💬 Remember per-customer chat history with Amazon Bedrock AgentCore
⚡ 0 views · 💬 Support Chatbots
Description
Quick Overview
This workflow uses the n8n chat trigger and Amazon Bedrock AgentCore to run a support assistant that keeps long-term, per-customer memory across separate chat sessions, then formats the agent response into a safe plain-text reply.
How it works
- Receives each incoming message from the n8n chat interface as a separate execution.
- Sets the agent name, resolves a customer identifier (defaulting to the chat session ID), and passes through the user’s message.
- Sends the message to Amazon Bedrock AgentCore with managed memory enabled, scoping long-term memory by actor ID (customer) and continuity by session ID.
- Parses and normalizes the AgentCore response (including optionally fenced JSON) and returns a plain-text output for the chat.
Setup
- Create and select an Amazon Bedrock AgentCore API credential (AWS access key, secret, region, and execution role ARN).
- Update the customer identifier mapping so
customerIdmatches your real user ID (or keep the default chat session ID for testing). - Optionally customize the AgentCore system prompt and agent name to match your support policy and tone.
🔗 Nodes Used
Chat Trigger
📥 Import
Download workflow.json and import into n8n:
Workflow menu → Import from File