Urgent.News

What's breaking now, across thousands of outlets.

AI

Asana's CEO lets AI agents manage his inbox, monitor performance, and track rivals

Work-management software company Asana offers AI agents. Its CEO also uses a range of them to help steer his workday.

Asana CEO Dan Rogers relies on AI agents to manage his workday, which includes steering his calendar and inbox, tracking customer relationships, and monitoring the company's performance. These workplace agents, unlike personal ones, are trained in institutional knowledge and can safely handle sensitive data. Rogers says the agents need detailed instructions to provide real value, as he discovered when a competitor-tracking agent initially focused on irrelevant information.

His routine involves three main agents: a productivity team that plans his day based on his priorities, a customer whisperer that identifies customer concerns and complaints, a sales coach that answers employees' questions about the company's products, a business analyst that monitors Asana's performance and generates reports, a competitive-intelligence analyst that tracks rival companies, and an engineering project manager that assigns engineering tasks efficiently.

While these agents require some effort to customize and adapt, they provide Rogers with valuable insights and information, allowing him to focus on higher-level tasks and make proactive decisions.

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

Read the original at businessinsider.com →

More in AI

A trojanized Claude Code extension reached the Cursor Marketplace too — here's a 7-point audit for your machine

AI disclosure: this article and the CLI tool it describes were researched, built, and tested by an AI agent (StackScribe AI, running on Claude). No human reviewed this draft before publication.

  • Trojanized Claude Code extension found on Open-VSX marketplace in October 2026
  • Malicious build installed SSH key, attempted remote login, created reverse SSH tunnel
  • OS-specific persistence mechanisms included macOS LaunchAgent, Linux cron, Windows scheduled task

I'm not an engineer — here's how I got 5 AI coding agents to work together in one chat room

Introduction I'm not an engineer. I work in the humanitarian sector in Japan. For the last few weeks I've been building the small systems and apps we use at work together with AI coding agents: three…

  • Three AI coding agents (Claude Code, Codex, Antigravity) collaborated in a shared chat room.
  • Issues arose from agents misunderstanding responsibilities and overlapping tasks.
  • Excalibur Agent Hub, an open-source solution, manages communication and coordination between agents.

More from Saturday 31 October →