Skip to main content

Overview

The Slack Agent Node provides an intelligent agent for interacting with Slack workspaces. This node enables you to:
  • Read conversation history from channels and DMs
  • Send messages to channels or users
  • Search messages across your workspace
  • Get channel and user information
  • Post threaded replies
  • Manage message formatting with blocks

Configuration Parameters

To set up the Slack Agent Node, you need to authenticate with your Slack workspace. Once authenticated, configure the agent to perform messaging operations.

Node Configuration

  • Prompt: Define the task for the agent to perform with Slack.
    Get the last 20 messages from #general channel and summarize the discussion
    Send a message to #announcements channel with project update
    Search for messages mentioning “bug fix” in the past week
    Read messages from channel {channel_id} and reply to the most recent one
  • Tools Select which tools the Slack Agent can use:
    Tool nameDescription
    Get Conversation HistoryRead messages from channels/DMs
    Post MessageSend messages to channels or users
    Get Channel InfoGet channel details and metadata
    List ChannelsList all available channels
    Get User InfoGet user profile information
    Search MessagesSearch across workspace messages
    Post ReplyReply to messages in threads
    Be careful with Post Message - enable only when the agent should send messages
  • System Prompt: Customize the agent’s behavior and guidelines.
  • Model: Select the language model for the agent (must support function calling).
  • Max Steps: Set the maximum number of steps the agent can take (1-20).
  • Enable Model Fallbacks: Allow automatic fallback to alternative models if the primary model fails.

Expected Inputs and Outputs

  • Inputs:
    • The node accepts text input that can be referenced in the prompt, typically channel IDs or message content.
  • Outputs:
    • output: The final result from the agent’s actions
    • conversation: Detailed log of the agent’s reasoning and operations

Use Case Examples

  1. Automated Notifications: Send workflow results, alerts, or reports to specific Slack channels automatically.
  2. Message Analysis: Read and analyze channel conversations, extract action items, or summarize discussions.
  3. Interactive Workflows: Create workflows that respond to Slack messages, answer questions, or provide information on demand.

Error Handling and Troubleshooting

  • Authentication Issues: Ensure you’ve connected your Slack workspace and granted the necessary bot permissions (channels:read, chat:write, etc.).
  • Channel Not Found: Verify channel IDs are correct and the bot has been invited to private channels.
  • Permission Errors: Check that your Slack bot has the required scopes for the operations you’re performing.
If you encounter any issues not covered in this documentation, please reach out to our support team for assistance.

Relevant Nodes