A regulatory submission is a set of numbers each of which must be defensible back to a source system. That makes most of the work reconciliation and evidencing rather than calculation — and it makes the design principle unusually clear.
All Financial Services →
Regulatory reporting teams rarely struggle with the arithmetic. They struggle with the fact that a figure in a submission has to be reconciled to a source system that was not designed to produce it, that definitions differ between the regulation and the general ledger, and that when a number moves between periods somebody has to explain why in terms a supervisor accepts.
The recurring work is therefore: chase the break, find the explanation, evidence it, and write the commentary. All of that is document and system archaeology, and it is done under a deadline every quarter by people who could be doing analysis instead.
An AI system is well suited to the archaeology and badly suited to the arithmetic. That division is the whole architecture, and inverting it — letting a model compute a reportable figure — is the failure mode we design against explicitly.
Every AI-produced element is labelled as such, with its sources attached, and is reviewed by a named person before it forms part of a submission. That review is the control, and pretending it can be removed is how a reporting system becomes a finding.
The lineage runs in both directions. From any figure you can reach the source records; from any source change you can find the figures it affects. Building this is unglamorous data engineering and it is what makes the AI layer useful rather than decorative — an agent that cannot show its working produces text nobody is allowed to rely on.
And the model version is pinned and recorded per reporting period. If a supervisor asks in five years how a particular explanation was produced, the answer has to be reproducible, which means the system that produced it has to be reconstructable.
figure vs source system
across systems and periods
the supporting records
cited, labelled AI-produced
accepts, corrects or rejects
computed by code, always
No, and we would decline to build that. Reported figures are calculated deterministically from defined sources. What the AI layer does is explain, evidence and draft around those figures, which is where the hours actually go.
The retrieval corpus is versioned, so you can ask what the rules required at a point in time rather than only what they require now. That matters when a prior period is reopened, and it is a small design decision with a large payoff.
Usually not. Reconciliation explanation and citation-grounded question answering are well within reach of a self-hosted open-weight model, which for financial data is frequently the preferred deployment anyway.
Not the arithmetic. The hours are in explaining the break, and that is the part a system can genuinely help with.
30-minute technical call · no deck
What we built, what stage it is at, and a link to the live thing wherever there is one.
yourOS is an operating system with an AI at its heart. You talk to it like a person, out loud or typed. It makes your calls, plans your days and works on your projects with a crew of agents, on your own private server. Our own product, built from the first commit; the waitlist is open.
Website, backend and app assets for Sonora, a free AI sound-therapy app on iOS and Android published by Cognitive AI.
Brand, website, prototype, apps on five platforms, the AI backend and the algorithm-intelligence pipeline for Podswap, a social growth engine that runs without a human in the loop.
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Live at coherence.com: brand identity generated with AI agents we directed, the motion system and website for the group behind Sonora, AboutAI, WakeUp and MudShadows. Agent work remains in build.
Live at domainbooth.com for DomainBooth, a premium domain brokerage: a new animated mark, every page redesigned and rebuilt with designed mobile layouts, and a custom CMS for its sales record, featured names, press and enquiries.
Apps, platforms and campaigns for these teams, long before the AI work. Every one is written up on the work page — what we did, and where our part ended.
