Tasks · desk · Extraction
CRM contacts from the scanned expo business cards
business-cards-scanned · 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.
Jess scanned the business cards from the expo. Can you turn them into contacts.csv for the CRM? Her note says how marketing wants it.
Workspace
- expo_cards/Scan_2026-09-17_001.pdf
- expo_cards/Scan_2026-09-17_002.pdf
- expo_cards/Scan_2026-09-17_003.pdf
- expo_cards/Scan_2026-09-17_004.pdf
- expo_cards/Scan_2026-09-17_005.pdf
- expo_cards/Scan_2026-09-17_006.pdf
- expo_cards/Scan_2026-09-17_007.pdf
- expo_cards/Scan_2026-09-17_008.pdf
- expo_cards/Scan_2026-09-17_009.pdf
- expo_cards/Scan_2026-09-17_010.pdf
- note_from_jess.txt
Expected deliverables
- contacts.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 |
|---|---|---|---|
| requested columns | csv_columns | yes | 0 |
| one row per contact | csv_set_equal | yes | 0 |
| row count | csv_row_count | yes | 0 |
| names | csv_values_match | yes | 0 |
| titles and companies | csv_values_match | yes | 0 |
| office phones | csv_values_match | yes | 0 |
| mobile phones | csv_values_match | yes | 1 |
| countries | 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 | 2 | 2 | 2.9 | 0.0295 | |
| Codex / GPT-5.6 sol | 3 | 3 | 1.5 | 0.2993 |
Per-attempt check verdicts, raw and frozen verdicts, usage, receipt and artifact hashes for this task are in results/latest/attempts.jsonl under "task": "business-cards-scanned".