Your funnel has opinions. This layer has evidence.
Every lender believes things about what converts — about transparency, about pricing presentation, about which leads are worth a call-back. The intelligence layer (we call it Datum) turns those beliefs into measured signals tied to real outcomes, so the next experience decision is made on evidence.
Evidence signals
Does a borrower who opens the “show me the math” panel submit more often? Does adopting the automated value estimate change completion? Does an LO pricing off par close better files? Each signal is a with/without cohort against submitted and funded outcomes — honestly labeled, thin cohorts flagged.
An experiment framework
Experience variants run as assigned arms with deterministic bucketing, and every outcome event carries its arm. Correlation is not causation — the framework exists precisely so a promising signal can graduate into a controlled test before it becomes policy.
Funnel & source economics
Attribution rides the file from first click through the LOS milestones, so lead sources compare on what they actually produce — submittable files and funded loans — not clicks.
Re-engagement
Stalled journeys are scored and re-engaged with the context the borrower left behind — the file they started, not a cold blast. Suppression rules keep completed and opted-out borrowers out of the queue, structurally.
Measured against the loan file, not the pageview
The layer’s spine is the platform’s own event taxonomy — a small, disciplined set of journey events that carry outcome, experiment arm, and evidence signals on every record. Because the same platform runs the borrower journey and pushes the LOS file, signals join to loan milestones without a data-engineering project.
Leadership view, not surveillance: the console reports cohorts and talk tracks — what your best-performing experiences and officers do differently — with borrower privacy preserved. References and statuses, never raw borrower payloads. More on the data posture →