Artificial Intelligence1 min read

How LoanPro built an agentic AI loan servicing assistant with Amazon Bedrock AgentCore

By · Published by Everything Blog

In short

Servicing agents previously struggled with operational inefficiencies, having to navigate multiple tabs, transaction records, and workflow queues during live borrower interactions. The newly deployed multi-agent assistant resolves this by supplying contextual borrower data and actionable recommendations in real time. Built using the open-source Strands Agents SDK and Amazon Bedrock, the architecture routes incoming tasks through a central composer to specialized models. This managed framework allows the platform to upgrade and evaluate individual components independently without maintaining an in-house runtime.

Key points

  • Manual data gathering across fragmented tabs and queues had previously led to prolonged c…: Manual data gathering across fragmented tabs and queues had previously led to prolonged calls and inconsistent customer service quality.
  • A central composer directs incoming user requests to specialized modular agents configure…: A central composer directs incoming user requests to specialized modular agents configured for specific loan servicing tasks.
  • The open-source Strands Agents SDK framework enabled the team to build modular agent logi…: The open-source Strands Agents SDK framework enabled the team to build modular agent logic supported entirely by managed services.

Sources checked by our analysis pipeline: 1

Artificial Intelligence

How LoanPro built an agentic AI loan servicing assistant with Amazon Bedrock AgentCore

This post is co-written with Mariah Miller from AWS and Colin Terry from LoanPro

Have you ever wondered what the experience is like for the person on the other end of the phone when you call your bank for support? When a borrower calls a lender, the answering agent must pull account data from dozens of fields, transaction histories, and workflow queues to orient themselves before they can help the borrower. All the while, the clock runs. Assembling that context by hand means longer calls, inconsistent service quality, and agent frustration. A loan servicing assistant built on agentic AI changes that.

LoanPro, the operating system for modern lenders, set out to change that. Working with AWS Partner AllCloud and the AWS Generative AI Innovation Center, LoanPro built a multi-agent AI assistant that gives servicing agents immediate access to synthesized borrower context and actionable next-step recommendations. Early results show customer call times reduced by up to 15 percent, according to AllCloud’s published case study.

In this…

Artificial Intelligence