Customer Stories / Financial Services / Switzerland

2024
BPC logo

Boosting Customer Service and Developer Productivity Using Generative AI on AWS with BPC

Learn how BPC, a global leader in payments solutions, uses generative AI on AWS to streamline its developer and customer service workflows.

66%

reduction in chatbot costs

4000

lines of code generated

46%

acceptance rate achieved

6640

lines of Java code scanned

Overview

Global payments solutions provider BPC has been experimenting with generative artificial intelligence (AI) for over 1 year to drive efficiencies across its internal workflows. Because it operates in a highly regulated industry, BPC must protect its customers’ data as it expands its technology road map. To maintain data sovereignty in the cloud, BPC uses Amazon Web Services (AWS) to adopt AI-powered solutions.

Since beginning its AI journey, BPC has trialed AI across multiple divisions, eventually launching two generative AI solutions for its customer service agents and developers. By implementing AI-powered solutions across its workforce, BPC has improved its customer support and accelerated the release of new features and updates. The company will continue using generative AI to improve its operational efficiency and customer experience.

BPC AWS image

Opportunity | Using Amazon Bedrock to Build an Intelligent Customer Support Chatbot for BPC

Headquartered in Switzerland, BPC—a global leader in payments solutions—is powering banking payments and e-commerce transactions for over 450 enterprises in over 120 countries. It has been using AWS since 2014. “We continuously innovate to remain competitive,” says Artem Zhukov, DevOps team lead at BPC. “At BPC, our goal is to help our customers drive innovation and deliver the payment experiences of tomorrow. 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 customer inquiries. “We use generative AI to enhance our operational efficiency,” says Eugene Tochilkin, engineering manager at BPC. “We aimed to develop a chatbot that could be used by both our clients and customer support teams. For instance, an agent can enter a client’s request into the chatbot and pass the generated response to the customer after review.” This chatbot was trained for high accuracy so that it reduces the workload for customer support agents.

To achieve maximum performance and deep AI capabilities, BPC uses large language models (LLMs) as the core of its chatbot. To deepen the capabilities of its solution, it also used retrieval-augmented generation, a technique that fetches data from BPC’s data sources and enriches prompts to provide more relevant and accurate responses.

Storing its data on AWS, BPC unlocked its full potential without sacrificing security using Amazon Bedrock, a fully managed service for building and scaling generative AI applications using foundation models. “To ensure optimal performance, we require an environment with advanced security features,” says Peter Ilosvai, head of operations at BPC. “Using Amazon Bedrock, we can resolve matters quickly and identify the causes of disruptions.”

BPC evaluated several foundation models in Amazon Bedrock. “Our prompts are huge,” says Tochilkin. “We put a lot of information in our prompts to produce highly relevant answers, which can drive up costs.” To balance cost with performance, the company uses Anthropic’s Claude 3 Haiku, which is one of the fastest and most cost-effective models in its intelligence class. (See figure 1.) “As soon as Claude 3 Haiku became available, we changed the settings of our engine to support it,” says Tochilkin. BPC has since reduced the cost of its chatbot by 66 percent compared with other models.

After deploying its chatbot to production, BPC offered it as a rebranded solution to its customers. “We’re getting positive feedback,” says Tochilkin. “Our customers can deploy the chatbot in their own sandbox environment and use it for marketing and advertisements.”

BPC diagram
Figure 1. BPC architecture diagram
kr_quotemark

Using Amazon Bedrock, we can resolve matters quickly and identify the causes of disruptions.”

Eugene Tochilkin
Engineering Manager, BPC

Solution | Achieving 46 Percent Acceptance Rate for Code Generation Using Amazon Q Developer

Next, BPC focused on streamlining its developers’ workflows by testing Amazon Q Developer, a generative AI–powered assistant for software development. Before this solution, some of the company’s developers used another AI assistant to help them debug code. But the quality was not good enough for company-wide adoption—the tool had an average acceptance rate of 30 percent according to the tool vendor.

BPC began piloting Amazon Q Developer with a group of eight developers. In 4 months, its developers generated over 4,000 lines of code with an acceptance rate of 46 percent. The group has also used the service to perform security scans on 6,640 lines of Java code, helping improve developer productivity. “It significantly reduces the amount of time spent on simple code and repetitive tasks,” says Stanislav Krainov, developer team lead at BPC. “Now we can focus on the more intelligent, challenging, and high-quality code in addition to our security posture.” Encouraged by the results of this experience, BPC plans to use Amazon Q Developer to help automate the refactoring of the company’s codebase and to debug application logic issues.

Outcome | Scaling Infrastructure and Expanding to New Markets on AWS

BPC plans to roll out Amazon Q Developer to all its 200 developers in phases. To further improve productivity, the company’s engineers are working on building their own custom LLMs using Amazon SageMaker, which developers use to build, train, and deploy machine learning models for virtually any use case with fully managed infrastructure, tools, and workflows. BPC also plans to test new generations of foundation models as they are released, helping improve the performance of its chatbot even more.

Additionally, BPC is already using Amazon Connect, which empowers contact center agents to deliver superior customer experiences from day 1. To further improve customer service with generative AI, the company is planning a proof of concept with Amazon Q in Connect, which delivers agents the responses, actions, and information they need to solve issues in real time.

Having experienced steady business growth, BPC is looking to expand into Middle Eastern and North African markets. To support this global expansion, the company is experimenting with AWS Outposts, which organizations use to run AWS infrastructure and services on premises for a truly consistent hybrid experience. “AWS helps our business operations and growth,” says Tochilkin. “We recognize value in AWS technology and AI services.”

About BPC

BPC shapes transactions with quick, safe, and easy payment processing. Focused on technology and customer service, BPC helps more than 450 clients in 120 countries deliver innovative solutions in banking, payments, commerce, and mobility industries.

AWS Services Used

Amazon Bedrock

Amazon Bedrock is a fully managed service that provides a single API to access and utilize various high-performing foundation models (FMs) from leading AI companies.

Learn more »

Amazon Q Developer

The most capable generative AI–powered assistant for accelerating software development and leveraging companies' internal data.

Learn more »

Amazon SageMaker

Amazon SageMaker is built on Amazon’s two decades of experience developing real-world ML applications, including product recommendations, personalization, intelligent shopping, robotics, and voice-assisted devices.

Learn more »

Amazon Outposts

AWS Outposts is a family of fully managed solutions delivering AWS infrastructure and services to virtually any on-premises or edge location for a truly consistent hybrid experience.

Learn more »

More Financial Services Customer Stories

Showing results: 5-8
Total results: 505

no items found 

  • United States

    Affirm Reduces Manual Security Response Efforts by 50% with AWS Partner Expel

    Affirm is a payment network that empowers consumers and helps merchants drive growth through flexible and transparent financing options. The company wanted to streamline its security operations program to address manual triage, decentralized tooling, and increasing alert fatigue. AWS Partner Expel offered a managed detection and response (MDR) service that integrated seamlessly with Affirm’s Amazon Web Services (AWS) environment. Expel MDRTM centralizes monitoring, automates routine tasks, and enhances detection and response workflows Expel reduced the volume of security alerts fielded by engineers by 50 percent and helped Affirm scale the foundations of its security operations program efficiently.

    2025
  • United States

    MarketReader Launches Its Real-Time Market Analysis Platform and AI Newsletter in Eight Months Using Nasdaq® and AWS

    MarketReader is an artificial intelligence (AI) analytics platform providing the financial sector with data-driven explanations of real-time asset movement. During development, MarketReader experienced delays in data delivery and received incomplete datasets from its initial data provider—which reduced the quality of the platform’s insights. To launch its differentiated product, the MarketReader team moved to cloud-based data solutions from AWS Partner Nasdaq, hosted on Amazon Web Services (AWS), to obtain direct access to high-quality, real-time market data for all US-listed securities. This approach elevated MarketReader’s US market coverage, increased data delivery time by 98 percent, and helped the platform go live within eight months. MarketReader now delivers timely, accurate insights. It publishes a daily newsletter in only seven minutes, driving customer engagement and expanding the newsletter’s reach up to 400 percent beyond MarketReader’s current client base.

    2025
  • United States

    Reducing Costs by 90% and Improving Scalability Using Amazon DynamoDB with Venmo

    Learn how Venmo in the financial services industry modernized its architecture with a purpose-built scaling solution using Amazon DynamoDB.
    2024
  • Australia

    Transforming the developer experience with Amazon Q

    Steve Day, Chief Technology Officer at NAB shares how the bank is using Amazon Q Developer to boost developer productivity and reimagine the future of the developer experience.
    2024
1 127

Get Started

Organizations of all sizes across all industries are transforming their businesses and delivering on their missions every day using AWS. Contact our experts and start your own AWS journey today.