Urgent.News

What's breaking now, across thousands of outlets.

Editions

AI

Slack Code taps into collective vibe, puts AI agents into the group chat

Developers can now invite the whole team along for their quality time with the coding bot

Slack Code taps into collective vibe, puts AI agents into the group chat

Slack has launched Slack Code, an AI-powered coding assistant that operates within team chat channels for the benefit of all users to observe. This tool, developed by the Salesforce-owned Slack, aims to bring AI coding agents into the group chat, allowing for real-time collaboration and visibility. Slack Code creates dedicated project channels for coding agents, enabling team members to follow the agent's progress, review proposed changes, and even request modifications if necessary.

Once the coding task is complete, the channel automatically archives itself, leaving behind a searchable record of the work done. This feature is not limited to developers; product managers, designers, and other team members can also participate without needing to code or use specialized tools. Slack emphasizes that human oversight remains essential, with the ability to pause, redirect, or halt the agent's actions.

Higher-stakes actions, like pushing code to production, require expert approval. Slack plans to integrate with various AI coding agents from companies such as Anthropic, Cognition, GitHub, OpenAI, and Vercel. These agents will be able to handle tasks beyond software development, including marketing and legal document review. Slack has also introduced DMs for agents and an Agents tab to easily manage and interact with them.

This new feature, along with other AI-assisted tools, aims to bring AI coding assistants into the collaborative workspace, making the process more transparent and efficient. Slack Code is currently available to users, but the specifics of access and rollout remain undisclosed.

Written by urgent.news from The Register'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 theregister.com →

More in AI

acc vs acc_norm: Why Length Bias Skews LLM Eval Scores

Your fine-tune gains three points of acc_norm on HellaSwag and loses two points of acc . Same checkpoint, same harness, same seed.

  • "acc" measures highest summed log-likelihood of candidate continuation
  • "accnorm" divides sum by byte length of continuation string
  • Length bias can skew LLM evaluation scores significantly

More from Thursday 20 August →