AML compliance automation for a regulated lender (SOFOM ER)
A regulated Mexican lender (SOFOM). We built agents that flag transactions, generate reports for Mexico's Financial Intelligence Unit (UIF) and reconcile against the SITI portal.
Regulated lender, SOFOM ER (client under NDA)
The compliance team spent most of its time on manual work: checking transactions against thresholds, generating reports for the UIF, reconciling against the SITI portal. Every regulatory change multiplied the workload. The compliance officer was approaching the limit of what one team could handle.
Stack and deliverable
A suite of agents: automatic detection of unusual and structured transactions with cross-account checks; assisted generation of RO/RI/OIP reports with XSD validation before submission; daily reconciliation against the SITI portal; and an immutable audit log with an executive dashboard for the Communication and Control Committee. The entire compliance-first architecture is inherited from the DTX™ Fintech playbook.
What changed in the operation
What we learned
Compliance isn't an optional feature — it's the design requirement. The immutable audit log and per-decision traceability are what hold up under an audit. Skipping that step looks like a time-saver, but it's technical debt with a regulatory price tag.
How it was built
Technology: SITI AML portal · Account APIs · Audit log
Delivery: Staged delivery through to production
FAQ · this case
How did this Regulated financial services project make it to production?
Staged delivery through to production: design, build, testing with real data and launch. By the end, the client's team was running the agent in production, with observability dashboards and guardrails already configured. Stabilization is part of the delivery.
What tech stack was used in this Regulated financial services case?
SITI AML portal · Account APIs · Audit log. Each piece was chosen to fit the client's existing systems — no forced migrations, integrating through official APIs wherever they were available.
How are results tracked?
Before the project starts, we agree on an operational baseline with the client, and during stabilization it's reviewed on the operations dashboard. Because of the NDA, we don't publish this client's figures. In the diagnostic we define what to measure in your case.
Can this be replicated at another company in Regulated financial services?
The pattern is replicable; the specific implementation depends on the current stack, operating volume and internal rules. The Studio diagnostic identifies which pieces apply to your context and estimates the return for your case.
Who runs the agent after the project?
The client's team. Studio hands over the agent running and trains the team on monitoring, prompt adjustments and exception handling. Stabilization support is included for the first few months; after that, an optional monthly retainer is available.
What happens if the AI model changes or gets more expensive?
We don't depend on a single provider. If a model changes or gets more expensive, we move the agent to another one without rebuilding it.
Facing similar challenges in Regulated financial services?
A Studio diagnostic with an architect. We identify which processes to automate first and estimate the return for your case.
No cost · No commitment