First I wrote about it.
Then I built it.

Where the hours actually go

Clauses drafted a thousand times before. Evidence mapped manually into Excel. Statement structures rebuilt that already exist in dozens of variations. Not legal work - assembly work. And clients who pay dearly for it, because there's no alternative.

15 years of international litigation. Arbitrations. Complex lawsuits. The accumulation of thousands of hours - and a moment every litigator knows: The best lawyers in the country wasting time on work a machine could do. I saw it from the inside.

I wrote that it was years away. I was wrong.

August 2025. Before a single line of code. Sat down and wrote an article. Not a business plan. Not a pitch deck. A professional article on AI and international arbitration. The premise: international arbitration is the natural laboratory for integrating AI into law.

Finished writing. Read what I'd written. Realized I was wrong. Not the analysis - the timeline. Technology is already here. Not 2032. Now.

The decision to leave and build

Let's be honest: partner at a large firm, a litigator - not a programmer. The decision to build this myself was not a given.

If I know what needs to be built, and if the technology is already here - then writing about it isn't enough. It needs to be built.

What they don't tell you

Built a system that produced documents that looked perfect and contained lies. Broke it down and rebuilt it. This time with quality checks that show no mercy.

"Process passes" doesn't mean "document is valid." Machine producing a document with one wrong fact - professional liability, not a tool. Legal experience becomes the advantage: I know what's broken because I know what's correct.