Fintech · 16 weeks to launch
Cutting loan decisions from 4 days to 7 minutes
A digital lending platform with automated underwriting that took loan decisions from a 4-day manual review to a 7-minute automated flow.
- loan decision time, down from 4 days
- 7 min
- loan decision time, down from 4 days
- application completion rate
- 2.1×
- application completion rate
- platform uptime since launch
- 99.98%
- platform uptime since launch
The challenge
- Client
- Consumer lending fintech
- Services
- Custom Software, AI & Machine Learning, Cloud Solutions
- Timeline
- 16 weeks to launch
The lender's underwriting ran on email, PDFs, and a five-person review team. Applications took four days to decide, and 60% of applicants abandoned before finishing the paperwork.
Compliance requirements meant every automated decision needed a full audit trail, human-review escalation paths, and explainable criteria. A rules engine, not a black box.
What we did
The approach, decision by decision
- 01
Rebuilt the application flow around completion
Replaced a 34-field form with a progressive six-step flow with document upload, autosave, and bank-data prefill. Every removed field was argued for with funnel data.
- 02
Automated underwriting with an explainable rules engine
Encoded credit policy as versioned, testable rules with ML-assisted risk scoring as an input, never the decider. Every decision produces a human-readable audit record.
- 03
Kept humans in the loop where it matters
Edge cases route to a purpose-built review console where analysts see the full applicant picture in one screen, cutting manual review time for the cases that still need it.
The results
- Median time-to-decision dropped from 4 days to 7 minutes for 83% of applications.
- Application completion more than doubled (2.1×) after the flow redesign.
- Review team refocused on genuinely complex cases; approval quality metrics held steady.
- Passed the client's external compliance audit with zero critical findings.
Built with
- Next.js
- Go
- PostgreSQL
- Redis
- AWS
- Terraform
Keep reading
More case studies
Logistics · Freight operations startup
Scaling a logistics SaaS from zero to 50,000 shipments a month
A multi-tenant freight management platform launched in 12 weeks, now processing 50,000+ shipments a month across three markets.
Read case studySaaS · B2B software company
Deflecting 62% of support tickets with a grounded AI assistant
A retrieval-grounded AI support assistant that resolves 62% of inbound tickets with answers cited from the client's own documentation.
Read case studyYour project could be the next case study
Tell us the metric you need to move. We'll scope the build that moves it: fixed price, weekly demos, results you can publish.
We reply within 1 business day.