Build a multi-agent support triage system with Amazon Bedrock AgentCore and Slack
UnknownWhat this workflow does
This AI workflow has 10 nodes and runs when a chat message arrives. Along the way it connects Slack and Agentcore (community).
How it runs
Trigger: When a chat message arrives.
- Set Customer Context (Edit Fields (Set)): sets 4 fields: agentName, customerId, question…
- Triage Agent (Agent Core Harness): uses Agent Core Harness
- Read Triage Decision (Code): runs custom JavaScript code
- Route To Specialist (Switch): routes items into 3 branches
- Analysis Specialist (Agent Core Harness): uses Agent Core Harness
- Architecture Specialist (Agent Core Harness): uses Agent Core Harness
- Research Specialist (Agent Core Harness): uses Agent Core Harness
- Format Reply (Code): runs custom JavaScript code
- Post Answer To Slack (Slack): uses Slack
Services it uses
Before you upgrade to n8n 3.0
We can't fully verify this one: it relies on 1 community package, and n8n 3.0 turns unverified community packages off by default (N8N_UNVERIFIED_PACKAGES_ENABLED=false).
- Check that @aws/n8n-nodes-agentcore is verified or supports 3.0 (used in Triage Agent, Analysis Specialist, Architecture Specialist).
Nodes used (6)
- Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Edit Fields (Set)
n8n-nodes-base.set - Agent Core Harness
@aws/n8n-nodes-agentcore.agentCoreHarness - Code
n8n-nodes-base.code - Switch
n8n-nodes-base.switch - Slack
n8n-nodes-base.slack
From the author
Quick Overview This workflow receives an n8n Chat message, uses Amazon Bedrock AgentCore to triage it and route it to one of three specialist agents that share customer memory, then posts the specialist’s reply to a Slack channel. How it works 1. Receives a…