PROMPT BRO
Customer service desk

Return requests checked against your policy

Return window is seven days. The ticket arrives on day eight with 'urgent'.

Not yet tested No recorded AI run has verified this prompt yet. Try it on the practice files first, then use the checks in step 3 before you rely on it.

By hand1 hr
With AI15 min
Per day · estimate
Easier on your office computer.Send to my computer
I usePick yours. We'll show the right steps.

Make a request sheet

Use ticket, delivery date, request date, condition and proof status. Keep actual documents locally.

First time? Try it on fake data first:

Privacy Remove customer phone numbers, addresses, order payment details and personal identifiers. Use ticket or order refs instead.

Fill the orange boxes
You send (the "prompt": the message you paste into your AI tool)
return-requests.xlsx

Whenever I send a return sheet, apply [Approved policy]. Sign off [Sign off]. A. Validate unique ticket refs, unambiguous calendar dates, and the supplied return-window rule. Calculate request date minus delivery date in whole calendar days; same day is 0, the inclusive boundary passes. Hold missing, invalid, ambiguous or negative dates, unknown condition/proof and duplicate or contradictory requests. Do not guess whether proof exists or an item is unused. B. Put every ticket in exactly one group: MEETS ALL CHECKS (goes to review); DOES NOT MEET A CRITERION (name it, e.g. outside the window, item used, proof marked No); HELD — INVALID OR INCOMPLETE (missing, invalid, ambiguous or negative date; unknown or blank condition/proof; duplicate or contradictory ticket). Give separate counts with reasons. Not meeting a criterion is not a decline: a person decides. C. Short (up to 6 lines) reply per ticket explaining next review or missing fact, never approving refund. Use only supplied facts and policy. No admission of legal liability, refund or replacement promise unless the supplied policy permits it and an authorised person confirms. No invented dates, prices or outcomes. A person checks before sending or deciding. Line limits count body lines only, not subject, greeting or sign-off. Keep every required fact; if they do not fit, say so instead of dropping one.

Set it up once. Save the approved rules and output format, not customer details. Pick your tool at the top to see how.

After that, each time: send the next masked notes or export and current rules; check the result.

First time? Try it in a normal chat: paste and send.

Which model? Use your tool's strongest model with thinking turned on.

In your AI tool: attach the files with the + button, paste, send.

What you'll get back (example, from the practice files)
2meet all checks
3don't meet a criterion
0held: invalid or incomplete
  • T29 days. Outside the 7-day window: criterion not met; a person decides.
  • T3Used. Condition not met; a person decides.
  • T4Proof: No. Invoice proof not provided; ask for it through the approved channel.
Before you trust it

Then send this: Recheck unique ticket refs, calendar dates, exact inclusive boundary, condition and proof. Hold every missing or contradictory input; count passing checks and held separately. No refund approval.

If it goes wrong
Approves return

Reply: "Checks only; manager decides."

Assumes proof

Reply: "Hold missing proof."

Adds legal rule

Reply: "Company policy only."

Sir ne bola urgent. Ab bolo: ho gaya.

Did it work?