Urgent.News

What's breaking now, across thousands of outlets.

Editions

AI

New ‘Slack Code’ turns AI coding into a team activity

With the launch of “Slack Code” channels, Slack this week introduced a new way for developers and non-tech staff to work collaboratively with coding agents . While Slack already integrates with several coding agents , developers have to interact with them independently to get work done. The aim of Slack Code is to make agents available to multiple coworkers in shared, project-based “code…

New ‘Slack Code’ turns AI coding into a team activity

Slack has unveiled "Slack Code," a novel feature enabling developers and non-technical staff to collaborate seamlessly with coding agents. This new capability consolidates coding agents within shared "code channels," facilitating multi-player AI experiences for various project-based tasks such as building applications, updating web pages, and fixing bugs.

Slack product marketing VP Sateja Parulekar explained that the objective is to bring development into Slack, encompassing not just engineers and product managers but also marketers and designers. To initiate a code channel, users tag a coding agent in a Slack channel or DM, which then generates a new channel, incorporates necessary documents, and invites relevant participants.

The channel operates like any standard Slack channel, allowing users to send messages, files, and interact with the agent using natural language commands. Outputs are tracked via session artifacts, including code diffs, Slack canvas documents, and live HTML previews. Once a project concludes, the code channel is automatically archived.

Slack Code integrates four coding agents at launch — Claude Code, Devin, GitHub Copilot, and Vercel — with plans for future expansion. The feature is available at no additional cost on all Slack subscriptions. Industry analysts view Slack Code as a significant advancement, enhancing collaboration and streamlining workflows within the Slack ecosystem.

While some IT professionals grapple with permissions management, the broader vision includes extending this collaborative AI approach across diverse teams and use cases, such as marketing campaigns and legal document reviews.

Written by urgent.news from Computerworld's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

This story

This is one outlet's version. Read the fullest account.

Read the original at computerworld.com →

More in AI

Can EnvHarness Turn Static Worlds Into Real Agent Training Grounds?

Originally published at vinpatel.com What actually happens when a research team says they've made a static world "awake" for agent learning?

  • EnvHarness transforms static data into interactive environments for agents.
  • Paper introduces method but lacks final proof of effectiveness.
  • Success depends on widespread adoption and independent evaluation.

A roadmap for safeguarding against AI bioweapons

AI-enabled bioweapons are a potentially catastrophic yet manageable risk — if government, the scientific community, the public health sector and leading tech companies can develop appropriate safeguards, a new report argues.

More from Friday 21 August →