AI coding is a team sport. Code channels bring software development out of private tabs, allowing teams and agents to write, review, and ship code together in the open.
We are in the middle of a coding boom that is changing how people build and work. Coding agents like Claude Code, Claude Tag, Devin from Cognition, GitHub Copilot, ChatGPT and Vercel agents have made writing and shipping code faster and more accessible. The challenge lies in connecting what you build to your team’s conversations, all within one workspace.
Work that happens between an individual and an agent outside Slack remains invisible to everyone else. Context disappears between conversations and tools, reviews happen late, and every handoff slows the process down. Slack is already where context lives and where your team works with AI. With Slack Code, it becomes where teams code together as well.
Innovative companies figured out early that the best place to build is in the open. They moved development work into Slack because visible work helps knowledge compound. Teams learn faster, move faster, and ship better products. Slack Code brings that same principle to everyone.
Coding agents changed how individuals build, and Slack Code changes how teams build. Fitting complex agent work into standard threads creates clutter, while letting developers retreat into private browser tabs destroys shared context. Slack Code gives your team a dedicated place to work with an agent on a specific coding session or project directly in Slack.
Meet Slack Code
Work happens in the open by default, allowing context and knowledge to carry from person to person and from person to agent. AI development becomes a collaborative activity. Code channels scale for agent work in ways that threads and public channels cannot. What appears is not merely text, but working code, prototypes, and documents built inside Slack.
When you have an idea, need to build a new feature, update a web page, or fix a bug, you tag in a coding agent such as Claude Tag or ChatGPT. The agent spins up a code channel to tackle the task. Everyone in the channel can see the conversation, review code diffs, check live previews, offer feedback, and approve the work before it ships without leaving Slack.
Slack Code brings AI development directly into the platform to alter how we build and work. Code channels are the first space in Slack built specifically for people to collaborate with agents on software development. They are inherently collaborative and accessible to everyone. They bring developers, product managers, designers, and non-technical teammates into the same workspace as the agent. Software development from idea to shipped product is no longer restricted to engineers, and no other platform offers this combination of an open ecosystem and a shared coding environment.
What Slack Code includes
- Project-based code channels: Every code channel maps to one project, staying live when needed and archived when complete.
- Automatic channel creation and archiving: Tag a coding agent from any conversation, and it spins up a code channel. When the task finishes, the channel archives itself while preserving the record as an audit log.
- Full visibility with dedicated tabs: Everyone in the channel can follow the work through separate tabs for conversation, planning, code diffs, and live previews.
- Code diffs: See exactly what changed with old lines struck through and new lines right beside them. It is the review engineers have always relied on, now open to the whole channel rather than buried in a separate tool.
- Previews: Watch the actual HTML output run live so the team can catch broken elements before shipping.
- Flexible APIs: Shape how the agent behaves by auto-provisioning accounts, authenticating users, and automating workflow steps to fit your organisation.
“AI only creates value when it is part of how a team actually works, rather than something people do alone in another tab. Code channels bring that work into the open where the rest of the team can see it, shape it, and build on it.”
— Rob Seaman, EVP and GM of Slack, Salesforce
Everyone becomes a builder
Software development has evolved from solo terminal coding to single-player AI copilots, and now to multiplayer coding with Slack Code. Instead of jumping between tools, teams and agents plan, build, and iterate together in a dedicated workspace.
Consider a product manager who spots a bug report in a channel. Instead of waiting for an engineer, the product manager asks a coding agent to help design a fix. That agent spins up a code channel, reviews the conversational context, screenshots, and documents already shared, and proposes code. The product manager brings in an engineer to check the diff, run the preview, and authorise the agent to open a pull request and merge to production. There is no ticket, no meeting, and no delay.
What changes is who gets to build. Because the work happens in a tool people already use, someone without technical skills can help shape the output without opening a terminal. Anyone in the channel can pause, redirect, or stop the agent if it drifts off track. Once the work finishes, the channel archives itself, keeping the sidebar tidy while the history remains searchable as institutional context.
Powered by an ecosystem of partners
Slack is becoming the natural home for AI agents from our partner network. Anthropic, Cognition, GitHub, ChatGPT, Vercel, and others build in and for Slack Code using our code channel APIs. The agents that developers, product managers, and designers rely on can now tap into shared team context inside Slack.
Software engineering is only the start. Soon these APIs will open to the broader developer community, allowing custom agents handling any task to join a code channel. This applies equally to a marketing team building a campaign or a legal team running a document review. As the partner network grows, Slack Code will become the place where every team builds with AI in the open.
Agents as teammates across Slack
As agents become central to how teams work, the user experience in Slack is evolving so agents feel like regular teammates everywhere.
- Agent Direct Messages: Work like any standard conversation. Agents are clearly labelled, and threads receive clear titles so you can resume a conversation easily.
- The Agents Tab: Gives every agent and session a home base. You can browse agents, view conversations, name them, check status, flag blocked threads, or stop an agent mid-task.
- Add to Slack: Allows anyone to build and ship an agent from NanoClaw, Lovable, Hyperagent, Superhuman, n8n, Vercel, ChatGPT, LangChain, Runlayer, or Skydive in a few clicks. We automated the OAuth, manifest setup, and environment configuration. A support assistant built on Lovable can be added quickly and go live alongside your team with its own identity.
The pattern holds across the workspace. Agents display a clear identity, follow standard channel norms, and answer to the administrative controls IT trusts, whether in a code channel, a direct message, or a project channel.
Built-in trust with human oversight
Agents in code channels inherit Slack’s security model, permissions, and administrative controls from day one without additional IT effort. They function as secure extensions of your existing setup with no new infrastructure to manage.
Speed does not come at the expense of oversight. For high-stakes actions like pushing code to production, the agent packages its work for an expert to sign off directly in the channel. This keeps people in control without delaying work through separate approval channels.
The space for collaborative AI
When a team works with AI in the open, context compounds. Better context leads to better output, making AI more useful for the next person. Slack Code brings building out of isolated terminals and into dedicated code channels, while the broader agent experience makes every agent in Slack feel like a teammate.
This represents a new approach to building software: open, collaborative, and powered by human judgment alongside agent scale. Teams that build this way will move faster and deliver work that was previously out of reach.
Get started with Slack Code today and discover what your team can achieve when agents work directly alongside you.
“For companies to unlock full value from AI, technology must move beyond individual productivity gains to operational transformation. Slack Code enables AI to move beyond individual copilots to embedded, contextual orchestration that delivers real return on investment at scale.”
— Rebecca Wettemann, CEO and Principal Analyst, Valoir Research