Microsoft supported Bradesco, one of the country’s leading banks, in creating BIA (an acronym for Bradesco Artificial Intelligence) Tech – a customized Artificial Intelligence (AI) copilot tailored to developers’ daily needs. The financial institution has a robust innovation strategy and leveraged all its AI expertise to create a solution focused on development by sharing code through GitHub Copilot and Azure OpenAI Service. The initiatives helped modernize the bank’s internal processes and led to efficiency gains of up to 40% in writing code snippets.
Expanding digital transformation in services used daily by millions of Brazilians is no easy task. To achieve this, Bradesco incorporates the learnings and innovative DNA that gave rise to BIA – an AI assistant launched in 2016 that revolutionized customer service in Brazil – into its innovation strategy. Since the launch of its AI, which now includes generative AI capabilities and allows for quick and accurate document generation, there have been nearly 2.5 billion customer interactions and a wide range of added services, from sending PIX and paying bills to personalized recommendations for products, services, and investments, as well as alerts for suspected transaction fraud.Currently, BIA with generative AI is available to 40,000 employees and over 500,000 customers.
“Bradesco has always invested in innovation and was one of the pioneers in using artificial intelligence in financial services. We’ve accumulated great experiences with BIA efficiently serving our customers and later with BIA Agências assisting our front-line managers in delivering better services and consulting internal regulations. That’s why we wanted to once again harness the full potential of Generative AI to help our developers be more efficient and have time to be more creative and consultive,” explains Nelson Borges, IT Superintendent at Bradesco.
A BIA (Tech) for Developers
With the successful implementation of BIA for both branch employees and external customers, Bradesco once again advances in AI adoption by creating BIA Tech, which leverages the full cloud power of Microsoft Azure and large language models from Azure OpenAI Service to address concrete IT team challenges. The first was supporting the writing of development project instructions.
For a new feature to be introduced, Bradesco’s development team must write ‘stories’ with instructions on what needs to be done by developers. With the strong analytical power of Generative AI, BIA Tech became an important tool for improving the quality of these instructions, breaking each story into smaller guidance parts and highlighting missing elements to make information clearer. Additionally, the team created a plugin to allow developers to interact naturally with BIA Tech integrated into existing tools and develop stories in an assisted manner.
“Everything being planned is based on feedback from Bradesco’s developer teams. Bia Tech already has over 1,500 heavy users, and the teams have recognized the benefits of working with an AI copilot supporting developers’ daily activities.”, highlights Nelson.
According to Bradesco’s technical team, BIA Tech not only alleviated the more bureaucratic work of a project but also increased the quality of produced stories by about 46 percentage points, with an average rating of 8.5 out of 10. This success led the bank’s IT team to expand the AI assistant’s capabilities, which can now help assess code change risks, identify potential vulnerabilities, assist with metrics, and more. The expectation is that BIA Tech will eventually cover all stages of the software development lifecycle.
Nelson adds, “the use of BIA Tech to evaluate incident solutions brought significant gains, such as a 23% reduction in incident analysis time involving root cause identification and solution definition, with 90% accuracy in suggested solutions.”.
BIA Tech with GitHub
Bradesco is also investing in AI solutions combined with automation that can complement and further enhance internal process efficiency, covering the entire development chain. In practice, this is reflected in accelerating ‘Time-To-Market’—the period a product takes from conception to market availability—reducing the time needed for provisioning and configuring infrastructure.
The combined solutions of BIA Tech, GitHub Actions, and GitHub Copilot have automated code management processes, improving process efficiency, team collaboration, and management quality through telemetry and data analysis—contributing to the bank’s product creation.
Currently, GitHub Copilot suggests over 10,000 lines of code per day, with high acceptance by developers. These numbers reflect a significant improvement in software development efficiency, with time savings ranging from 30 to 40% per code snippet.
The goal is to empower employees and provide tools so they can replace repetitive tasks with activities that explore their creative and cognitive potential, ensuring the bank remains at the forefront of technological innovation. The implementation of GitHub, GitHub Copilot, and Bia Tech at Bradesco paves the way for exploring new technologies and innovations. The bank is also experimenting with other AI and automation solutions to further enhance its internal processes.
“What we’ve seen is that using AI within the IT solution cycle can bring considerable productivity gains to engineers, whether in solution creation or operation. Our focus for 2025 will be expanding use cases through open, collaborative, and modern AI architectures focused on multi-agents.”, concludes Nelson.
“Generative AI presents unprecedented potential for financial institutions. It supports teams in daily tasks, generating agility in repetitive processes, assisting technical teams, and simplifying access to internal regulations. This technology is also a great ally in creating data-driven, assertive solutions that meet the specific needs of the bank’s diverse customer profiles.”, comments Joana Moura, Vice President for Corporate Customers at Microsoft Brazil.
