Forward-Deployed AI · Payments Infrastructure

I fixed payment systems at 2am. Now I build AI that holds up in production.

Ten years in payments operations: SWIFT, ISO 20022, ACH, cross-border settlement. Today I build production AI agents and automations that run real work end to end. This is where I write what I am building, and break down what is happening underneath agentic commerce.

Book an AI consultation Read the blog
ex-HSBCSociété GénéraleMcGillMontreal
Scroll
01 / About

I spent ten years watching money move. Now I build the systems that move it.

For ten years my job was to know how money actually moves. SWIFT, Lynx, ISO 20022, ACH, cross-border settlement, across HSBC and Société Générale. Not the marketing version of payments. The 2am version: the batch that half-processed, the one malformed record that failed an entire file, the reconciliation that broke three systems downstream because someone truncated a remittance field a decade earlier.

That work taught me a discipline that has little to do with technology being clever and everything to do with respecting how it fails. Scope before you fix. Find the poison pill. Race the cutoffs. Tell people early, because clients forgive a delay and never forgive silence. Write the root-cause analysis, because it is the only thing standing between you and the same incident twice.

What changed is that I stopped only writing about this and started building. I now design and ship production AI systems against real problems: multi-tool agent integrations, scheduled autonomous workflows, a full-stack app on a live database that my own household depends on. Not demos. Things that run real work end to end, break in real ways, and get fixed.

The surprise was how familiar it felt. Running a fleet of AI agents is the same job as running payment operations. Schedule the jobs so they do not step on each other. Build idempotency so nothing posts twice. Keep a hard respect for the limits of the system, except now the budget is a context window instead of a settlement cutoff. Ten years of operations turned out to be ten years of training for this.

I write here a few times a week about the infrastructure underneath agentic payments: how autonomous systems will authenticate, transact, and settle, from someone who operated the rails and now builds on top of them. If you are putting AI into production against a real operational problem, book a consultation or join the weekly newsletter.

02 / Projects

Things I have shipped.

Two live products, both built and run end to end. One sells. One tells a story to a few hundred thousand people.

Joey

AI SDR · Forward-Deployed AI

An AI sales rep that works the leads a business already paid for. It answers every new lead in seconds, re-engages the no-shows everyone ignores, qualifies against the founder's own rubric, and books the ready ones straight onto the calendar, all in the founder's voice. Not a cold-email robot. It works the people who already raised a hand. Built into the funnel and run for you, on a fixed pilot priced on booked calls, not messages blasted.

ARCHV

The ARCHV

Football history, illustrated · @thearchv_ca

An immersive archive of football's greatest moments, retold for a few hundred thousand people across social. The owned site is the brand's credibility surface and link-in-bio destination, built to an awwwards-grade brief on a locked navy, cream and gold identity, with a WebGL hero and scroll choreography. The whole content operation behind it runs as a fleet of scheduled AI agents: generation, scheduling, analytics, and a performance log that breeds toward what works.

03 / Blog

Field notes from building in production.

Lived-experience write-ups on payment infrastructure and running AI agents against real work. Expanded from what I post each week.

Read all posts →

04 / News

The brief on agentic commerce.

A running digest of payments, agentic commerce, and the AI stories that touch how money will move. Sourced, edited, and written plainly.

See the full digest →

05 / Work with me

One conversation. The one build worth doing.

30 min

Most teams do not have an AI problem. They have a deployment problem: a real operational pain, and no one who has both shipped against it and lived inside the domain. That is the gap I work in.

Book a consultation and we name the one build actually worth doing, what it is worth, and how it would run in production. You leave with a plan whether or not we work together.

For founders and teams putting AI into production against payments, operations, or agentic-commerce problems.

Put a real problem in front of someone who has shipped.

Thirty minutes, no pitch deck. We scope the highest-leverage AI build for your funnel or your operation.

Book your AI consultation