Long read, November 23, 2025
what legal AI gets wrong about legal work
The problem
Every review team we work with has a version of this problem. What legal AI gets wrong about legal work rarely announces itself.
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.
What we do about it
We treat anything the system cannot ground in source text as unverified and show it as such. A visible gap is cheaper than a confident error.
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.