing 101: Role, Context, Task and Format.
Role: You are the office manager at [BUSINESS], replying to an employee about an expense reimbursement request. Context: Our reimbursement policy: [POLICY]. The request: [REQUEST]. Apply only this policy. Don't approve or turn down anything for a reason that isn't in it, and don't give tax advice. When reimbursements are paid: [PAYMENT TIMING]. Don't promise any other date. Task: First, pick the status the policy points to and quote the rule that decides it. Then write a short email to the employee with the status and exactly what they need to do next, if anything. Format: Line one, for me: "Status: ... (rule: ...)". Then a blank line and the email: under 100 words, friendly and brief, greet them by first name, no emoji. If the request is missing something the policy needs, ask for that one thing.
Fill in the blanks
[BUSINESS]- Your business name.
[POLICY]- Your reimbursement rules, word for word: amount limits, receipt rules, who approves what.
[REQUEST]- Employee's first name, what they spent, the amount, the date, the business purpose, and whether a receipt is attached.
[PAYMENT TIMING]- When approved requests get paid, such as "with the next payroll." If you don't have a set rule, say so.
Example, filled in
A made-up example from the free lesson Build an Expense Reimbursement Form With AI Policy Checks. The made-up firm Maple Street Bookkeeping uses a three-status reimbursement policy in the lesson. An employee has submitted train tickets for a client workshop.
Role: You are the office manager at Maple Street Bookkeeping, a small bookkeeping firm, replying to an employee about an expense reimbursement request. Context: Our reimbursement policy: Needs receipt if the employee says there is no receipt or doesn't mention one. Needs manager OK if the amount is $100 or more. Approved if under $100, with a receipt and a clear business purpose. The request: Sam, round-trip train tickets to Philadelphia on September 29 for a client workshop, $142.50, receipt attached. Apply only this policy. Don't approve or turn down anything for a reason that isn't in it, and don't give tax advice. When reimbursements are paid: approved requests are paid with the next payroll. Don't promise any other date. Task: First, pick the status the policy points to and quote the rule that decides it. Then write a short email to the employee with the status and exactly what they need to do next, if anything. Format: Line one, for me: "Status: ... (rule: ...)". Then a blank line and the email: under 100 words, friendly and brief, greet them by first name, no emoji. If the request is missing something the policy needs, ask for that one thing.
What a good answer looks like
- "Status: Needs manager OK (rule: the amount is $100 or more)."
- An email that says the request is with the manager, not that it was denied.
- Payment timing only as "with the next payroll once it's approved," with no specific date.
- Nothing asked of Sam, because the receipt and purpose are already there.
How to check it before you use it
An AI draft can sound right and still say something you never told it. Use the habit from the Reply Faster lesson: check every promise, name, date and number against what you gave it before anything goes out.
- Confirm the status yourself against the policy. The AI suggests; you decide.
- Check the amount and date in the email against the request and receipt.
- Make sure it didn't promise approval ("this should be fine") or a payment date the policy doesn't give.
- If the email asks for something, make sure the policy actually requires it.
Why this prompt works
Asking for the status and the deciding rule before the email makes the AI show its reasoning where you can check it in one glance. The Context's "apply only this policy" keeps it from inventing a rule that sounds sensible. That is grounding in a small, practical form.
Practice it in the free lesson
Build an Expense Reimbursement Form With AI Policy Checks: Build an expense reimbursement form in Lovable for Maple Street Bookkeeping and connect it to n8n — the AI agent checks each request against the policy, saves it to Google Sheets and emails the employee the status. You do every step yourself in a practice copy of Lovable and n8n, and nothing touches your real accounts.
Also useful: Reply Faster: Turn a Messy Customer Email Thread into a Clear, Friendly Reply
Terms used here
Related prompts
- Receipt details extraction prompt: Pull date, vendor, tax, total and job from receipt photos into a table, with "Unreadable" instead of guesses and a check that…
- Expense categorization prompt: Sort a batch of expenses into your own categories, with a short note each and a Needs Review bucket for anything unclear…
- Policy summary for staff prompt: Turn a long internal policy into a plain staff summary: who it applies to, what to do, limits and deadlines, with unclear lines…