Customer Service Automation · Document Processing · Risk Management
Hong Leong Bank needed to replace slow manual banking operations and limited chatbot performance with a secure AI ecosystem that could support dynamic customer support, document-heavy trade operations, sanction screening, and faster software delivery.
Reported impact
Hong Leong Bank increased chatbot accuracy and engagement, sped up document-heavy operations, reduced development time, and created a secure platform for expanding agentic banking services.
Hong Leong Bank built its AI ecosystem on Google Cloud with Gemini platform as the secure environment for internal and customer-facing agents. The bank runs Gemini as a private instance to minimize data exposure. For customer service, it replaced a static open-source chatbot with Gemini 2.5 Flash in a Retrieval-Augmented Generation architecture, then used the Agent Development Kit to coordinate specialized agents that call backend APIs and retrieve real-time core-banking data for personalized responses and promotions. Document AI handles trade-finance OCR across invoices and shipping forms and supports sanction screening for credit-underwriting teams. Compute Engine, Cloud SQL, and Google Cloud Search support the wider application environment, while Gemini Code Assist improves developer productivity. This gives HLB one platform for conversational banking, document automation, risk controls, and faster software delivery.
Customer or employee requests are interpreted by Gemini 2.5 Flash in Gemini platform, which uses ADK-driven agents to call secure backend banking APIs and return real-time answers. Trade-finance and underwriting documents are processed through Document AI, while the wider application environment relies on Compute Engine, Cloud SQL, and search services.
Document AI to process high-volume documents, such as invoices and shipping forms.
Gemini 2.5 Flash for its dynamic Retrieval-Augmented Generation (RAG)
Gemini Code Assist that speeds time-to-market.
Using the Agent Development Kit (ADK), Gemini commands specialized agents to execute secure calls to HLB's backend APIs
the bank deploys a diverse suite of AI agents on this platform
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Huawei Cloud Sample Archived · Apr 20, 2026 Postal Savings Bank of China Postal Savings Bank of China needed a scalable AI infrastructure and unified model platform so it could automate customer service, trading, document review, and risk workflows without creating disconnected AI pilots… RFQ volume exceeded 1.5 trillion yuan AI computing and data center · Huawei Cloud Stack · Youzhi large model 
In-house Sample May 8, 2024 Mapfre Mapfre wanted to improve customer experience and streamline insurance operations such as claims handling, risk assessment, underwriting support, document management, internal knowledge access, and digital content… 75 use cases under study for the application of generative AI ControlExpert · Cyberwrite · Holistic AI In-house Sample Apr 9, 2024 ClearBank ClearBank needed to deploy multiple generative AI use cases for banking API workflows in a regulated financial environment while safeguarding security, robustness, transparency, bias control, and regulatory alignment. Large Language Models (LLMs) · evaluation pipeline · model experiment tracking system 
