Tasks · desk · Reformatting
Import the roofing pipeline into HubSpot deals
hubspot-deals-import · 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.
Our companies are in HubSpot now; next are the deals from pipeline_2026.xlsx. Marcus wrote up how our pipelines are set up, and the companies export and HubSpot's template are in the folder. Save the import as hubspot_deals.csv.
Workspace
- hubspot_companies_export.csv
- hubspot_deals_import_template.csv
- hubspot_setup_notes.md
- pipeline_2026.xlsx
Expected deliverables
- hubspot_deals.csv
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 |
|---|---|---|---|
| HubSpot template columns, exact order | csv_columns | yes | 0 |
| one deal per bid | csv_set_equal | yes | 0 |
| row count | csv_row_count | yes | 0 |
| pipeline and stage | csv_values_match | yes | 0 |
| amount | custom | yes | 0 |
| close date | csv_values_match | yes | 0 |
| company domain | 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 | 1.9 | 0.0330 | |
| Codex / GPT-5.6 sol | 3 | 3 | 2.5 | 0.2970 |
Per-attempt check verdicts, raw and frozen verdicts, usage, receipt and artifact hashes for this task are in results/latest/attempts.jsonl under "task": "hubspot-deals-import".