Slack Code brings AI coding agents into team channels
Slack launched Slack Code on August 21, 2026, a product that drops AI coding agents directly into dedicated Slack channels so entire teams can watch, steer, review, and ship software together in one place.
What’s in the product
At launch, Slack Code supports four agents: Anthropic’s Claude Code, Cognition’s Devin, GitHub Copilot, and Vercel’s agent. Teams get code diffs, live previews, and a plan view in dedicated tabs inside the channel. Engineers, product managers, and designers can all contribute in the same thread.
New interface pieces ship alongside it: agent DMs that work like normal conversations, an Agents tab for managing active sessions, and an automated deployment flow for connecting agents from external platforms.
Access and pricing
Slack Code is available on any Slack plan from day one. You’ll need your own access to whichever partner agent you want to use. It’s available now, not gated behind a waitlist.
The numbers Cognition shared
Cognition reported that internal merged pull request counts rose tenfold in recent months despite only a 40% increase in headcount. That figure came from Cognition’s own team, so read it as a vendor data point rather than an independent benchmark.
NanoClaw: a related launch the same week
One day earlier, on August 20, 2026, NanoCo launched the NanoClaw Slack integration. It lets users spin up entire teams of AI agents from a single Slack message. NanoCo CEO Gavriel Cohen put a stake in the ground:
“In the next 12 to 18 months, everyone on a team will be a manager of agents.”
NanoClaw stores agents’ Slack tokens locally on the user’s machine rather than on NanoCo’s servers. Once authorized, the first agent is ready to interact immediately.
The operator angle
If your small team already lives in Slack, the pitch here is straightforward: you get AI coding output visible to everyone who needs to review it, without context switching to a separate tool. Slack’s interim CEO Rob Seaman framed the shift directly:
“Code is no longer the bottleneck.”
The open question is quality control. Slack’s answer is transparency: if the whole team can see what an agent is producing in real time, bad output gets caught before it merges. Whether that holds up at scale is still unproven.
I’m founder of BizStack at Cagri Sarigoz LLC and a passionate advocate for entrepreneurs.
With over 14 years in tech, marketing, and AI, including my role as Head of SEO at CitizenShipper and co-founder of TaleBot at Intale AI, I’m dedicated to sharing genuine, useful product insights and tips.
At BizStack, I aim to cut through the digital noise to provide clear, actionable advice.
And more than all else, I’m a father to a (always) little girl and a husband.
Contact me at [email protected] for assistance.
