FIELD RECORD · 2016–2026 [FDE / APPLIED AI]

Ten years forward-deployed in the legal vertical.

I build and ship automation inside law firms: intake, conflicts, drafting pipelines. I bring a security researcher's habits to AI adoption. The client work here is anonymized; the patterns are real.

PROJECT · 01 / 02 [OPEN SOURCE]

I built this as a reference implementation of what secure legal intake automation can look like using the Model Context Protocol. The server is fully deterministic (no LLM calls, no network calls) and handles conflict screening, matter validation, follow-up templating, and triage logging. The idea is that the language model does the language work, and the server does the record work, with a clean boundary between them.

  • mcp
  • legal-ops
  • deterministic

Repository · Write-up

INDEX · WRITING

Writing

  1. What regulated-industry buyers actually need before they'll adopt AI

  2. Anatomy of a legal intake automation

  3. Deploying AI in a change-resistant vertical: field notes from a decade in law firms