Architecture decisions, eval patterns, compliance approaches, and engineering writeups from the work we ship. Written by the engineers building it — not a marketing team translating it.
The five-phase workflow we follow on every fintech AI engagement — what gets locked at each phase, and the few places where EU and US specifics actually shape the engineering. The interesting decisions in a fintech AI build are not about the model. They are about everything around it — the audit log, the human override, the eval discipline, the model inventory. Each of these is a normal engineering concern in any AI system. Each is treated very differently when the system sits inside a regulate
Roughly monthly. Production notes on fintech AI as we publish them. No marketing, no upsell — just the post.
Unsubscribe anytime. We use your email only to send the newsletter.