Suspense entries matched to possible sources
Suspense ledger: where entries go while everyone waits for someone else to remember.
Tested Claude Opus 5.5, medium effort · 15 Nov 2026 · on the practice files
Get the suspense list
Use entry ref, date, signed amount and non-personal reference hint. Add other ledger candidate refs and amounts on the same sign basis.
Confirm matching basis
Only clear a suspense item after checking the original evidence. Use sample first.
Privacy Use masked refs and amounts; remove bank and customer payment identifiers. Delete bank account numbers; replace customer UPI IDs and phone numbers.
I'm attaching suspense and candidate lists as on [As on date]. Rule: [Match rule]. A. Show each suspense ref, age in days, exact signed-amount candidates and status: likely, ambiguous or none. A matching reference hint may identify a likely row only if it agrees with the signed amount. Hold both if two rows compete for the same candidate; keep unhinted multiple original candidates ambiguous even if another row has a likely hint. Flag duplicate refs, invalid signed amounts, missing dates or negative age; never reuse a candidate or force a tie. B. Sum suspense amounts and status amounts; list evidence to confirm each likely match. C. Questions for accounts to resolve ambiguous or no-match items. No reclassification or clearing automatically. Use only my data. GST rates, HSN and TDS rates only from my supplied figures; never guess tax treatment. This is a first pass; a person checks and posts any final entries in Tally/Busy. Do not repeat personal identifiers from the data (personal names, phone numbers, email or postal addresses, bank account numbers, UPI IDs, PAN, Aadhaar, GSTIN or other registration numbers) unless the output genuinely needs one; use the code, ref or row instead, and copy any needed identifier exactly. Keep masked values masked; never guess, complete or unmask them.
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.
Two sheets: suspense A:D ref, date, signed amount, masked hint; candidates A:B ref, signed amount. As on [As on date], rule [Match rule]. Give formulas for age, exact-amount count, candidate list and hint match, ambiguity and possible reuse flags; sum by status. Never automatically clear. Tell me where to paste formulas or how to set up the local steps; use fictional examples only, no actual records. Hold competing proposals and all duplicate refs; check original candidate list, not after a provisional allocation. Never infer a match from row order.
Run locally, verify flagged rows against your source and have the responsible person approve any action.
- S2₹5,000 ambiguous. C2 and C3 both match; no hint.
- S4₹3,000 no match. Check original entry.
- S5C3 hinted. ₹5,000 matches; S2 stays unresolved until verified.
Then send this: Recheck signed amounts, original candidate lists, hints and unique refs; hold competing proposals, invalid dates/amounts and reconcile known status amounts to total known suspense.
It picks a tie
Reply: "Show all candidates; hold ambiguity."
It changes sign
Reply: "Exact signed amount only."
It clears without evidence
Reply: "Draft review, no posting."
Sir ne bola urgent. Ab bolo: ho gaya.
Did it work?
Doing this every week? Save it once.
Save the prompt in your AI tool, so next time you only drop the files in. 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.
If your whole team does this, we'll set it up for all of them in one session.