PROMPT BRO
Sales desk

Pending orders and customer status messages

Customer asks you. You ask dispatch. Dispatch asks stores. Stores is at lunch.

Tested Claude Opus 5.5, medium effort · 15 Nov 2026 · on the practice files

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.

Get the pending order export

Use order ref, customer, ordered qty, dispatched qty, verified stage and confirmed delivery date if any. Include order line ref, SKU, unit, actual dispatch ref and whether a confirmed date is dispatch or delivery.

First time? Try it on fake data first:

Check with the responsible team

Use the latest production or stores update; missing dates stay unconfirmed.

Privacy Remove phone numbers, email IDs and payment details where not needed. Use only approved business names and facts.

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

Whenever I send pending orders as on [As on date], prepare status updates. Sign off: [Sign off]. A. Per unique sales order line (order ref + line ref + SKU), validate matching unit and numeric nonnegative ordered/dispatched qty. Hold duplicate or incomplete lines and negative remaining (over-dispatch); calculate remaining qty = ordered minus dispatched. Show confirmed dispatch or delivery date only with its explicit type; flag pending past confirmed date. Do not confuse dispatch with delivery or treat physical dispatch as billing approval. B. Count pending, completed and invalid order lines; list overdue and missing dates separately. Roll up orders only after checking all lines: an order is completed only when every valid line has no remaining quantity and no held line. Do not sum quantities across different SKUs or units. Give a copyable handoff table with order ref, line ref, SKU, unit, dispatched qty, remaining qty, actual stage, hold/approval status carried from earlier steps (e.g. rate held) and supporting dispatch ref if supplied; mark missing ref [confirm]. C. Draft one short (up to 6 lines) customer update per order using verified line-level stage/remaining and confirmed date/type only; if none, say date to confirm. Internal queries for invalid rows; do not claim invoice or payment is due. Use only supplied facts. Never invent customer names, testimonials, urgency, prices, discounts, delivery dates or credit terms. A person reviews 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 pending-order format. Pick your tool at the top to see how.

After that, each time: send the latest verified order and dispatch status.

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)
3pending
1completed
1invalid row
  • O25 pending, late. 10 ordered, 5 dispatched; confirmed date 12 Nov.
  • O3Date missing. 8 pending; date to confirm.
  • O5Over-dispatched. 6 dispatched vs 5 ordered; check stores.
Before you trust it

Then send this: Recheck qty and date comparisons, count groups, ensure customer messages match source and no invented date. Reconcile every order line, confirm units and date type, and do not mark an order completed if any line remains or is held.

If it goes wrong
It promises a new date

Reply: "Use confirmed date only or to confirm."

It sets negative balance to zero

Reply: "Flag invalid; check stores."

It says completed when partial

Reply: "Remaining positive means pending."

Sir ne bola urgent. Ab bolo: ho gaya.

Did it work?