ToolsThe story, in brief

Building Slack agents can be easy

Not a pilot. Vercel just cut Slack agent deployment from weeks to a single session with Claude Code.

Illustration of independent geometric mechanisms passing paper tasks along branching amber tracks.
AI agents and the coordination of work.AI illustration by KeyNews
The KeyNews take

Why it matters

Vercel's new Slack Agent Skill automates the entire workflow for building and deploying Slack bots—from planning to production—by leveraging coding agents like Claude Code to handle coordination across fragmented systems. This lowers the barrier for teams to build agent-powered workflows without AI expertise.

The key facts

8 to know
  1. Vercel Slack Agent Skill ships with template, wizard, and one-session deployment to production

  2. Works with Claude Code, OpenCode, Cursor, GitHub Copilot and other coding agents

  3. Built-in human-in-the-loop approval gates for sensitive actions; billing only on active CPU time during human wait periods

  4. Includes Workflow DevKit for multi-turn conversations with suspension/resumption across messages and threads

  5. AI Gateway provides model switching across providers with automatic failover

  6. Pre-configured OAuth scopes, event subscriptions, slash commands in manifest template

  7. Includes Vercel Academy course covering full Slack agent lifecycle and Vercel Sandboxes for isolated code execution

  8. Published March 3, 2026

Go to the source

Vercel Blogvercel.com

Publisher excerpt: Slack is already where teams work. It provides a natural interface for agents, with messages, threads, buttons, and events, so you don't need to invent a new UI or onboarding flow. Getting from "I want a Slack agent" to a running deployment, though, means coordinating across a lot of systems: Each…
Read original report
Back to today's editionMore tools news

Keep reading

Related stories

More from Tools