Weekly sales report from your CRM
Monday sales review: the CRM says open, the rep says almost closed, finance says nothing booked.
Tested Claude Opus 5.5, medium effort · 15 Nov 2026 · on the practice files
Export deal rows
Use deal ID, customer code, stage, value, expected close date and previous stage. Use one currency and period.
Confirm stage names
Agree which stages mean won, lost and open. Don't treat pipeline as booked revenue.
Privacy Remove phone numbers, email IDs and payment details where not needed. Use only approved business names and facts.
Whenever I send weekly CRM rows for [Reporting week], report using [Stage mapping]. Basis: [Value basis]. A. Count deals and sum value by current stage; show open pipeline, wins and losses separately. Flag missing amount or date for open deals and duplicate IDs. B. List stage changes from previous stage, open deals without expected close, and deal value missing. Do not forecast probability without supplied data. C. Five-line report: facts and separate suggested next checks. No invented reasons for wins/losses. Use only supplied facts. Never invent customer names, testimonials, urgency, prices, discounts, delivery dates or credit terms. A person reviews before sending or deciding.
Set it up once. Save stage mapping and report format. Pick your tool at the top to see how.
What is that?
A Project is a folder in ChatGPT that keeps your instructions and files for every chat inside it. It's on the free plan too. Checked 14 Nov 2026.
What is that?
A Project in Claude is a workspace with its own instructions and files that every chat inside it uses. Checked 14 Nov 2026.
What is that?
A Gem is a custom Gemini that loads your instructions before every chat. Free on every plan; you create it on a computer. Checked 14 Nov 2026.
What is that?
Signed in with a work account, Microsoft's Copilot Chat applies enterprise data protection: your prompts aren't used to train its models. Checked 14 Nov 2026.
After that, each time: send the weekly CRM export and reporting dates.
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.
Keep the actual records in your own Excel workbook; share only headings and rules.
Excel A:F deal ID, customer code, current stage, value, expected close, previous stage. Stage mapping [Stage mapping] and value basis [Value basis]. Give COUNTIF duplicate and missing checks, stage-change flag, SUMIFS deal values and COUNTIFS counts by stage; label missing-value pipeline partial, no forecast revenue. Tell me where to paste formulas or how to set up the local steps; use fictional examples only, no actual records.
Run locally, verify flagged rows against your source and have the responsible person approve any action.
- D2Open date missing. ₹40,000 pipeline; confirm expected close.
- D4Lost this week. ₹30,000, previous Open; reason not supplied.
- D5Open value missing. Pipeline total partial; ask rep.
Then send this: Recount deal rows and stage changes, sum known values per stage, and verify missing amounts are not zero.
It forecasts revenue
Reply: "Open pipeline only; no probability supplied."
It assumes missing value zero
Reply: "Known total, partial."
It guesses loss reason
Reply: "State change only; ask rep."
Sir ne bola urgent. Ab bolo: ho gaya.
Did it work?
If your whole team does this, we'll set it up for all of them in one session.