Salesforce Launches Slack Code, Bringing AI Coding Agents Into Team Chat Channels
Slack's new Slack Code feature moves AI coding agents out of private terminals into shared, self-archiving team channels, launching with Anthropic, Cognition, GitHub, and Vercel.
Overview
Salesforce’s Slack introduced Slack Code on August 20, 2026, a feature that moves AI coding agents out of private terminals and browser tabs and into dedicated, shared “code channels” that the whole team can watch and steer, according to Slack. The feature launches with integrations from Anthropic, Cognition, GitHub, OpenAI, and Vercel, per Slack.
What We Know
Tagging a coding agent in a Slack conversation spins up a code channel, a dedicated space that “shapes itself around the work,” surfacing artifacts such as code diffs, planning docs, or a live HTML preview for the whole team to see, according to Slack. When a task wraps up, the channel archives itself automatically while remaining searchable “like an audit log in Slack for future reference,” per Slack. The Register describes the same mechanic: tagging an agent lets people “follow what it’s doing, review its proposed changes, view live HTML previews, and tell it to change course when needed.”
Slack Code is live at launch for Claude (Anthropic), Devin (Cognition), and GitHub Copilot integrations, along with Vercel, while OpenAI’s ChatGPT integration is “available soon” rather than active immediately, according to Slack. Slack says the feature inherits its existing permissions and admin controls, so higher-stakes changes such as production pushes can be routed to a person for approval rather than requiring a separate management layer, per Slack. Internally, Slack says more than 70% of its own code channels “spin up and close within a single day, from idea to merged PR,” according to Slack.
GitHub Chief Product Officer Mario Rodriguez framed the integration as part of a broader shift in how developers work with agents: “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,” he said, according to Slack.
Slack Chief Marketing Officer Ryan Gavin told SiliconANGLE that solo agent use limits the payoff of AI coding: “All this individual work is a solo player sport. The knowledge and the speed at which you’re acting as an individual stays with you as an individual, and you’re not getting an exponential return for the organization.” Valoir Research Chief Executive Rebecca Wettemann told SiliconANGLE that “for companies to unlock the full value from AI, it has to move beyond individual productivity gains to operational transformation,” adding that “Slack Code enables AI to move beyond individual copilots to embedded, contextual AI orchestration.”
The Register reports that Slack calls the approach “multiplayer AI” and describes the workflow it enables as “No ticket, no meeting, no waiting – just a fix, shipped.” Beyond code channels, Slack is also rolling out an “Add to Slack” option for deploying third-party agents in a few clicks, per The Register, alongside a new Agents & Tools tab described by Slack as a “home base for managing agent conversations across threads, DMs, and code channels.” Slack also says the collaborative model will eventually extend “beyond code, stretching into marketing campaigns, legal contract reviews, IT onboarding, and every corner of your business,” according to Slack.
What We Don’t Know
Accounts differ on how broadly Slack Code is available. SiliconANGLE reported that Salesforce said the feature is available “using any Slack plan,” while The Register noted that Slack’s own announcement “doesn’t spell out which Slack plans have access, how broadly the feature is being rolled out, or which of the named coding-agent integrations are available at launch,” and said it had asked Slack for clarification. Neither the company’s announcement nor either outlet’s coverage specifies pricing for Slack Code usage or details how token or compute costs for the underlying agents are billed to customers.
Analysis
Slack Code arrives as coding agents increasingly compete on where developers do their work rather than purely on model quality, with rivals racing to embed agents directly into IDEs, terminals, and now team chat. By opening at launch with agents from four separate AI vendors plus its own GitHub sibling, Slack is positioning code channels as a neutral meeting point for competing coding agents rather than a proprietary alternative to any one of them — a bet that the interface where a team reviews and steers agent work will matter as much as which agent is doing that work.