I build agent products that stop before they do damage.

Product manager in supply-chain finance. My work is mostly about the gap between what a model can draft and what a regulated business can act on — policy packs an agent must cite, approval gates it cannot route around, and evidence honest enough to argue with.

Work

KYC Checker Agent

Compliance review · live demo

August – September 2026

An agent that reads a KYC case against fifty-three rules, gathers the standard evidence, and stops. A human approves, edits or declines; only then does the server run anything. Graded on 9 cases and 66 written-in-advance expectations.

Read the case studyOpen the live demo ↗

Stablecoin receivables platform

Trade finance · private repo

July – August 2026

The product the agent lives inside: suppliers submit invoices, funders finance them in USDC, and every status change is re-derived from the chain before the database is trusted. Seven roles, and a gate nobody can self-serve past.

Read the case study

Pricing analyst

In progress

The same method in a different domain — a rules engine that sets the band, an agent that reasons inside it and never computes the price itself. It is here to be held to: the claim this portfolio makes is that the method transfers, and one project cannot show that.

How I work

  • Write the decision rule before the run. On the model comparison in the KYC case study, the rule I fixed in advance disqualified the model I ended up choosing. That is recorded rather than reinterpreted.
  • Counts, not rates. 9 hand-graded transcripts do not make a percentage, and quoting one invites comparison with benchmarks measuring something else.
  • Publish the limits at the same size as the results. What the evidence does not cover is part of the evidence.