PROMPT BRO
Purchase desk

Material consumption against approved standard

BOM says two pieces. Production says three. The variance sheet says discuss.

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

By handHalf day
With AI30 min
Each time · estimate
Easier on your office computer.Send to my computer
I usePick yours. We'll show the right steps.

Prepare job material rows

Use job, SKU, output qty, approved BOM per unit and actual consumed. Same material unit.

First time? Try it on fake data first:

Privacy Remove bank account numbers, PAN, personal phone numbers and emails. Use vendor business names or codes, item codes and approved commercial details.

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

Period: [Period] Variance rule: [Variance rule] I'm attaching consumption.xlsx. A. Calculate standard usage and variance per row; hold missing values. B. List excess, under and exact; group by SKU/unit, no mixed-unit total. C. Questions for production about variance; no guessed cause. Use only supplied facts, quotes and approved terms. Flag missing GST, freight, payment days or delivery instead of assuming. Check stock against physical count or software before ordering. A person checks before sending, ordering, paying or posting.

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)
2excess rows
1under row
1held
  • J15 excess. 10 × 2 = 20; actual 25.
  • J32 under. 10 standard, actual 8.
  • J4BOM missing. Hold variance.
Before you trust it

Then send this: Recalculate all standards and variances; check missing row excluded.

If it goes wrong
Invents BOM

Reply: "Hold missing."

Claims wastage cause

Reply: "Variance only; ask production."

Mixes units

Reply: "Group SKU/unit."

Sir ne bola urgent. Ab bolo: ho gaya.

Did it work?