Scope
one problem, named
founder decides, agents build
AI Engineer · Fintech Operations
At 2am a SWIFT MT103 batch failed with 4,112 records held. For ten years a human paged on-call, found the poison record, resubmitted the batch, and released settlement by morning with no loss and no sleep. The same job now runs as agents that isolate the record, resubmit, and settle while the human stays asleep.
01 / About
I was born in Nigeria and grew up in Lagos. At nine I moved to the United States, to New Hampshire, where my mother was studying at Dartmouth. Then Eaglebrook School in Massachusetts, then Canada and McGill. I got used to arriving somewhere new, reading the room and learning how to contribute.
Payments was not a plan. I studied electrical engineering at McGill with a focus on digital system design and automation. I planned on working on control systems but found myself at HSBC managing market risk systems instead. Fast forward to today, I have spent ten years keeping bank systems running, with the last five of those in payments.
I started building with AI because I kept seeing people post about what they had made, and it looked like something I could try. My partner and I now run our household on an app I wrote for us. Outside work I make music in Ableton Live and engineer the audio for a friend's podcast, Pros in the Arena.
I am building and optimizing with AI in production, and I write down what I learn for anyone making the same moves, or just trying to be happier in the job they have. Follow along here.
02 / The delivery
Scope to Run, the way I actually ship. Scroll through it, or drag the timeline.
one problem, named
founder decides, agents build
The ARCHV iOS app, build 40
agent fleets, every diff reviewed
238 tests, none failed
fresh-install UI gates
review caught shipping bugs in 4 of 6 builds
deploys verify themselves before going green
a desk that publishes every morning
health probes that email before users notice
Two live products, both built and run end to end. One tells football's story with an iOS app live on the App Store, and one explains AI news in plain English.

An immersive archive of football's greatest moments, retold across social and in an iOS app that is live on the App Store. The owned site is the brand's credibility surface and link-in-bio destination, built to an awwwards-grade brief, 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.

An Instagram that turns recent AI news into plain, single-graphic posts, with a Substack for the longer reads. It runs on a scheduled agent that pulls the week's real stories, writes each post to a fixed brief, and checks every one against hard rules on sourcing and voice before it ships. No invented numbers, no hype, one direct question to end on.
This is how I size a two-week build. Answer three questions and the sketch fills in, honest about what fits in a fortnight.
Lived-experience write-ups on payment infrastructure and running AI agents against real work. Expanded from what I post each week.
A running digest of payments, agentic commerce, and the AI stories that touch how money will move. Sourced, edited, and written plainly.
Plain-English reads on the companies building AI's data centres: where the power and the cooling come from, and what has actually been built. Some issues cover model and agent news instead. It lands on Substack every Monday, Wednesday and Friday.
Trouble with the form? Subscribe on Substack. Unsubscribe any time.