AI in Slack overview
Slack provides a set of tools, APIs, and platform features for bringing AI-powered experiences into the flow of work.
Build agents
Agents are autonomous, goal-oriented AI apps that can reason, use tools, and maintain context across conversations in Slack. They go beyond simple Q&A bots by planning actions, calling external systems, and iterating on results without constant human intervention.
Slack offers dedicated surfaces for agents, including a split-view container, top navigation entry point, app threads, text streaming, and suggested prompts. Use these alongside design best practices around trust, transparency, and bounded autonomy to build agents that feel native to Slack.
Build with AI
Bring AI into your Slack app building journey and lean on tools, skills, and plugins to move faster.
- AI-assisted development gives your AI coding assistant, IDE, or chat-based LLM better context about the Slack platform.
- Vercel's Slack Agent Skill walks you through building, testing, and deploying a Slack agent on Vercel.
- The OpenClaw Slack Plugin connects an OpenClaw agent to your workspace.
- The Slack MCP and Skills Plugin bundles skills that help you develop on the Slack platform with Claude Code and Cursor.
Connect Slack and AI with MCP
Model Context Protocol (MCP) is an open standard that gives AI a consistent, secure way to discover and use external tools and data. Slack offers two ways to work with it:
- The Slackbot MCP Client connects remote MCP servers to Slack. Once connected, Slackbot discovers your server's tools and invokes them based on user prompts in conversation.
- The Slack MCP Server lets AI apps search channels, send messages, manage canvases, and perform other Slack actions through any MCP-compatible client. Connect it to clients like Cursor and Claude.
Integrate AI in other ways
AI doesn't have to only live in an agent. You can bring AI capabilities into Slack through workflow automations and Salesforce Agentforce.
