An AI agent works a Connect-style accounting workbook
One recorded run on a benchmark replica modeled on McGraw Hill Connect, sped up 15×. The replica is a test copy we built, not the real site.
What happens in the clip
The agent works a Connect-style accounting workbook of integrated business models: dense grids of numeric cells and dropdowns spread across requirement tabs, with a question map for moving between items. It checks its work as it goes, fixes cells until they check out, and submits.
Step by step
- Works through the integrated business models of a Connect-style accounting workbook on the replica.
- Fills dense grids of numeric cells and dropdowns.
- Moves across the requirement tabs, using the question map to get between items.
- Checks its work as it goes and fixes cells until they check out.
- Submits the workbook.
- Replica read back: 106 of 109 graded parts correct.
What this replica tests
Dense multi-cell grids, requirement tabs and a question map. The side panel in the video shows how many graded parts are complete and whether the assignment has been turned in.
About this recording
This recording is a separate run with a different result from the benchmark table: the scored run on 22 September 2026 got 102 of 109, submitted; this recording got 106 of 109, submitted.
A benchmark replica we built for testing, modeled on McGraw Hill Connect. It is not the real site, and the platform's maker is not affiliated with it and has not endorsed it. The agent is the Base plan's vision engine, run in a standalone test harness, not the full desktop app. The on-screen label “Luke’s Empire” is the benchmark’s internal name.
This clip is one of seven on the benchmark page, which has the full method and the scored results. It is also shown on the McGraw Hill and McGraw Hill Connect pages.
Other recorded runs
- Replica modeled on WebAssign: STEM homework workbook · 8 of 8 graded parts correct, submitted
- Replica modeled on Cengage MindTap: Mixed assessment · 9 of 9 graded parts correct, submitted
- Replica modeled on Cengage WebAssign: Calculus homework · 16 of 16 graded parts correct, submitted
- Replica modeled on Pearson MyLab Finance: Finance homework (first third) · 9 of 9 graded parts correct, submitted
- Replica modeled on Macmillan Achieve: Statistics assignment (first third) · 6 of 8 graded parts correct, not submitted
- Replica modeled on Pearson MyLab College Algebra: College algebra (first third) · 5 of 5 graded parts correct, submitted
Silent Student is the desktop app this engine runs in. See what it does on McGraw Hill Connect.
Updated 19 October 2026