Case studies Banking & insurance
A regulatory compliance scoring agent on a bank's own servers
A large bank
72%reduction in manual policy review time
10%
Of policies had compliance gaps that manual review had missed
25k to 30k
Regulations in the knowledge base
The challenge
Internal policies had to stay aligned with a large and constantly changing body of central bank regulation: anti-money-laundering notices, circulars and historical rulings. Manual reviews were slow and expensive, and gaps were easy to miss.
What we built
- An in-house large language model, fine-tuned on central bank regulatory data and running on the bank's own servers.
- A structured knowledge base of roughly 25,000 to 30,000 historical regulations and notices, with vector-embedded comparison.
- Each internal policy is checked against the closely related requirements to return a compliance score, flag contradictions and gaps, and recommend improvements.
- Historical rulings are cross-referenced so every assessment is grounded in precedent.
The results
- Manual policy review time reduced by 72%.
- 10% of policies found to have compliance gaps that manual review had missed.
- Data never leaves the bank: the model and knowledge base run on-premise.
Related work.
80%reduction in information retrieval time
An AI knowledge platform for a bank's credit card division
A leading Australian bank
80%improvement in intent understanding accuracy
Optimising a bank's customer service chatbot
A large, well-established bank
10%increase in profitability
A sovereign data ecosystem for a digital microfinance bank
A leading digital microfinance bank
A similar workflow in your business?
Tell us how it runs today. A strategist and an engineer will work out what agents could do with it and what that would take.