How AgentFlo built AI sales agents with Amazon Bedrock AgentCore – Part 1

Summary

AgentFlo built autonomous AI sales agents to address cart abandonment, unassisted messaging channels, and severe traffic spikes across eCommerce platforms. The system uses the Strands Agents SDK alongside Amazon Bedrock AgentCore to manage intent, recommend products, and execute transactions. Incoming customer communications pass through AWS Fargate before entering AgentCore runtime, which executes model-driven agents inside isolated microVMs with stateful sessions lasting up to eight hours. Tool execution is brokered separately through AgentCore Gateway to ensure operations like cart modifications scale independently from model reasoning. This deployment model enables merchants to launch specialized conversational agents in minutes without pre-provisioning capacity or maintaining custom container configurations.

Takeaways

1. 1

   Strands Agents SDK employs a model-driven architecture where tools are Python functions and the model orchestrates flows without rigid state machines.

2. 2

   Amazon Bedrock AgentCore runtime isolates customer sessions in microVMs, maintaining persistent state and local filesystem caching for up to eight hours.

3. 3

   AgentCore Gateway decouples tool execution from agent reasoning, ensuring cart and catalog operations scale without throttling model loops.