Banco Bradesco Streamlines Customer Service with Azure AI Foundry, Apps, and Databases

Overview

Banco Bradesco, co-developing with Microsoft and Avanade, built Bridge, a multi-agent, technology-agnostic generative AI platform based on Azure OpenAI in Foundry Models, with governance standardized through Azure Red Hat OpenShift and Azure API Management for deployment and scaling. Bridge powers BIA for Customers and BIA Corporate virtual assistants across phone, chat and WhatsApp for roughly 74 million customers. Results include an 83% resolution rate for digital customer service, 80% for employee queries, 89% request retention, a more than 30% reduction in technology costs, product launches up to 10x faster, an 8x productivity increase in managerial efficiency, and a 65% efficiency gain in audit planning. Azure Cosmos DB processes more than two million requests and two billion inference tokens daily. The bank runs 10 large language models and at least 20 use cases in production, including MentorIA, which automates analysis of more than 18,000 collections calls per day.

The challenge

In Brazil's financial sector, regulations keep growing more complex, fraud and cyber threats are on the rise, and banks must race to meet the service expectations of digital-native consumers. Complex approval flows and technical barriers slowed the release of new solutions at Bradesco, while manual, repetitive tasks and decentralized information limited employees' focus on strategic tasks.

The solution

Bradesco partnered with Microsoft and Avanade to co-develop Bridge, a multi-agent, technology-agnostic generative AI platform built on Azure OpenAI in Foundry Models. Governance is standardized through Azure Red Hat OpenShift, with Azure API Management enabling rapid deployment and scaling across channels. Bridge incorporates the bank's BIA for Customers and BIA Corporate virtual assistants, serving phone, chat and WhatsApp channels, and non-technical teams use Bridge with Microsoft Power Platform to create and manage their own specialized agents. Azure Cosmos DB provides reliable access to current information for BIA Corporate, and Azure Redis Cache enhances performance across the AI-powered services.

Reported business value

BIA for Customers achieved an 83 percent resolution rate serving roughly 74 million customers, and BIA Corporate reached an 80 percent resolution rate for employee queries, lifting the Net Promoter Score by six points. Requests were retained (resolved without escalation) 89 percent of the time. The source describes automation and orchestration as driving both a more than 30 percent reduction in technology costs and, elsewhere, a more than 30 percent increase in productivity compared with legacy solutions, with product launches up to 10 times faster. Generative AI tools drove an 8x productivity increase in managerial efficiency, and the internal Audit Intelligent Learning Assistant delivered a 65 percent efficiency gain in audit planning. MentorIA automates analysis of more than 18,000 collections calls per day, driving an increase in conversion of more than 22 percent. Azure Cosmos DB processes more than two million requests and two billion inference tokens daily. The bank runs 10 large language models across more than 400 experiments and at least 20 use cases in production.