Slack launched Slack Code on August 20, 2026, introducing dedicated collaborative coding channels where teams can work with AI agents. This new feature aims to integrate AI-assisted coding directly into team workflows, allowing for real-time collaboration and auditing of AI-generated code.
The platform's expansion addresses the growing demand for seamless AI integration within enterprise communication tools. It shifts the paradigm of AI coding from individual assistants to a shared team experience, fostering transparency and collective oversight.
What is Slack Code's core function?
Slack Code's core function is to provide an open, project-specific environment for teams to engage in "vibe-coding" with AI agents, removing the need to switch between disparate tools. These channels offer features for code comparisons and HTML output previews, streamlining the development process before deployment.The new channels include dedicated user tabs, along with tools that compare coding changes. Users can also preview HTML output directly within the channel before projects ship. Slack describes this as an easy way to collaborate with AI agents
These coding channels automatically archive upon assignment completion, creating an audit log for recordkeeping. This approach emphasizes transparency and structured feedback within the development cycle. This model builds on the concept of integrating AI agents into team communication, similar to how Vercel's Chat SDK deploys agents across various platforms from a single codebase (Vercel's Chat SDK Deploys AI Agents Across Slack, Teams, and WhatsApp From One Codebase).When you have an idea or need to build a new feature, update a web page, or fix a bug, you simply tag in a coding agent like Anthropic's Claude or Cognition's Devin, and that agent then spins up a code channel to tackle the task. There, everyone has full visibility to the conversation, can audit code diffs, get live previews of the agent's output, give feedback, and approve the work before it ships.
— Slack, Press Release
How does Slack Code integrate AI agents?
Slack Code seamlessly integrates AI agents available through Slack's marketplace directly into coding channels. This allows teams to leverage powerful AI models like Claude Code, Devin, and GitHub Copilot as active collaborators within their project discussions.
Agents from founding partners, including Anthropic's Claude Code, Cognition's Devin, Vercel Agent, and GitHub Copilot, are designed to work smoothly within these new code channels. This represents a significant push to position AI as an integral part of the team, rather than a standalone tool, as Gizmodo notes about the push for "AI coworkers".
AI Agent | Primary Function | Integration Type |
|---|---|---|
Anthropic's Claude Code | Generative code assistant, bug fixing | Direct channel integration |
Cognition's Devin | Autonomous software engineer, task execution | Dedicated code channels |
Vercel Agent | Front-end development, deployment assistance | Embedded in workflow |
GitHub Copilot | Code completion, suggestion, refactoring | Seamless within Slack Code |
How does this change developer workflow?
This integration fundamentally alters developer workflow by transforming AI agents into visible, auditable team members within a shared communication platform. It enables real-time interaction with AI-generated code, facilitating immediate feedback and collective decision-making, thereby accelerating development cycles.Developers can now directly interact with AI models in a conversational manner. This allows for a more natural integration of AI assistance into daily tasks like building new features, updating web pages, or fixing bugs. The full visibility into the AI's conversation and output ensures transparency, which is crucial for complex projects.
