Challenge
BH Capital Funding's underwriters were doing high-judgment work buried under low-value work. Every file meant pulling data from documents by hand, checking it against lender criteria, and assembling a submission package — roughly 30 minutes per file before a human even made a decision. Volume capped out at how fast people could read, approvals stretched into days, and too many files were declined for reasons that were knowable up front.
Approach
We mapped the real underwriting workflow end to end, then automated the mechanical steps while keeping a human on the decision. A rules engine and AI-assisted parsing handle intake, extraction, scoring, and lender-fit routing; underwriters review and decide. Everything writes back to the CRM so the pipeline stays current.
Solution
The engine ingests a file, extracts and structures the data, scores it against a custom rules engine, and routes it to the right lenders — assembling the submission package automatically. Underwriters spend their time on judgment, not data entry. Because submissions arrive cleaner and better matched to lender criteria, fewer come back declined.
Before
- Manual file review — ~30 minutes each
- Approvals measured in days
- Avoidable declines from mismatched files
- Throughput capped by reading speed
After
- Rules-based scoring + routing — ~5 minutes each
- Approvals in 2–3 hours
- Decline rate down roughly 35%
- Underwriters focused on decisions
Client quote pending approvalA quote from BH Capital leadership will be added here once approved for publication.
BH Capital Funding