Contract review
Clause extraction and commercial risk.
Domain evidence · Legal
Contract and diligence tasks with published traces.
Clause risk, obligations, and diligence tasks.
Published evidence for Legal covers 285 scored tasks across 2 task categories and 1 benchmark, with 1 flagship run open in full — prompts, files, traces, and rubric grades.
2Task categories
285Scored tasks
1Benchmarks
0/1Flagship passes
Selected published runs
Tasks, traces, and rubric results.
Includes runs that miss one or more rubric criteria.
Workflows
Stay inside the work that brought you here.
Category hubs
Related published task collections
Measured failure modes
What current agents miss in this domain.
- Overlooked obligation or risk allocation