How to Embed an AI Agent in Slack: An AWS CDK + Lambda Template
AWS has walked through a practical integration of Amazon Bedrock AgentCore with Slack. The example uses AWS CDK, three dedicated Lambda functions, and an SQS queue to stay within Slack's response-time limits. The walkthrough also shows how to store conversation context with AgentCore Memory and map sessions to Slack threads. Teams can reuse the same template for other enterprise AI agents.
AI-processed from AWS Machine Learning Blog; edited by Hamidun News
AWS has shown how to embed an AI agent built on Amazon Bedrock AgentCore directly in Slack, so teams don't have to write a new integration from scratch for every agent.
Which AWS services do you need to connect an AI agent to
Slack? The infrastructure layer consists of API Gateway (for Slack webhooks), AWS Lambda (for event processing), Secrets Manager (for token storage), and Amazon SQS (for asynchronous processing). The agent itself runs on Amazon Bedrock AgentCore.
How do you preserve conversation context in a
Slack integration? In this setup, Amazon SQS separates receiving a request from actually processing it. That lets Lambda handle events asynchronously and preserve conversation context.
- Oct 31, 2026Worldwide Express hands disputed invoices to AI agents and cuts unresolved disputes by 75%
- Oct 30, 2026AWS gives coding agents a live site preview straight from an isolated session
- Oct 30, 2026MoEngage Opens 400 Private APIs to AI Agents Through AgentCore Gateway, Without Building Its Own MCP Servers
- Oct 29, 2026NVIDIA Nemotron 3.5 Super VL: 120B Parameters, 12B Active, Running on AWS
Key Questions Answered
Which AWS services do you need to connect an AI agent to Slack?
The infrastructure layer consists of API Gateway (for Slack webhooks), AWS Lambda (for event processing), Secrets Manager (for token storage), and Amazon SQS (for asynchronous processing). The agent itself runs on Amazon Bedrock AgentCore.
How do you preserve conversation context in a Slack integration?
In this setup, Amazon SQS separates receiving a request from actually processing it. That lets Lambda handle events asynchronously and preserve conversation context.
Test Frontier LLMs & Autonomous Agents in One Workspace
Run Claude Opus 5.5, GPT-6, Gemini 3.1, and DeepSeek side-by-side in Nomad AI (nomadnet.ai) — unified model routing, deep research, and multimodal workflows under one subscription.
The AI world, distilled — once a week
Seven stories that actually mattered, hand-picked. No noise, no reposts, no press releases.
Done! Check your inbox for a confirmation.