Bank of Beijing
Language-model agent platform for employee assistants
Bank of Beijing reported an AI operations assistant serving nearly 3,000 tellers
Problem
Bank employees needed access to financial knowledge and operating guidance. Customer-service staff also needed answers grounded in the bank's business rules.
Approach
The bank put its language-model agent platform into production in September 2023. It combined internal knowledge retrieval with application plugins. Its operations assistant provided regulatory policies and operating guidance, while a separate assistant supported remote customer-service staff.
Results
Takeaway
The bank separated assistants by employee role while sharing the underlying platform. The disclosed staff counts did not establish how often each employee used an assistant.
Categories
- Size
- Large enterprise
- Industry
- Finance and insurance
- Business function
- Internal work and knowledge managementCustomer service
- Innovation type
- Process innovation
- AI technology
- Generative AIAI agents
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
A bank-authored case submission described production deployment and employee assistants. The bank reported serving nearly 3,000 tellers and nearly 700 remote customer-service staff.
Full details are in the original sources.