Tasks · desk · Spreadsheet
Rep by month sales table from the invoice export
sales-pivot-by-rep · 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.
Kwame needs January to June sales for each rep by month, with totals, from the invoice export in this folder. Save it as sales_by_rep.xlsx and keep it live. His note has what counts.
Workspace
- invoice_lines_2026-01_to_2026-06.csv
- note_from_kwame.txt
- rep_sales_2025H2.xlsx
Expected deliverables
- sales_by_rep.xlsx
This task also has a task-specific grader (check.py).
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 |
|---|---|---|---|
| live formulas | xlsx_has_formulas | yes | 0 |
| no error cells | xlsx_no_errors | yes | 2 |
| Cruz H1 total (four spellings merged) | xlsx_value_present | yes | 2 |
| Walker H1 total (two spellings merged) | xlsx_value_present | yes | 2 |
| Walker January (credits netted, deposits out) | xlsx_value_present | yes | 2 |
| H1 total, all reps | xlsx_value_present | yes | 2 |
| Patel April reads 0 | custom | yes | 0 |
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 | 3 | 3 | 2.0 | 0.0253 | |
| Codex / GPT-5.6 sol | 1 | 1 | 5.2 | 0.5581 |
Per-attempt check verdicts, raw and frozen verdicts, usage, receipt and artifact hashes for this task are in results/latest/attempts.jsonl under "task": "sales-pivot-by-rep".