Tasks · desk · Reformatting
Clean the catalog mailing list for the mail house
address-standardize · 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.
Keystone is mailing our winter catalog. Please clean up the mailing list to their address standard and save it as addresses_clean.csv - Ruth's email, their standards sheet and the template are in the folder.
Workspace
- catalog_mailing_list.xlsx
- email_from_ruth.txt
- keystone_address_standards.txt
- keystone_import_template.csv
Expected deliverables
- addresses_clean.csv
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 |
|---|---|---|---|
| Keystone template columns, exact order | csv_columns | yes | 0 |
| one row per mailing address | csv_set_equal | yes | 0 |
| row count | csv_row_count | yes | 0 |
| delivery address line | csv_values_match | yes | 0 |
| city, state and ZIP | csv_values_match | 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 | 2.5 | 0.0448 | |
| Codex / GPT-5.6 sol | 3 | 3 | 2.3 | 0.2982 |
Per-attempt check verdicts, raw and frozen verdicts, usage, receipt and artifact hashes for this task are in results/latest/attempts.jsonl under "task": "address-standardize".