TasksDocument ExtractionBusiness track

Email thread to action items

biz-extract-05suite v1.0json

Quality15%judge panel
Correctness70%deterministic · field-match
Completeness15%deterministic · schema-validate

Exact prompt sent to every model

Below is a 7-message email thread between a church administrator, an IT provider and a vendor about replacing the sanctuary AV system. Extract: participants (array of {name, email, organization, role}), decisions (array of {decision, decided_by, date}), open_questions (array of strings), action_items (array of {owner, task, due_date or null, source_message_index}), budget {approved_amount, currency, approved_by}, and next_meeting {date, time, timezone} or null. Only include decisions that were actually agreed, not proposals. Return only the JSON.

A private fixture (biz-extract-05/thread.txt) is shown to the model but not published.

Responses

Latest published run: gemini-3.8-flash. For each model the repeat closest to its published median is shown; every repeat is in the repository.

No published attempts for this task yet

When the run is published, every model's raw response, per-dimension scores, judge rationales, human review notes and rendered artifacts appear here side by side.