Financial Services
Decisions a regulator can still follow nine months later.
When your lending roadmap has more work on it than your engineers can carry, ours join your team to build the origination, refinance, servicing and repossession systems, so a decision can still be defended to an examiner long after it was made.
In lending the same problems keep coming back. There's a process with a regulator at the end of it, a queue of exceptions someone clears by hand, and a system of record that can't explain how a decision was reached nine months later.
We build the durable workflow for steps that must not half-complete, the application your operators actually open, and lineage good enough to answer an examiner, and the engineer who sits with your servicing team to map that queue is the one who writes the code.
For SWBC we rebuilt the LOSExpress front end that credit unions use, for Auto Approve an approval engine that replaced more than four manual workflows, and for iLending the automated loan officer assignment and rate sheet processing.
Clients in this sector
What we have built here
Automotive / FintechSWBC doubles orders processed on a rebuilt LOSExpress
Credit union loan officers quote and book vehicle protection in SWBC's LOSExpress alongside a member's auto loan, but quoting was slow and new staff took too long to learn it. After gathering feedback from SWBC's staff and customers, our engineers and designers rebuilt one of its modules as a single-page application on a new design system. Orders processed doubled, and each loan officer now spends half as long on an order.
100%
Increase in orders processed
29%
Account growth
50%
Less order time per loan officer
Automotive / FintechAuto-refinance company doubles loans processed without adding agents
Auto Approve's loan agents were copying every refinance request by hand between the CRM, lender sites and Excel, a process that took two to three days. Our senior engineers worked hand in glove with Auto Approve's own IT staff to build the approval engine that automates it, and the company doubled the loans it processes each month without hiring more agents.
2×
Monthly loans processed
4+
Manual workflows replaced
0
Additional agents hired
Automotive / FintechModernizing an auto refi platform: iLending's Phoenix app
iLending's new loan application had stalled with another developer, running late, over budget and short of features, while call center agents kept turning refinance leads into loans by hand. TechFabric's engineers picked the project up, reviewed what had been built, and rebuilt the app day to day alongside iLending's own developers, automating lead and loan officer assignment, rate sheets and stipulation documents. Manual errors dropped and new agents got productive faster.
Automotive / FintechLocation Services: Synapse and SQL Server onto Databricks
Location Services' repossession platform automates assignment intake, so fewer people handle each case, and our engineers built it with the company's own technology team. When it was time to leave Synapse and SQL Server, we moved it onto Databricks in waves that could each be rolled back, and the rules engine that checks every assignment came through unchanged.
Automotive / FintechMitigating risk in vehicle repossession with durable execution
A wrongful repossession, and the penalty that follows, can start with one API call nobody saw fail. Location Services' software sometimes didn't tell a vendor an assignment was closed, and nothing retried the call. Our senior engineers rebuilt that process as a durable workflow on Temporal and put it into production, so every close retries on its own, alerts the operations team when retries run out, and keeps a full history.
B2B ecommerceTotalLoop: Cosmos DB and SQL Server onto Lakebase
TotalLoop finds a dealership's customers with equity in their vehicle and matches them to cars on the lot. DealerIQ brought the idea and the dealership know-how, and our senior engineers worked inside its team to build it on Azure, test it with one dealer account and ship a lean first version. Later we moved it off Cosmos DB and SQL Server onto Databricks Lakebase, in waves that could each be rolled back.
Automotive finance · Our own productThe auto loan lifecycle, run by governed agents
Origination and refinance steps that slow a deal down, such as credit pulls, VIN decode, deal structuring, stipulations and payoff quotes, run by agents in the lender's own environment. It came out of years of origination and refinance work for lenders and dealer groups. It connects to DealerTrack, RouteOne and CDK, and every action is checked against policy and recorded for the examiner.
The lines that do this work
Migrations to Databricks
Off Snowflake, Synapse, Teradata and SQL Server, onto Lakehouse and Lakebase, with a cutover you can reverse.
Data science & AI
Context stores, memory, retrieval and governed agents that survive production.
APIs & durable systems
Long-running operations that survive restarts and partial failure. Temporal under the lakehouse jobs, agent runs and approvals that must not half-complete.
Data & AI governance
Unity Catalog designed so grants hold, lineage survives a refactor, and an agent inherits permissions instead of routing around them.
FAQ
Financial Services: questions we get asked
Do you understand lending compliance, or only the engineering?
In this sector they are the same problem. TILA, ECOA and FCRA checks are built into AutoFabric at /products/autofabric as policy the agent is evaluated against on every action, rather than sampled in a quarterly review. We build the system so your compliance people can prove what happened.
We are a credit union, not a national lender. Is that too small?
The SWBC work at /case-studies/swbc was built for credit unions specifically, and the constraint there was loan officers who needed to move faster without a training manual open beside them. Smaller institutions tend to have clearer problems and shorter decision paths, which suits how we work.
Can you work with our existing loan origination system?
Yes, and it is the more common shape. The Auto Approve engine at /case-studies/auto-approve sat in front of existing workflows rather than replacing them, and AutoFabric reaches into DealerTrack, RouteOne and CDK because that is where the deals already are.
Talk to someone who has built this.
A technical conversation with a senior engineer who has shipped in this sector, about what you are trying to build.