This n8n workflow creates an intelligent Slack chatbot that responds to messages with personalized, context-aware replies. The workflow listens for new messages in a specified Slack channel, filters out non-user messages, and manages conversation context using PostgreSQL for memory storage. When a message is received, it triggers an AI-powered agent that generates a helpful and friendly response, which is then sent back to the user in Slack.

The process begins with a Slack trigger node that detects incoming messages in a specific channel. A condition node checks whether the message is from a user and not the bot itself, filtering out noise. Once validated, the workflow activates a ‘typing’ indicator in Slack to inform users that the bot is processing.

The core component is an AI agent powered by language models, which uses a customizable prompt to generate replies. The conversation history is retrieved from a PostgreSQL database to provide context, ensuring interactions feel natural and coherent. After generating a response, the workflow sends the reply back to Slack with a neatly formatted message.

Practical use cases include customer support bots, interactive Q&A systems, or any scenario where context-aware conversational automation enhances user engagement and efficiency.

Node Count	11 – 20 Nodes
Nodes Used	@n8n/n8n-nodes-langchain.agent, @n8n/n8n-nodes-langchain.lmChatOpenRouter, @n8n/n8n-nodes-langchain.memoryPostgresChat, httpRequest, if, noOp, slack, slackTrigger, stickyNote