We Test
Can AI actually do legal work?
How do we find out? We build systems and workflows, put them to the test on legal tasks, and examine where they succeed, where they fail, and why.
We Build → We Test → We Document
What We Test
- Technical Question: Can AI systems actually perform the tasks we ask?
- Legal Question: Can AI actually perform meaningful legal work?
- Reliability Question: Where does AI stop being reliable?
- Human Judgment Question: Where does human/attorney judgment matter?
The Test Record
The Record
Tests in progress and planned.
In progress
More tests will appear here as they enter the record.