Build unified intelligence with Amazon Bedrock AgentCore

Building cohesive and unified customer intelligence across your organization starts with reducing the friction your sales representatives face when toggling between Salesforce, support tickets, and Amazon Redshift. A sales representative preparing for a customer meeting might spend hours clicking through several different dashboards—product recommendations, engagement metrics, revenue analytics, etc. – before developing a complete picture of the customer’s situation. At AWS, our sales organization experienced this firsthand as we scaled globally. We needed a way to unify siloed customer data across metrics databases, document repositories, and external industry sources – without building complex custom orchestration infrastructure.

We built the Customer Agent & Knowledge Engine (CAKE), a customer centric chat agent using Amazon Bedrock AgentCore to solve this challenge. CAKE coordinates specialized retriever tools – querying knowledge graphs in Amazon Neptune, metrics in Amazon DynamoDB, documents in Amazon OpenSearch Service, and external market data using a web search API, along with security ...