The trace view, one year on
We shipped the trace view expecting associates to check every step. They open it in one query in five, and almost always for the same reason. What we expected, what happened and what we changed.
The empathy layer: what we learned building Interview with trauma-informed clinicians
What should a voice agent do when the caller starts crying? We spent six months with three clinicians and 140 mock intakes finding out. The answers were mostly about pacing and consent.
Earn-out structures in European biotech deals: what Recall surfaces
Across 184 anonymised acquisition agreements with European biotech targets, what milestone types, efforts standards and dispute mechanisms look like, and what Review does with that.
The cost of a false positive in contract review
A dismissed flag costs a reviewer forty-one seconds. That is the small number. The larger one is what happens to the next three flags.
ZAAN-7B Counsel: a small model trained end-to-end for clause-level reasoning
Our in-house model: what it was trained on, what it was not, how it was evaluated against the models we previously routed to, and where it still falls short.
Modelling a tribunal from published awards: what we can and cannot infer about a chair
Simulation models venues, not named arbitrators. This note sets out what a corpus of published awards actually supports, where selection bias defeats it, and why we stopped short.
MAC clauses in tech acquisitions: patterns across our 2024 matter index
What 480 anonymised 2024 technology SPAs in our index say about material adverse change drafting: carve-out counts, cyber language, and the slow exit of the pandemic clause.
How we evaluate redline quality: accept rate is not enough
Accept rate rewards timid redlines. Here is the four-part measure we use instead, the sample behind it, and the places where it still misleads us.
The parity guarantee: how we check that a Mandarin and an English draft say the same thing
A bilingual contract that differs between its two language versions is a dispute waiting for a tribunal. Here is how we test for parity, what the test catches, and what it still misses.
How we measure first-pass review time without flattering ourselves
Time saved is the easiest number to inflate. Here is how we define first-pass review time, who we measure, what we exclude and where the measurement still misleads.