Tasks · desk · Bookkeeping
Payables aging by vendor for the line of credit review
ap-aging · timeout 1200 s · source
The ask
Sent verbatim as the prompt. The agent works in a copy of the workspace below and sees nothing else.
The bank wants our accounts payable aging as of August 31. Wes's note says how to do it and the bills, vendor list and credits are in the folder. Save the aging as ap_aging.xlsx and the write-up as memo.md.
Workspace
- bills_export_2026-08-31.csv
- note_from_wes.txt
- vendor_credits_open.csv
- vendor_list.xlsx
Expected deliverables
- ap_aging.xlsx
- memo.md
Checks
The task passes only when every required check passes. Reference answers, tolerances, and the planted traps are in the repository, not here.
| Check | Type | Required | Failed (frozen) / 6 |
|---|---|---|---|
| ap_aging.xlsx exists | file_exists | yes | 0 |
| live formulas | xlsx_has_formulas | yes | 0 |
| no error cells | xlsx_no_errors | yes | 1 |
| total payables | xlsx_value_present | yes | 0 |
| current bucket total | xlsx_value_present | yes | 1 |
| 1-30 bucket total | xlsx_value_present | yes | 2 |
| 31-60 bucket total | xlsx_value_present | yes | 2 |
| Northline Freight total | xlsx_value_present | yes | 1 |
| Summit Gas total | xlsx_value_present | yes | 1 |
| Hopkins Family Pears total | xlsx_value_present | yes | 1 |
| memo carries total and past due | text_numbers_present | yes | 0 |
| memo names the most overdue bill | text_sentence_matches | yes | 2 |
Recorded results, complete desk comparison
pass pass, frozen scorer only fail timed out
| System | Repetitions | Frozen / 3 | Raw / 3 | Median minutes | Mean cost (USD) |
|---|---|---|---|---|---|
| Proto / DeepSeek V4.1 Flash | 1 | 1 | 9.2 | 0.1229 | |
| Codex / GPT-5.6 sol | 1 | 1 | 5.5 | 0.6006 |
Per-attempt check verdicts, raw and frozen verdicts, usage, receipt and artifact hashes for this task are in results/latest/attempts.jsonl under "task": "ap-aging".