New Codex features include the ability to use your computer in the background

2026-04-16 · Source: AI - Ars Technica · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Intermediate, quick

Summary

OpenAI has released a new version of its Codex desktop app on April 16, 2026, introducing significant features aimed at both developers and general knowledge workers. Key updates include the ability for Codex to perform tasks on a user's PC in the background, utilizing its own cursor to interact with applications without interrupting the user's work. This background capability also allows for scheduling tasks hours, days, or weeks in advance. Additionally, the app now features an in-app web browser for visual feedback on web development, enabling users to leave comments on specific page elements. Software development enhancements include running multiple terminal tabs and acting on GitHub review comments, complemented by 90 new plugins expanding its utility beyond coding into general knowledge work. These changes are part of OpenAI's strategy to evolve Codex into a "super app" that integrates various agentic tools.

Key takeaway

For AI Product Managers evaluating developer tools or agentic platforms, the new Codex features signal a shift towards more autonomous, integrated AI assistants. You should consider how background task execution and an in-app browser could streamline development workflows and expand AI's role in non-developer knowledge work. Explore the new plugins and the potential for Codex to act as a foundational component for broader "super app" strategies within your organization.

Key insights

OpenAI's updated Codex app introduces background task execution and an in-app browser, advancing its "super app" vision.

Principles

• Parallel agentic operation without user interference.
• Iterative development of a "super app" from existing tools.

Method

Codex agents use a dedicated cursor for background interaction with desktop applications, enabling parallel task execution and scheduled operations, while an in-app browser facilitates visual feedback and collaboration.

In practice

• Automate frontend changes and app testing in the background.
• Schedule tasks for later execution by Codex.
• Provide visual feedback on web mockups via in-app browser.

Topics

• OpenAI Codex
• Background Computer Use
• In-App Web Browser
• Software Development
• AI Agents

Best for: AI Product Manager, AI Engineer, Software Engineer, Director of AI/ML

Related on AIssential

• OpenAI Codex Can Now Use Your Computer! (Full Breakdown + Testing) — OpenAI's Codex is an evolving AI agent designed for non-technical users, excelling in browser and computer control.
• The Codex App Has Upended My Daily Workflow — The Codex app transforms coding into managing AI agents, enabling parallel work and sustained context through a desktop interface.
• OpenAI's Codex update lets agents build interactive enterprise workspaces via Sites and role-specific plugins — Codex's update transforms it into an agentic AI operating environment for business, enabling precise automation and interactive app creation.
• OpenAI's superapp hiding inside Codex — OpenAI is evolving Codex into a "superapp" with expanded agentic capabilities, while Anthropic's Opus 4.7 advances coding performance.
• OpenAI expands Codex with role-specific plugins to build a general-purpose app for non-developers — OpenAI is transforming Codex into a general-purpose, role-specific AI work app, expanding beyond coding for non-developers.
• OpenAI Boosts Codex's Core Functionality — OpenAI's Codex updates enhance desktop control and multi-agent capabilities, directly challenging Anthropic's offerings.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by AI - Ars Technica.