One-page weekly KPIs from five system exports
weekly-kpi-dashboard · timeout 1800 s · source
The ask
Sent verbatim as the prompt. The agent works in a copy of the workspace below and sees nothing else.
Kwame wants a one-page weekly KPI sheet for the staff meeting built from the five exports in this folder. Save it as kpi.xlsx with live formulas; his note lists what goes on it.
Workspace
- lab_jobs.csv
- newsletter_audience.csv
- note_from_kwame.txt
- pos_end_of_day_report.csv
- schedule_hours_export.csv
- webstore_orders.csv
Expected deliverables
- kpi.xlsx
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 |
|---|---|---|---|
| kpi.xlsx exists | file_exists | yes | 0 |
| live formulas | xlsx_has_formulas | yes | 0 |
| no error cells | xlsx_no_errors | yes | 0 |
| staff hours week of 17 Aug (Monday weeks) | xlsx_value_present | yes | 0 |
| sales per staff hour week of 17 Aug | xlsx_value_present | yes | 1 |
| online sales week of 24 Aug (paid only) | xlsx_value_present | yes | 1 |
| glasses jobs finished week of 7 Sep | xlsx_value_present | yes | 0 |
| total sales, six weeks | xlsx_value_present | yes | 3 |
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 | 5.1 | 0.0596 | |
| Codex / GPT-5.6 sol | 0 | 0 | 4.8 | 0.6047 |
Per-attempt check verdicts, raw and frozen verdicts, usage, receipt and artifact hashes for this task are in results/latest/attempts.jsonl under "task": "weekly-kpi-dashboard".