Slack launches code channels for AI software teams

Slack has launched Slack Code, a feature that lets teams and AI coding agents collaborate in dedicated code channels. The product is designed to move software development into shared spaces within Slack.

The launch adds a new workspace for software projects, where teams can ask an agent to start a coding session, then review code changes, inspect live previews and approve work without leaving the platform. Channels are created for individual projects and archive automatically when the task is complete, while keeping a searchable record.

The move reflects a broader shift in software development as companies try to integrate AI coding tools into day-to-day teamwork rather than leave them as one-to-one tools in separate browser tabs. Slack is positioning the product as a way to make that work visible to a wider group, including product managers, designers and other non-technical staff.

Users can trigger a code channel by tagging a coding agent such as Claude, ChatGPT, Devin, GitHub Copilot or Vercel agents from an existing conversation. Once the channel is live, participants can follow the planning discussion, view code diffs and see the output running in a preview tab.

Code channels are meant to keep complex development work out of standard message threads, which can become hard to follow when an AI agent is producing multiple rounds of output. By separating that activity into its own workspace, Slack aims to preserve the surrounding business context while making the development process easier for teams to monitor.

Team workflow

The product also expands Slack's approach to AI agents beyond coding. It introduced an agents tab for tracking agent sessions and managing their status, along with changes to direct messages so conversations with agents more closely resemble exchanges with human colleagues.

People can also add agents built on third-party platforms including NanoClaw, Lovable, Hyperagent, Superhuman, n8n, Vercel, ChatGPT, LangChain, Runlayer and Skydive. Slack has automated steps such as OAuth, manifest setup and environment configuration to simplify deployment inside the platform.

Security and oversight are central to the pitch. Slack says agents in code channels inherit the platform's existing permissions and administrative controls, and tasks such as pushing code to production still require human sign-off in the channel.

Rob Seaman, EVP and GM of Slack at Salesforce, described the rationale behind the launch in operational terms. "AI only creates value when it's part of how a team actually works, not something people go 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," Seaman said.

Slack is also leaning on its partner network to support the rollout. Anthropic, Cognition, GitHub, ChatGPT and Vercel are among the organisations developing for Slack Code through its code channel application interfaces, according to the company.

That backing matters because competition in AI-assisted software development is increasingly tied not only to model performance but also to where the work happens. Major software vendors are trying to embed coding agents into collaboration tools, developer environments and workflow systems to capture more of the development process.

Partner support

Several partners framed the new feature as a way to bring coding activity closer to the team discussion that often starts it. "So much engineering work already starts as a conversation in Slack with Claude Tag: a bug report, a piece of feedback, a 'what do you think about...' Slack Code gives teams a dedicated channel where the people, the context, and Claude work together from the start. Review the code diff and see a live HTML preview right in the channel, without anyone leaving the conversation," said Cat Wu, Head of Claude Product, Anthropic.

Cognition focused on how autonomous agents fit into team communication. "Agents earn their place on a team the same way people do, by knowing when to contribute and when to stay out of the way. With code channels Devin responds in Slack autonomously, verifies its work by running end-to-end in cloud agents, and brings the right people together without cluttering the conversation," said Wang.

GitHub linked the launch to its effort to put Copilot into more collaborative settings. "Slack is a strategic part of a broader GitHub promise: humans set direction, agents close the loop. That has to be true wherever developers are working, which is why we're bringing Copilot into the flow of conversation in code channels to help teams turn shared intent into shippable software," said Mario Rodriguez, Chief Product Officer, GitHub.

Vercel's Malte Ubl pointed to the way coding sessions have expanded beyond quick exchanges. "Slack is already where our teams collaborate, and Code Channels bring that same collaboration into how we work with agents. A thread is great for a quick back-and-forth, but the work with an agent has gotten valuable and complex enough that it deserves its own space. A whole team can gather in one Code Channel, watch the agent work, steer it together, and ship a preview, with all the context and history staying in one shared place. It turns building software from something that happens in one person's local session into something the whole team does together," Ubl said.