Use Case Intelligence RSS Search use cases Search
AWS Financial Services Hong Kong

HKBGE

Customer Service Automation

HKE Holdings , a listed fintech group focused on the Asia-Pacific region, established Hong Kong BGE Limited (HKBGE) to offer digital asset trading solutions for both retail and professional investors.

Read the original story Explore all use cases
70% cost savings redirected to staff training
Furthermore, HKBGE anticipates reducing support costs by 70 percent, freeing up resources to invest in staff training and tailored customer service.
Once the chatbot is fully in production, HKBGE expects to reduce support costs for FAQs as much as 70 percent, freeing up resources to invest in staff training.

Reported impact

Business outcome

HKBGE is currently running its generative AI chatbot on AWS in a testing environment and plans to implement it with the launch of the trading platform, providing an excellent onboarding experience and platform for customers with personalized responses to FAQs.

  • Cost Reduction
  • Customer Experience

Solution

HKBGE is establishing a compliant and trusted virtual asset trading platform for clients to transact and trade virtual assets together with the company's secure custody services. To personalize responses to customers' questions, HKBGE collaborated with AWS to create a generative AI chatbot based on Meta's Llama 2 large language model. The chatbot, powered by Amazon EC2 G5 instances with NVIDIA A10G Tensor Core GPUs, is expected to deliver a better customer onboarding experience, providing thousands of personalized responses daily. Furthermore, HKBGE anticipates reducing support costs by 70 percent, freeing up resources to invest in staff training and tailored customer service. Since the license application in 2021, HKBGE has collaborated extensively with Amazon Web Services (AWS) on the development of its trading platform.

Data flow

As part of the development process, the CS & IT team worked with AWS on the RAG chatbot's search capability. Another part of the development process involved making sure the LLM could recognize inappropriate questions from bad actors. "Our integrated security approach on AWS provides real-time monitoring, ensuring adherence to regulatory standards and safeguarding the customer's privacy," adds Cyrus.

Solution architecture

5 components · 2 layers
  1. Compute
    • Llama 2 Provides the open language model used by the customer and agent support workflows.
    • AWS Lambda Executes serverless processing and workflow glue for the customer and agent support workflows.
  2. Governance
    • Amazon GuardDuty Monitors threats and security signals around the customer and agent support workflows.
    • Amazon Inspector Assesses the workload posture supporting the customer and agent support workflows.
    • Amazon Detective Helps investigate security events tied to the customer and agent support workflows.

Architecture clues

  • "Our integrated security approach on AWS provides real-time monitoring, ensuring adherence to regulatory standards and safeguarding the customer's privacy," adds Cyrus.
  • As part of the development process, the CS & IT team worked with AWS on the RAG chatbot's search capability.
  • Cyrus Chan, network specialist at HKBGE, says, "We need to safeguard the chatbot from misuse by individuals with disruptive intentions." This protection strategy was also part of a broader program to...
  • Later in 2023, HKBGE's IT team worked with AWS Solutions Architects to develop a retrieval-augmented generation (RAG) chatbot, which combines the advantages of retrieval-based models with generative...
  • To personalize responses to customers' questions, HKBGE collaborated with AWS to create a generative AI chatbot based on Meta's Llama 2 large language model.

Evidence from the source

As the business expands, HKBGE anticipates a proportional increase in queries over time.
Later in 2023, HKBGE's IT team worked with AWS Solutions Architects to develop a retrieval-augmented generation (RAG) chatbot, which combines the advantages of retrieval-based models with generative AI models to provide more contextually...
Since the license application in 2021, HKBGE has collaborated extensively with Amazon Web Services (AWS) on the development of its trading platform.
The chatbot, powered by Amazon EC2 G5 instances with NVIDIA A10G Tensor Core GPUs, is expected to deliver a better customer onboarding experience, providing thousands of personalized responses daily.
To help deliver a better customer experience, HKBGE looked to develop a generative artificial intelligence (AI) chatbot to provide personalized responses to frequently asked questions (FAQ) as customers visit the platform.
To personalize responses to customers' questions, HKBGE collaborated with AWS to create a generative AI chatbot based on Meta's Llama 2 large language model.
Transparency Evidence & methodology 96/100 reference value · 90% confidence · 3 sources

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value96/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity16/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    3 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence90%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability23/25
    11 of 12 key fields link to a named source.
  • Direct evidence20/20
    6 direct source quotes retained.
  • Date provenance8/10
    The publication date comes from publisher-controlled metadata.
  • Source transparency9/10
    3 source references document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. AWS

    HKBGE customer story

    First-party
    https://aws.amazon.com/solutions/case-studies/hkbge/
    Source type
    Vendor-published customer story
    Published
    Aug 1, 2024
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date
  2. The SFC Network

    Hong Kong BGE Limited (CE BSI739) | SFC Licensed Firm

    Independent secondary
    https://thesfcnetwork.com/firm/BSI739/hong-kong-bge-limited

    The profile description says '4 current licensed staff', and the Organization JSON-LD contains numberOfEmployees value 4.

    Source type
    Structured company profile
    Supports
    • Company size
  3. The SFC Network

    Hong Kong BGE Limited (CE BSI739) | SFC Licensed Firm

    Independent secondary
    https://thesfcnetwork.com/firm/BSI739/hong-kong-bge-limited

    The JSON-LD lists addressCountry 'HK' and numberOfEmployees value 4; the meta description says '4 current licensed staff.'

    Source type
    Structured company profile
    Supports
    • Company size

Date evidence

Not separately sourced Industry, Region. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
AWS Oct 25, 2024 BPC Financial Services Global To support this, we began exploring the implementation of AI features to benefit both our employees and customers.” To improve the customer experience, BPC started to develop an intelligent chatbot that could respond to… Additionally, BPC is already using Amazon Connect , which empowers contact center agents to deliver superior… Customer Service AutomationIT Operations Automation Amazon Bedrock · Amazon Q · Amazon Q Developer AWS Sep 1, 2024 SBI Life Insurance Financial Services India SBI Life Insurance, an SBI Insurance Group company, provides consumers with products such as an affordable mortality insurance plan, which allows customers to revise the sum insured based on their stage of life; a… It also shortened the training periods by about 30 percent. Customer Service AutomationEnterprise Knowledge Search Amazon Bedrock · Amazon Kendra · Amazon OpenSearch Service AWS Jan 1, 2024 bunq Financial Services Netherlands bunq was founded in 2012 to bring diversity of product, people, and business models to the traditional banking sector. Just over a decade after its launch, the neobank with a €1.65 billion valuation operates a banking… 1.65 billion Customer Service AutomationDocument Processing AWS CloudHSM · AWS Key Management Service · AWS Security Hub