Tasks · desk · Spreadsheet
Fall to spring enrollment, adds and drops by course
class-roster-changes · 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.
Renata needs fall-to-spring enrollment changes for every course for the board packet. Save it as roster_changes.csv; her email explains what she wants counted.
Workspace
- email_from_coordinator.txt
- fall_2025_rosters.xlsx
- spring_2026_enrollment_export.csv
- spring_2026_waitlist.csv
Expected deliverables
- roster_changes.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 course | csv_set_equal | yes | 0 |
| fall enrolled per course | csv_values_match | yes | 0 |
| spring enrolled per course | csv_values_match | yes | 0 |
| added per course | csv_values_match | yes | 0 |
| dropped per course | 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 | 2.0 | 0.0313 | |
| Codex / GPT-5.6 sol | 3 | 3 | 1.9 | 0.3866 |
Per-attempt check verdicts, raw and frozen verdicts, usage, receipt and artifact hashes for this task are in results/latest/attempts.jsonl under "task": "class-roster-changes".