The method
Four principles, every one of them learned by breaking something.
- 01
The evaluation set before the pipeline
30 stratified files, 8 critical fields, 240 cells annotated by hand, sample drawn deterministically so it can be replayed. Without it, “is this better?” is judged by eye on a handful of familiar queries. I did it afterwards. I’d do it first.
- 02
How much of your information lives in tables?
It’s my first question on an unfamiliar corpus, and the answer doubles or halves the estimate. Flowing text settles quickly; 228,771 price-schedule rows needed an entirely separate processing chain, because in a grid the structure is the information.
- 03
Silence is a product goal
A system that always answers is a system that sometimes invents — the only truly serious failure mode on a contractual document. Making “that information is not in this file” a correct, deliberate answer is as much interface work as model work.
- 04
Scope by deliverable, not by days
“Delivered on the 30th” is a promise I can keep. “Two days a week” is a promise the unexpected breaks. Scoping happens by deliverable and date: that is what gets you a firm date instead of a theoretical availability.
Sectors
- Legal tech
- Contracts, clause extraction, case files
- Insurance
- Claims, policy and coverage comparison
- Healthcare and admin
- Records, coding, compliance
- Technical documentation
- Manuals, standards, specifications
- Finance
- Reports, regulatory filings, due diligence
The problem is the same everywhere: a lot of text, very little structure, and stakes that rule out approximation.
Got a corpus that fights back?
Describe your documents in three lines — volume, format, what you need out of them. In thirty minutes I’ll tell you whether it’s feasible, how, and what it costs. Reply within 24 hours on weekdays.