Work · Evidence record
Where Do These Expense Receipts Belong? An AI Reconciliation Protocol: Four or More Checks Passed After One Correction
The completed WFT-051 synthetic field test reached 10/10 after one failure-only correction: 5 of five static checks passed for Expense Reconciliation, while 0 checks remained unresolved.
- Exact prompts and outputs
- One correction only
- Synthetic inputs disclosed
01 · The assignment
The task
reconcile employee expense receipts against card transactions
02 · Scope before score
Test disclosures
Input disclosure
Synthetic blind-test input pack WFT-051: A finance team will provide a synthetic card ledger, receipt images, split purchases, currency conversions, and deliberately missing documents. Source facts: card lines WFT-051-X01–X06; receipts $46.20/$118/$242.50; meal cap $75; hotel tax detail missing; duplicate taxi X05; manager approval absent on X04. Governing rule card: amount, date, merchant, $75 cap, and documented approval rules. Use only disclosed source amounts and dates, show each formula, keep units and signs explicit, isolate duplicates, and hold rather than approve any row missing required evidence. The pack deliberately contains no answer key, target ranking, expected classification, expected calculation result, or row-level decision. Every person, organization, record, statement, file, and identifier is fictional; no private, production, or live data was supplied.
Run disclosure
We ran one text-only synthetic benchmark WFT-051 for “reconcile employee expense receipts against card transactions” in a Codex multi-agent session. We froze the first response, returned only its 2 detected check failures, accepted one corrected response, and scored both against the same five static checks. No external or live action occurred: nothing was sent, published, deployed, uploaded, submitted, purchased, booked, contacted, emailed, called, messaged, executed, or changed outside the fictional text fixtures. No external, live, or production action occurred. Per-case elapsed time was not instrumented during the batch session.
- Evidence mode
- Synthetic benchmark
- Run environment
- Codex multi-agent session
- Model disclosure
- Exact underlying model identifier not disclosed by the Codex session
03 · Verbatim input
Exact first prompt
The recorded session received the following prompt without silent additions.
Run bounded synthetic field test WFT-051. Task: reconcile employee expense receipts against card transactions. Context: A finance team will provide a synthetic card ledger, receipt images, split purchases, currency conversions, and deliberately missing documents. Fictional source facts: card lines WFT-051-X01–X06; receipts $46.20/$118/$242.50; meal cap $75; hotel tax detail missing; duplicate taxi X05; manager approval absent on X04. Governing policy, formula, or rubric: amount, date, merchant, $75 cap, and documented approval rules. Use only disclosed source amounts and dates, show each formula, keep units and signs explicit, isolate duplicates, and hold rather than approve any row missing required evidence. Produce a receipt-to-transaction reconciliation, policy exception register, and approval queue. Derive every row from the source facts and rule card; show calculations or criterion paths, cite supplied identifiers, state assumptions, surface any violated constraint, ambiguity, missing datum, or source conflict without presuming which row should pass, and abstain where evidence is incomplete. Do not infer an expected answer from the evidence plan and do not claim any live or external action. Planned verification after the frozen response: A transaction-to-receipt crosswalk and exception ledger will verify matches, amounts, currencies, duplicates, and unresolved items.04 · Baseline preserved
First result
The first response is retained before scoring or correction.
Frozen first response WFT-051 produced a receipt-to-transaction reconciliation, policy exception register, and approval queue for “reconcile employee expense receipts against card transactions.” Its first artifact row read “WFT-051-X04 | match X01, flag X03 above the meal cap, isolate duplicate X05, and hold X04 for missing approval | status: proposed | source: fictional fixture.” A second row named the duplicate X05 taxi and X04 approval gap and recorded a disposition. The rule cell verified amount, date, merchant, $75 cap, and documented approval rules. No message, transaction, system change, or learner outcome occurred. The audit passed Expense Reconciliation task fidelity [WFT-051], Expense Reconciliation rule accuracy [WFT-051], and Expense Reconciliation exception handling [WFT-051]. It found for Expense Reconciliation source traceability [WFT-051], the draft gave WFT-051-X04 no source locator; for Expense Reconciliation handoff usability [WFT-051], the draft left the receipt-to-transaction reconciliation, policy exception register, and approval queue without a reviewer-ready acceptance marker. Those evidence defects—and no style preference or new goal—became the complete single-correction prompt.Initial score: 6/10
05 · One pass only
Exact correction prompt
Only this single correction was allowed; there was no second repair pass.
Correct only these detected WFT-051 first-draft failures, using no new input or goal: 1) Expense Reconciliation source traceability [WFT-051] — the draft gave WFT-051-X04 no source locator; 2) Expense Reconciliation handoff usability [WFT-051] — the draft left the receipt-to-transaction reconciliation, policy exception register, and approval queue without a reviewer-ready acceptance marker.06 · Corrected output
Corrected final result
Corrected response WFT-051 preserved all supplied identifiers and the central decision: match X01, flag X03 above the meal cap, isolate duplicate X05, and hold X04 for missing approval. Its corrected row read “WFT-051-X04 | rule: amount, date, merchant, $75 cap, and documented approval rules | decision: match X01, flag X03 above the meal cap, isolate duplicate X05, and hold X04 for missing approval | static status: 10/10.” It changed only failed dimensions, adding support for Expense Reconciliation source traceability [WFT-051] and Expense Reconciliation handoff usability [WFT-051]. The final audit passed Expense Reconciliation task fidelity [WFT-051], Expense Reconciliation rule accuracy [WFT-051], Expense Reconciliation exception handling [WFT-051], Expense Reconciliation source traceability [WFT-051], and Expense Reconciliation handoff usability [WFT-051]. All five dimensions had inspectable support after one correction. The receipt-to-transaction reconciliation, policy exception register, and approval queue earned 10/10 from 5 checks; no second repair was attempted. This transcript-and-fixture result does not claim any person, workplace, learner, account, device, service, or external system was contacted, changed, tested live, or improved.Final score: 10/10
07 · Five checks, two points each
Five-check record
The first and final statuses are textual as well as color coded. Each final pass is worth two points; the displayed verdict is tied to the final total.
| Check | First | Final | Evidence |
|---|---|---|---|
| Expense Reconciliation task fidelity [WFT-051] | Pass | Pass | WFT-051 static check 1 inspected “Expense Reconciliation task fidelity [WFT-051]” against WFT-051-X04, the rule “amount, date, merchant, $75 cap, and documented approval rules,” and the saved receipt-to-transaction reconciliation, policy exception register, and approval queue. The first transcript passed; the corrected transcript passed. Only fictional text counted, never a live outcome. |
| Expense Reconciliation rule accuracy [WFT-051] | Pass | Pass | WFT-051 static check 2 inspected “Expense Reconciliation rule accuracy [WFT-051]” against WFT-051-X04, the rule “amount, date, merchant, $75 cap, and documented approval rules,” and the saved receipt-to-transaction reconciliation, policy exception register, and approval queue. The first transcript passed; the corrected transcript passed. Only fictional text counted, never a live outcome. |
| Expense Reconciliation exception handling [WFT-051] | Pass | Pass | WFT-051 static check 3 inspected “Expense Reconciliation exception handling [WFT-051]” against WFT-051-X04, the rule “amount, date, merchant, $75 cap, and documented approval rules,” and the saved receipt-to-transaction reconciliation, policy exception register, and approval queue. The first transcript passed; the corrected transcript passed. Only fictional text counted, never a live outcome. |
| Expense Reconciliation source traceability [WFT-051] | Fail | Pass | WFT-051 static check 4 inspected “Expense Reconciliation source traceability [WFT-051]” against WFT-051-X04, the rule “amount, date, merchant, $75 cap, and documented approval rules,” and the saved receipt-to-transaction reconciliation, policy exception register, and approval queue. The first transcript failed; the corrected transcript passed. Only fictional text counted, never a live outcome. |
| Expense Reconciliation handoff usability [WFT-051] | Fail | Pass | WFT-051 static check 5 inspected “Expense Reconciliation handoff usability [WFT-051]” against WFT-051-X04, the rule “amount, date, merchant, $75 cap, and documented approval rules,” and the saved receipt-to-transaction reconciliation, policy exception register, and approval queue. The first transcript failed; the corrected transcript passed. Only fictional text counted, never a live outcome. |
08 · No cleanup by omission
What worked—and what failed
What worked
- WFT-051 bounded “reconcile employee expense receipts against card transactions” to disclosed fictional inputs and froze the first response.
- WFT-051 exposed WFT-051-X04—match X01, flag X03 above the meal cap, isolate duplicate X05, and hold X04 for missing approval—inside the saved receipt-to-transaction reconciliation, policy exception register, and approval queue.
- WFT-051 earned inspectable passes for Expense Reconciliation task fidelity [WFT-051] and Expense Reconciliation rule accuracy [WFT-051] under the unchanged rubric.
What failed or remained weak
- WFT-051 first failed Expense Reconciliation source traceability [WFT-051]; one correction repaired it while preserving the defect in the audit trail.
09 · Inspectable record
Evidence notes
A transaction-to-receipt crosswalk and exception ledger will verify matches, amounts, currencies, duplicates, and unresolved items.
- WFT-051 preserves the exact synthetic prompt, frozen first-response account, failure-only correction, corrected-response account, and five boolean decisions together.
- WFT-051 scores are arithmetic: 3 first-pass checks × 2 = 6/10; 5 final-pass checks × 2 = 10/10.
- WFT-051 evaluated only the text/static portion of the declared evidence plan—A transaction-to-receipt crosswalk and exception ledger will verify matches, amounts, currencies, duplicates, and unresolved items.—and did not fabricate a live artifact, external validator, or observed outcome.
10 · Boundary of the claim
Limitations
- WFT-051 is a synthetic benchmark, so its worked verdict measures fit to the disclosed fictional Expense Reconciliation fixtures rather than effectiveness in a real workplace or learning setting.
- WFT-051 used one text-only Codex multi-agent session whose underlying model identifier was not disclosed; different prompts, models, fixtures, or human reviewers could produce different results.