Benchmark, August 6, 2026
Benchmark: redline generation against a firm playbook
The problem
This one comes up in almost every matter review, and the answer is less settled than the confidence around it suggests.
The usual approach is to read for the obvious form of the issue and move on. That catches the clean cases. It misses the ones where the operative language sits somewhere other than where you expect, which in a negotiated document is most of the time.
How we measured it
Our approach is to index the document twice: once by structure, once by defined term. Findings then carry a pointer back to both, so a reviewer can confirm a conclusion without re-reading the agreement.
In the current build this runs as part of the standard pass, so it applies to every document in the set rather than only the ones someone thought to check.
Where it breaks
Scanned originals with poor image quality remain the weakest input. So do agreements that were assembled from three precedents and never reconciled, which is common in long-lived supplier relationships.
We will revisit this once we have a larger sample. The current numbers are directional rather than settled.
Working notes from the Lawrs team. General information about legal technology and practice, not legal advice.