Mahal Systems OfficeBench
Fits office assistants that move content between documents, spreadsheets, email and calendars. Borrow the three-tier design (one, two, three apps) and the mix of exact, fuzzy and execution-based checks on output files.
What it asks the agent to do
- read a document or PDF and write the answer into a file
- edit spreadsheet cells and convert to PDF
- create or delete calendar events
- read and send email
- switch between apps to finish one office task
What to borrow from it
case templategrading designsandbox design
Caveats
Apps are thin Python wrappers rather than real Office software; tasks are small and the best models already pass the one- and two-app tiers.
Details
| Workloads | documents, spreadsheets, email calendar, general assistant |
|---|---|
| Interaction | single turn |
| Environment | containers |
| End state checked | Yes |
| Tools | Word, Excel, PDF, Calendar, Email, OCR, Shell operations in Docker |
| Grading | exact match, programmatic check |
| Size | 300 |
| Data | synthetic |
| Personal data | none |
| License | Apache-2.0 |
| Harness | own repo |
| Status | active |