Writing
The archive, page 9.
587 published, 143 scheduled
- Practice noteJan 30 2026
Practice note: how to scope a document review before agreeing search terms
This one comes up in almost every matter review, and the answer is less settled than the confidence around it suggests.
7 min read
- BenchmarkJan 29 2026
Benchmark: redline generation against a firm playbook
Every review team we work with has a version of this problem. Redline generation against a firm playbook rarely announces itself.
4 min read
- Build logJan 28 2026
Build log: measuring redline quality against a human baseline
We keep coming back to measuring redline quality against a human baseline, because the cost of a miss here compounds across a portfolio.
6 min read
- Jurisdiction updateJan 27 2026
Ireland: disclosure of AI-assisted work product
This one comes up in almost every matter review, and the answer is less settled than the confidence around it suggests.
4 min read
- Clause teardownJan 26 2026
Clause teardown: confidentiality carve-outs
The short version: confidentiality carve-outs is easier to get wrong than most teams assume, and the failure is usually silent.
6 min read
- Long readJan 25 2026
what legal AI gets wrong about legal work
Every review team we work with has a version of this problem. What legal AI gets wrong about legal work rarely announces itself.
7 min read
- Field guideJan 24 2026
Field guide: tracing chain of title on assigned IP
We keep coming back to tracing chain of title on assigned IP, because the cost of a miss here compounds across a portfolio.
9 min read
- Practice noteJan 23 2026
Practice note: making a status report a client reads to the end
This one comes up in almost every matter review, and the answer is less settled than the confidence around it suggests.
3 min read
- BenchmarkJan 22 2026
Benchmark: cross-reference validation after renumbering
The short version: cross-reference validation after renumbering is easier to get wrong than most teams assume, and the failure is usually silent.
5 min read
- Build logJan 21 2026
Build log: reconciling three rounds of tracked changes deterministically
Every review team we work with has a version of this problem. Reconciling three rounds of tracked changes deterministically rarely announces itself.
6 min read
- Jurisdiction updateJan 20 2026
New York: enforceability of restrictive covenants
We keep coming back to New York: enforceability of restrictive covenants, because the cost of a miss here compounds across a portfolio.
8 min read
- Clause teardownJan 19 2026
Clause teardown: governing law and forum
We keep coming back to governing law and forum, because the cost of a miss here compounds across a portfolio.
9 min read
- Long readJan 18 2026
what legal AI gets wrong about legal work
Every review team we work with has a version of this problem. What legal AI gets wrong about legal work rarely announces itself.
7 min read
- Field guideJan 17 2026
Field guide: mapping indemnity flows in a three-party structure
The short version: mapping indemnity flows in a three-party structure is easier to get wrong than most teams assume, and the failure is usually silent.
7 min read
- Practice noteJan 16 2026
Practice note: how to scope a document review before agreeing search terms
This one comes up in almost every matter review, and the answer is less settled than the confidence around it suggests.
5 min read
- BenchmarkJan 15 2026
Benchmark: chronology construction from unstructured document sets
We keep coming back to chronology construction from unstructured document sets, because the cost of a miss here compounds across a portfolio.
3 min read
- Build logJan 14 2026
Build log: streaming long answers without losing the citation trail
Every review team we work with has a version of this problem. Streaming long answers without losing the citation trail rarely announces itself.
8 min read
- Jurisdiction updateJan 13 2026
the Netherlands: privilege in internal investigations
The short version: the Netherlands: privilege in internal investigations is easier to get wrong than most teams assume, and the failure is usually silent.
8 min read
- Clause teardownJan 12 2026
Clause teardown: step-in rights
This one comes up in almost every matter review, and the answer is less settled than the confidence around it suggests.
6 min read
- Long readJan 11 2026
trust, verification, and the reviewer's burden
We keep coming back to trust, verification, and the reviewer's burden, because the cost of a miss here compounds across a portfolio.
4 min read
- Field guideJan 10 2026
Field guide: testing a non-compete for enforceability
Every review team we work with has a version of this problem. Testing a non-compete for enforceability rarely announces itself.
9 min read
- Practice noteJan 9 2026
Practice note: what to keep out of a first draft
This one comes up in almost every matter review, and the answer is less settled than the confidence around it suggests.
6 min read
- BenchmarkJan 8 2026
Benchmark: clause classification across 40,000 executed agreements
The short version: clause classification across 40,000 executed agreements is easier to get wrong than most teams assume, and the failure is usually silent.
8 min read
- Build logJan 7 2026
Build log: chunking contracts without breaking clause boundaries
Every review team we work with has a version of this problem. Chunking contracts without breaking clause boundaries rarely announces itself.
3 min read