Fintech & banking

Rebuilding an SME lending platform around automated underwriting

We replaced a manual, spreadsheet-heavy loan origination process with a web platform that pulls Open Banking data, scores applications and routes only edge cases to underwriters.

of applications decided automatically within policy
41%of applications decided automatically within policy
applications handled per underwriter per week
2.6xapplications handled per underwriter per week
median decision time for complete applications
<1 daymedian decision time for complete applications
A small business owner reviewing financial charts on a laptop

The challenge

The lender's application journey collected documents through a web form, after which underwriters downloaded bank statements, rekeyed figures into spreadsheets and emailed applicants with follow-up questions. A straightforward application took several days to decide, and applicants frequently dropped out while waiting.

The business wanted to grow loan volume without growing the underwriting team at the same rate. Any automation had to be explainable to underwriters and auditable for the regulator, and credit policy changes needed to ship without a full release cycle.

Our approach

We redesigned the applicant journey first, reducing the form to the fields actually used in decisions and adding Open Banking consent so transaction data arrives directly from the applicant's bank. Company data is enriched from Companies House and a credit bureau API at submission.

A categorisation and affordability service turns raw transactions into cash flow features such as average monthly revenue, volatility and existing debt servicing. A versioned rules engine applies credit policy, and a gradient-boosted model trained on the lender's historical book produces a risk score with feature-level explanations. Clear accepts and declines are decided automatically within policy limits; everything else goes to an underwriter workbench that shows the data, rules fired and model explanation side by side.

Every decision is stored with the inputs, policy version and model version used, so any outcome can be reproduced later. Credit policy is edited by the risk team through a reviewed configuration workflow with test cases, and the release pipeline includes contract tests against each third-party API and regression suites for the decision logic.

What we delivered

  • Shortened applicant journey with Open Banking consent and document upload
  • Transaction categorisation and cash flow affordability metrics
  • Versioned credit policy rules editable by the risk team with review
  • Risk scoring model with per-decision feature explanations
  • Underwriter workbench with case assignment, notes and referrals
  • Reproducible decision records for audit and complaints handling

More case studies

Travel & hospitality

A complete taxi booking platform: fleet ERP, booking website and Flutter apps

We built a taxi operator's full digital platform: a fleet and operations ERP, a booking website, and Flutter rider and driver apps sharing one real-time backend.

ERP, website and mobile apps on one live backend
3-in-1ERP, website and mobile apps on one live backend
apps for iOS and Android from one Flutter codebase
2apps for iOS and Android from one Flutter codebase
driver tracking for riders and the dispatch team
Livedriver tracking for riders and the dispatch team

Travel & hospitality

A restaurant management platform: ERP, online ordering website and Flutter apps

We built a restaurant group's ERP for orders, kitchen, menu and inventory, plus an online ordering website and a Flutter customer app, all on one shared system.

ERP, website and mobile app sharing one menu
3-in-1ERP, website and mobile app sharing one menu
commission on direct online orders
0%commission on direct online orders
sales and stock view across every outlet
Livesales and stock view across every outlet

Healthcare & life sciences

A remote patient monitoring platform that care teams actually use

We rebuilt a telehealth provider's video visit and remote monitoring stack so device readings, alerts and clinician workflows live in one HIPAA-aligned platform.

faster median time from out-of-range reading to clinician review
64%faster median time from out-of-range reading to clinician review
systems clinicians use to review a monitored patient
3→1systems clinicians use to review a monitored patient
to launch a new chronic care programme, down from months
11 wksto launch a new chronic care programme, down from months

Facing a similar challenge?

Tell us where you are and what you need. A senior engineer replies within 24 hours with next steps, not a sales script.