AI invoice reconciliation: all three found $940, but one follow-up reversed the rule
Six invoice rows add up to $2,152. Only $940 belongs in the payment-review queue after removing a duplicate and checking prices, quantities and arithmetic. ChatGPT, Gemini and Claude all reached that $940 result. The difference appeared in what they told the next person to do. For this handoff, WekeyLab AI would start with ChatGPT’s answer.
The answer we would use: ChatGPT’s handoff
ChatGPT provides a five-invoice table, the $940 eligible amount, a separate $572 held subtotal and an action for each exception. Its most useful sentence concerns East’s unknown receipt: at least 10 units must be available for billing before a 10-unit invoice can pass. It also leaves the incorrect Lake invoice on hold rather than quietly replacing $190 with $200.
Gemini reaches the same amounts with a longer explanation. Claude’s initial classifications are also correct, but its follow-up tells the reader to check whether the received quantity is 10 or fewer. That reverses the threshold. Getting the final total right does not make every instruction safe to copy.
One fixed question, six deliberately different rows
The fictional US team accepts partial invoices. A pass requires an exact unit-price match, correct quantity-times-price arithmetic and an invoiced quantity no greater than either ordered units or received units available for billing. Unknown receipt quantity stays unknown. There is no tax, freight, foreign-exchange adjustment or tolerance in this exercise.
The duplicate key is supplier plus invoice number. North N100 and West N100 are different invoices; two identical North N100 rows are one invoice. All receipts are otherwise unbilled. We fixed these rules and the checks before asking the websites the same English question, once each, with no answer-length limit.
The PO inputs are ordered units / unit price / received units: North P1 100/$8/80; West P2 20/$15/20; East P3 10/$25/unknown; South P4 12/$10/12; Lake P5 5/$40/5. Invoice rows are North N100 80×$8=$640 twice; West N100 20×$15=$300; East E200 10×$25=$250; South S300 12×$11=$132; Lake L400 5×$40 with a stated $190 total. The full submitted question is preserved below.
The control total: $1,512, not $2,152
The six raw rows total $2,152. Removing the repeated $640 North invoice leaves five unique invoices totaling $1,512 as stated. North’s $640 and West’s $300 pass, producing $940 for review. East $250, South $132 and Lake $190 remain separate holds: $572. The control equation is $1,512 = $940 + $572. These are stated invoice amounts, not a forecast of the eventual payment.
North invoiced 80 of 100 ordered units and all 80 are received, so partial billing passes. South’s multiplication is correct, but its $11 invoice price conflicts with the $10 PO price: a $12 difference across 12 units. Do not replace its $132 amount with $120 and pass it. Lake’s multiplication yields $200, which is $10 above its stated $190. Do not turn that calculation into a passed $200 invoice either.
A separate Python Decimal calculation checked each row and all totals. We reviewed three originals against eight precommitted checks each. The raw and unique totals are additional cross-checks: the prompt asked for the forward amount and exceptions, so their omission is not an arithmetic error. No accounting system was connected and no payment was executed.
ChatGPT: short enough to reuse, specific enough to verify
The response deduplicates North without accidentally removing West’s invoice with the same number. It separates the held stated amount from the amount that can proceed and explains why the Lake total must not be replaced automatically. The handoff repeats the key identifiers, making it usable without rereading the entire question.
For East, “at least 10” states the correct direction of the test. The original also specifies quantity available for billing, which matters because a receipt record is useful only if those units remain available for this invoice under the exercise rules. We found no failed row classification or invented payment date in this response.
Our edits are modest: bring the $572 held subtotal into the final handoff itself and add the $1,512 control total. These improve the document’s audit trail without changing ChatGPT’s decisions.
ChatGPT: “If it is at least 10 units, the invoice can then pass the stated checks.”
Gemini: a fuller walkthrough with a more formal memo
Gemini explains each row, repeats the decisions in a table, then drafts a memo. This makes the arithmetic easy to inspect, though the same results appear several times. It correctly keeps West separate, holds the unknown receipt and preserves the stated $190 as a hold. Its $940 and $572 subtotals match the independent calculation.
The memo calls the first group “Approved to Move to Payment-Review Queue.” In context, that is permission to enter review, not a claim that money was paid. We would still use “eligible for review” to make the status immediately clear. The closing promise to follow up also needs an actual owner before someone sends it.
For South, it suggests a credit memo or revised invoice. That is a proposed follow-up route, not an action it performed or a reason to release the hold now. The essential instruction remains: resolve the unit-price mismatch and recheck the documents.
Gemini: “Total Held for Checking: $572.00”
Claude: the table passed; the receipt instruction did not
Claude identifies all five unique invoices correctly and gives the same $940 review amount. It explicitly says reconciliation is not final approval. The problem is a later instruction, written in Korean, to verify whether P3’s received quantity is “10 or fewer.” For a 10-unit invoice, the necessary condition is 10 or more available for billing, while the invoiced quantity must also stay within the order.
This is a real difference in the next action, not merely style. With 9 received units, the invoice must remain held. With 10, the receipt check can pass. Claude’s current classification stays Hold, so we are not claiming it actually released an invalid invoice; its follow-up criterion is what needs correction.
The memo also inserts a September 2025 reference period absent from the input. That is an unsupported reporting date, not an invented payment date. It calls the held total undetermined and East’s $250 an estimate. The eventual valid payable may need resolution, but the stated held subtotal is already $572.
The same English question produced a Korean answer in this session. We retained that original rather than retrying to get a preferred result. For an English handoff it requires translation as well as the substantive corrections. This observation does not establish how Claude would respond in other sessions.
Claude original: “입고팀에 P3 실입고 수량 확인 후 10개 이하인지 재검증”
WekeyLab AI’s revised payment-review handoff
This is our reusable rewrite of the supplied fictional records, not a fourth model response or proof of payment.
Payment-review handoff — five unique invoices. Eligible for review: North/N100/P1 $640 and West/N100/P2 $300, total $940. The repeated North row is excluded; West is a distinct supplier despite the same invoice number. Holds, at stated invoice amounts: East/E200/P3 $250; South/S300/P4 $132; Lake/L400/P5 $190, total $572. Unique control total: $1,512 = $940 + $572. For East, confirm at least 10 received units remain available for billing; unknown is not zero or confirmation. For South, resolve the $11 invoice versus $10 PO price and recheck the supporting documents. For Lake, request clarification/correction of the stated $190 versus calculated $200; do not silently replace it. Keep each exception held until its checks pass. This handoff records reconciliation only. Final payment approval and a payment date have not been established.
A prompt worth reusing with your own rules
Try: “Reconcile these invoices against the supplied orders and receipts using my explicit matching rules. Identify duplicates by the key I specify. Keep unknowns and exceptions separate; do not repair a value and treat it as verified. Show the amount eligible for the next review stage, the stated held amount, and the duplicate-adjusted control total. Draft a handoff with the identifier, reason and next check for each exception. Do not invent approval, dates or owners.” Then add your rules and sanitized tables.
Oracle’s documentation describes three-way matching using order, receipt and invoice information, with configured tolerances. It supports the workflow background, not this exercise’s particular zero-tolerance rule. Real organizations may have different matching and authorization settings. Here the test is whether the AI follows the rules it was actually given.
For adjacent work, our vendor-quote comparison examines purchasing choices and our inventory-reorder comparison checks quantities before a proposed order. Search volume for this topic was not established; the case was chosen for its practical, independently checkable task.
Sources and actual records
Actual website collection September 23, 2026, 09:02–09:06 KST. Identical English prompt once per service, no length limit. ChatGPT Free, Think off, specific model not displayed; Gemini Flash, plan unverified; Claude Free, Sonnet 5 Medium. ChatGPT/Gemini answered in English; Claude answered in Korean. Exact copied originals and prompt fingerprints verified. Independent Decimal arithmetic plus 24 criterion reviews; no ERP/payment execution. One synthetic case, not an overall model benchmark. Korean and Chinese editions localize this same run and retain USD for the same test. Full input and originals follow.
Oracle: Match Approval Level Options
구매 견적 비교 / Vendor quote comparison
재고 보충 비교 / Inventory reorder comparison
ChatGPT · 2026-09-23 09:02–09:06 KST
I'm preparing a payment-review handoff for a fictional US office-supply team. Can you reconcile these invoice rows against our purchase orders and receipts, identify what can move to the payment-review queue and what needs checking, and write the handoff for my colleague? Do not actually approve or send payments. Our rules for this exercise: all amounts are USD, with no tax, freight or currency conversion. Each PO below has one line. To pass, an invoice's unit price must equal its PO price, its stated total must equal quantity times unit price, and its quantity must not exceed either the ordered quantity or the received quantity available for billing. A lower quantity is allowed: we accept partial invoices. There is no tolerance for differences. Unknown receipt quantity is not zero and cannot pass until checked. A wrong stated total is held; do not silently replace it with your calculation and pass it. Duplicate key is supplier plus invoice number, not invoice number alone. Identical repeated rows with the same key represent one invoice; count it once. All receipts and POs below are otherwise unbilled, and there are no other invoices. Keep holds separate from passed amounts; do not invent a payment date or treat a matching check as final approval. PO | Supplier | Ordered units | PO unit price | Received units available for billing P1 | North | 100 | 8.00 | 80 P2 | West | 20 | 15.00 | 20 P3 | East | 10 | 25.00 | unknown P4 | South | 12 | 10.00 | 12 P5 | Lake | 5 | 40.00 | 5 Row | Supplier | Invoice no. | PO | Invoiced units | Invoice unit price | Stated total R1 | North | N100 | P1 | 80 | 8.00 | 640.00 R2 | North | N100 | P1 | 80 | 8.00 | 640.00 R3 | West | N100 | P2 | 20 | 15.00 | 300.00 R4 | East | E200 | P3 | 10 | 25.00 | 250.00 R5 | South | S300 | P4 | 12 | 11.00 | 132.00 R6 | Lake | L400 | P5 | 5 | 40.00 | 190.00 Please show the reconciliation and the amount that can move forward under these rules, along with the follow-up needed for the other rows. Here’s the reconciliation, applying the rules exactly and counting the duplicate North rows only once. | Invoice key | PO | Qty | Unit price | Stated total | Result | Reason | | ------------ | -- | --: | ---------: | -----------: | -------- | ---------------------------------------------------------------------------------------- | | North + N100 | P1 | 80 | $8.00 | $640.00 | **Pass** | Price matches; $8 × 80 = $640; 80 ≤ 100 ordered and 80 received | | West + N100 | P2 | 20 | $15.00 | $300.00 | **Pass** | Price matches; $15 × 20 = $300; 20 ≤ 20 ordered and received | | East + E200 | P3 | 10 | $25.00 | $250.00 | **Hold** | Receipt quantity is unknown, so billing quantity cannot be confirmed | | South + S300 | P4 | 12 | $11.00 | $132.00 | **Hold** | Invoice unit price does not match PO price of $10.00 | | Lake + L400 | P5 | 5 | $40.00 | $190.00 | **Hold** | Stated total is incorrect: 5 × $40 = $200; do not replace the stated total automatically | ### Amount that can move forward * **North / N100:** $640.00 * **West / N100:** $300.00 * **Total eligible for payment-review queue: $940.00** * **Held amount as stated on invoices:** $250.00 + $132.00 + $190.00 = **$572.00** The two North rows (R1/R2) have the same supplier + invoice-number key and are identical, so they represent **one $640 invoice**, not two. ### Follow-up * **East / E200:** Verify the receipt quantity available for billing. If it is at least 10 units, the invoice can then pass the stated checks. * **South / S300:** Obtain a corrected invoice or otherwise resolve the $11.00 unit-price mismatch against the $10.00 PO price. * **Lake / L400:** Have the invoice corrected/confirmed because the stated $190.00 total does not equal 5 × $40.00. The matching calculation would be $200.00, but it must **not** be substituted automatically. ### Handoff to your colleague Payment-review handoff: **Move forward to payment review — $940.00 total** * North / invoice N100 / PO P1 — $640.00 * West / invoice N100 / PO P2 — $300.00 * North N100 appeared twice (R1/R2), but the duplicate key is supplier + invoice number, so count it once. **Hold / follow up** * East / E200 / P3 — receipt quantity is unknown; verify received quantity available for billing before passing. * South / S300 / P4 — invoice unit price is $11.00 vs PO price of $10.00; resolve the mismatch. * Lake / L400 / P5 — stated total is $190.00, but 5 × $40.00 = $200.00; obtain clarification/correction rather than substituting the calculated amount. The $940.00 figure is the amount that passes these reconciliation rules and can move to the payment-review queue. This is not final payment approval, and no payment has been approved or sent. If you want, I can also turn this into a compact spreadsheet-style exception report with columns for **pass/hold, reason, owner, and next action**.
Gemini · 2026-09-23 09:02–09:06 KST
I'm preparing a payment-review handoff for a fictional US office-supply team. Can you reconcile these invoice rows against our purchase orders and receipts, identify what can move to the payment-review queue and what needs checking, and write the handoff for my colleague? Do not actually approve or send payments.
Our rules for this exercise: all amounts are USD, with no tax, freight or currency conversion. Each PO below has one line. To pass, an invoice's unit price must equal its PO price, its stated total must equal quantity times unit price, and its quantity must not exceed either the ordered quantity or the received quantity available for billing. A lower quantity is allowed: we accept partial invoices. There is no tolerance for differences. Unknown receipt quantity is not zero and cannot pass until checked. A wrong stated total is held; do not silently replace it with your calculation and pass it.
Duplicate key is supplier plus invoice number, not invoice number alone. Identical repeated rows with the same key represent one invoice; count it once. All receipts and POs below are otherwise unbilled, and there are no other invoices. Keep holds separate from passed amounts; do not invent a payment date or treat a matching check as final approval.
PO | Supplier | Ordered units | PO unit price | Received units available for billing
P1 | North | 100 | 8.00 | 80
P2 | West | 20 | 15.00 | 20
P3 | East | 10 | 25.00 | unknown
P4 | South | 12 | 10.00 | 12
P5 | Lake | 5 | 40.00 | 5
Row | Supplier | Invoice no. | PO | Invoiced units | Invoice unit price | Stated total
R1 | North | N100 | P1 | 80 | 8.00 | 640.00
R2 | North | N100 | P1 | 80 | 8.00 | 640.00
R3 | West | N100 | P2 | 20 | 15.00 | 300.00
R4 | East | E200 | P3 | 10 | 25.00 | 250.00
R5 | South | S300 | P4 | 12 | 11.00 | 132.00
R6 | Lake | L400 | P5 | 5 | 40.00 | 190.00
Please show the reconciliation and the amount that can move forward under these rules, along with the follow-up needed for the other rows.
### Independent Row-by-Row Reconciliation
* **R1 & R2 (North | Inv: N100 | PO: P1):**
* *Analysis:* Identical repeated rows with the same key (North + N100). Evaluated once as a single invoice.
* *Unit Price:* Invoice $8.00 matches PO $8.00.
* *Stated Total:* $80 \times \$8.00 = \$640.00$. Stated total $640.00 is correct.
* *Quantity Check:* Invoiced 80 units $\le$ Ordered 100 units AND Invoiced 80 units $\le$ Received 80 units.
* *Status:* **PASS** ($640.00).
* **R3 (West | Inv: N100 | PO: P2):**
* *Analysis:* Supplier is West, making key (West + N100) distinct from North's N100.
* *Unit Price:* Invoice $15.00 matches PO $15.00.
* *Stated Total:* $20 \times \$15.00 = \$300.00$. Stated total $300.00 is correct.
* *Quantity Check:* Invoiced 20 units $\le$ Ordered 20 units AND Invoiced 20 units $\le$ Received 20 units.
* *Status:* **PASS** ($300.00).
* **R4 (East | Inv: E200 | PO: P3):**
* *Analysis:* Received quantity for P3 is **unknown**.
* *Rule Check:* Unknown receipt quantity cannot pass until verified.
* *Status:* **HOLD** ($250.00).
* **R5 (South | Inv: S300 | PO: P4):**
* *Analysis:* Invoice unit price is $11.00, but PO unit price is $10.00.
* *Rule Check:* Unit price does not match PO price.
* *Status:* **HOLD** ($132.00).
* **R6 (Lake | Inv: L400 | PO: P5):**
* *Analysis:* $5 \text{ units} \times \$40.00 = \$200.00$, but stated total on invoice is $190.00.
* *Rule Check:* Stated total is incorrect. Rules forbid silently correcting math to pass it.
* *Status:* **HOLD** ($190.00).
---
### Reconciliation Summary Table
| Invoice Key | PO | Invoiced Amount | Status | Action Required / Reason |
| --- | --- | --- | --- | --- |
| **North - N100** | P1 | $640.00 | **Pass** | Move to payment-review queue (R1/R2 deduplicated). |
| **West - N100** | P2 | $300.00 | **Pass** | Move to payment-review queue. |
| **East - E200** | P3 | $250.00 | **Hold** | Confirm receiving quantity for PO P3. |
| **South - S300** | P4 | $132.00 | **Hold** | Price variance: Invoiced at $11.00 vs PO price of $10.00. |
| **Lake - L400** | P5 | $190.00 | **Hold** | Stated total error: $5 \times \$40.00$ should be $200.00. |
* **Total Ready for Payment-Review Queue:** **$940.00**
* **Total Held for Checking:** **$572.00**
---
### Handoff Memo
**To:** Payment Review Team
**From:** Accounts Payable Reconciliation
**Subject:** Invoice Reconciliation Handoff & Exception Review
Hi Team,
I have completed the preliminary 3-way match reconciliation for the latest batch of office supply invoices against our open purchase orders and receiving logs. Please find the queue routing details below:
#### 1. Approved to Move to Payment-Review Queue ($940.00 Total)
The following invoices have successfully matched unit prices, line arithmetic, and receiving thresholds:
* **North (Inv #N100 / PO #P1):** **$640.00** (80 units @ $8.00/unit). *Note: R1 and R2 were duplicate submissions of the same invoice key and have been deduplicated.*
* **West (Inv #N100 / PO #P2):** **$300.00** (20 units @ $15.00/unit).
#### 2. Exceptions / Items On Hold ($572.00 Total)
The following items require further investigation before moving forward:
* **East (Inv #E200 / PO #P3) – $250.00:** On hold due to missing receipt confirmation. **Follow-up:** Check receiving log or contact warehouse receiving to confirm physical arrival of the 10 units.
* **South (Inv #S300 / PO #P4) – $132.00:** On hold due to a price discrepancy. Invoiced unit price is $11.00 versus agreed PO price of $10.00. **Follow-up:** Reach out to procurement/vendor to request a credit memo or revised invoice at the $10.00 rate.
* **Lake (Inv #L400 / PO #P5) – $190.00:** On hold due to a calculation error. Stated total is $190.00, but $5 \text{ units} \times \$40.00\text{/unit} = \$200.00$. **Follow-up:** Request a corrected invoice from Lake for the proper total amount.
Please proceed with processing the $940.00 approved queue. I will follow up on the missing receipt and price/math discrepancies.
Best regards,
AP SpecialistClaude · 2026-09-23 09:02–09:06 KST
I'm preparing a payment-review handoff for a fictional US office-supply team. Can you reconcile these invoice rows against our purchase orders and receipts, identify what can move to the payment-review queue and what needs checking, and write the handoff for my colleague? Do not actually approve or send payments. Our rules for this exercise: all amounts are USD, with no tax, freight or currency conversion. Each PO below has one line. To pass, an invoice's unit price must equal its PO price, its stated total must equal quantity times unit price, and its quantity must not exceed either the ordered quantity or the received quantity available for billing. A lower quantity is allowed: we accept partial invoices. There is no tolerance for differences. Unknown receipt quantity is not zero and cannot pass until checked. A wrong stated total is held; do not silently replace it with your calculation and pass it. Duplicate key is supplier plus invoice number, not invoice number alone. Identical repeated rows with the same key represent one invoice; count it once. All receipts and POs below are otherwise unbilled, and there are no other invoices. Keep holds separate from passed amounts; do not invent a payment date or treat a matching check as final approval. PO | Supplier | Ordered units | PO unit price | Received units available for billing P1 | North | 100 | 8.00 | 80 P2 | West | 20 | 15.00 | 20 P3 | East | 10 | 25.00 | unknown P4 | South | 12 | 10.00 | 12 P5 | Lake | 5 | 40.00 | 5 Row | Supplier | Invoice no. | PO | Invoiced units | Invoice unit price | Stated total R1 | North | N100 | P1 | 80 | 8.00 | 640.00 R2 | North | N100 | P1 | 80 | 8.00 | 640.00 R3 | West | N100 | P2 | 20 | 15.00 | 300.00 R4 | East | E200 | P3 | 10 | 25.00 | 250.00 R5 | South | S300 | P4 | 12 | 11.00 | 132.00 R6 | Lake | L400 | P5 | 5 | 40.00 | 190.00 Please show the reconciliation and the amount that can move forward under these rules, along with the follow-up needed for the other rows. ## 대사 결과 (Reconciliation) | Row | Supplier/Invoice | PO | 단가 일치 | Total 검산 | 수량 조건 | 판정 | |---|---|---|---|---|---|---| | R1+R2 (중복키, 1건 처리) | North/N100 | P1 | 8.00=8.00 ✓ | 80×8.00=640.00 ✓ | 80≤100(주문), 80≤80(입고) ✓ | **Pass** | | R3 | West/N100 | P2 | 15.00=15.00 ✓ | 20×15.00=300.00 ✓ | 20≤20(주문), 20≤20(입고) ✓ | **Pass** | | R4 | East/E200 | P3 | 25.00=25.00 ✓ | 10×25.00=250.00 ✓ | 입고수량 **unknown** → 확인 불가 | **Hold** | | R5 | South/S300 | P4 | 11.00≠10.00 ✗ | (참고: 12×11.00=132.00, 그러나 단가 자체 불일치) | — | **Hold** | | R6 | Lake/L400 | P5 | 40.00=40.00 ✓ | 5×40.00=**200.00**, 명세 총액 190.00 ✗ | 5≤5(주문), 5≤5(입고) | **Hold** | - North N100은 R1/R2가 동일 키(공급사+송장번호)로 완전히 동일한 행이므로 1건으로만 집계. ## Payment-Review Queue로 이관 가능 (Pass) | Supplier | Invoice | PO | 금액 | |---|---|---|---| | North | N100 | P1 | $640.00 | | West | N100 | P2 | $300.00 | | **합계** | | | **$940.00** | ※ 대사 통과는 최종 승인이 아니며, payment-review 대기 상태로만 이관. ## 보류 (Hold) 및 후속 조치 필요 | Supplier | Invoice | 보류 사유 | 필요 조치 | |---|---|---|---| | East / E200 | P3 | 입고수량(unknown) 미확인 — unknown은 0이 아니며 확인 전 통과 불가 | 입고팀에 P3 실입고 수량 확인 후 10개 이하인지 재검증 | | South / S300 | P4 | 송장 단가 $11.00 ≠ PO 단가 $10.00 | 공급사에 단가 상이 사유 문의 또는 PO/계약 조건 재확인. 임의로 $10 기준 재계산하여 통과 처리 금지 | | Lake / L400 | P5 | 명세 총액 $190.00 ≠ 계산값 $200.00 (5×40.00) | 공급사에 정정 송장 요청. 계산값으로 임의 대체 후 통과 처리 금지 | --- ## 인계 메모 **제목**: 사무용품 공급사 송장 대사 결과 — Payment-Review 이관 및 보류 건 (2025년 9월 기준, 예시) **상태**: 대사 완료, 승인/지급 미실행 **근거(Rationale)**: PO 5건, 인보이스 6행(중복 제거 시 5건) 대사. 단가 일치·총액 검산·수량(주문/입고 한도) 3개 기준 모두 충족한 건만 Pass 처리. 하나라도 미충족 시 자동 보정 없이 Hold. **금액(Cost)**: - 이관 가능(Pass): $940.00 (North $640.00 + West $300.00) - 보류(Hold): 금액 미확정 — East $250.00(추정, 입고 확인 전), South $132.00(단가 불일치로 보류), Lake $190.00 vs $200.00(총액 불일치) **예상 효과(Expected effect)**: $940.00을 payment-review 큐로 이관 시 정상 대사 완료 건 우선 처리 가능. 나머지 3건은 원인 확인 전까지 지급 보류로 리스크 차단. **대응(Response)**: 1. East(P3): 입고 담당자에 실입고 수량 확인 요청 2. South(P4): 공급사에 단가 상이 사유 확인 3. Lake(P5): 공급사에 총액 오류 정정 인보이스 요청 4. 위 3건은 확인 완료 전까지 payment-review 큐에 올리지 않음 궁금하신 부분이나 기준 조정이 필요하면 말씀해 주세요.