Case studies Banking & insurance
Optimising a bank's customer service chatbot
A large, well-established bank
80%improvement in intent understanding accuracy
50%
Higher journey completion
NPS
Improved
The challenge
The bank's customer service chatbot was poorly optimised. Conversation flows broke, integration with internal systems was weak, and low NPS scores showed customers were frustrated.
What we built
- A current-state assessment of the existing chatbot.
- An optimisation strategy targeting the bank's biggest pain points and easier management for business users.
- Redesigned conversation flows and deeper integration with core systems.
- A future-state architecture for scale.
The results
- Higher customer satisfaction.
- More users completing their journeys.
- A chatbot that business teams can manage themselves.
Related work.
80%reduction in information retrieval time
An AI knowledge platform for a bank's credit card division
A leading Australian bank
72%reduction in manual policy review time
A regulatory compliance scoring agent on a bank's own servers
A large 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.