Slack has introduced Slack Code, a new feature that brings AI coding agents into shared project channels within Slack, allowing developers, product managers, and other team members to watch, review, and redirect an agent's work in real time.
The feature aims to make the coding process more transparent and collaborative by moving agent work out of isolated terminals and into a group chat, while maintaining human control through pause, redirect, and stop controls—and requiring expert approval for production deployments.
What happened
Slack has introduced Slack Code, a feature that lets AI coding agents work in dedicated project channels where team members can watch, review, and redirect their work in real time. Developers can tag an agent from a conversation to create a code channel; the agent then proposes changes, displays live HTML previews, and team members can pause or stop it before it pushes code to production.
Why it matters
The feature moves AI-assisted coding from isolated developer terminals into a shared workspace, letting product managers, designers, and other non-technical staff see what the agent is doing without learning specialist tools. Slack positions this as a way to compress the development cycle—no ticket, meeting, or waiting—and to give colleagues visibility and veto power before changes ship. For teams using multiple coding agents, this centralizes oversight within Slack's existing permissions and security framework.
What to watch
Integrations from Anthropic (Claude), Cognition (Devin), GitHub (Copilot), OpenAI (ChatGPT), and Vercel are among those named; Slack says the APIs will eventually open to the broader developer community. Slack has not yet disclosed which plan tiers have access, rollout scope, or which integrations are live at launch. Beyond coding, Slack suggests agents could handle marketing work and legal document review.
Ask the AI about this article →
Slack Code represents a shift in how teams manage AI-assisted coding work. Historically, developers invoke coding agents in isolated environments—a terminal, browser window, or IDE—and bring results back for team review only when work is ready to merge. Slack's argument is that this out-of-sight process loses opportunities for early feedback, cross-functional input, and course correction. By embedding agents into Slack's shared channels, the company positions Code as a way to make the process transparent from the start, giving colleagues real-time visibility without requiring them to adopt new tools or understand code syntax.
The feature also consolidates agent management and security. Rather than asking organizations to build separate permission and governance layers for coding agents, Slack Code agents inherit the workspace's existing permissions, security policies, and administrative controls. This reduces friction for IT teams rolling out AI tooling at scale.
The set of named partners—Anthropic, Cognition, GitHub, OpenAI, and Vercel—signals broad industry backing, though Slack has not disclosed which integrations are live at launch or which pricing tiers include access. The announced plan to open APIs to third-party developers suggests Slack sees Code as a platform for agents beyond coding, though concrete use cases (marketing, legal review) remain speculative at this stage.
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytime
Ask AI anything about this article. Q&As are published on this page for other readers too.
Salesforce trades at a P/E of 23 with free cash flow yield of 8.53%, down 21.8% year-to-date, ahead of its fis…
In August 2026, NVIDIA announced memorandums of understanding with KKR and five other global financial institu…
RBC Capital Markets models Nvidia's fiscal Q2 revenue at $91.1 billion and adjusted EPS at $2.06, slightly bel…
HUMAIN, the AI firm of Saudi Arabia's Public Investment Fund, has teased a new laptop developed with chip desi…
Chinese models—Moonshot's Kimi K3, Alibaba's Qwen3.8-Max, and GLM-5.3—have closed the performance gap with Ope…
Researchers at security firm Adversa discovered that Grok can be tricked into stealing user data—including nam…
The AI news that matters, in one minute each morning.
Sign up free