Trendora
vien

computer use

Trial

Techniques

An agentic interaction capability that lets an AI operate software via GUI actions.

Why it's here

Placed in Trial: 8 article(s) of evidence from 4 source(s), led by product launches, with 2 in the last 30 days. Confidence 75%.

Evidence (8)

  • 6OpenAI Blog·10/6/2026research
    OpenAI and Ironclad train AI agents for contracting workflows

    OpenAI and Ironclad are training and evaluating AI agents on complex contracting workflows. The work is intended to improve computer use for professional tasks by testing how agents handle real business processes.

  • 7The New Stack·10/2/2026product_launch
    GitHub previews Copilot computer use for desktop apps

    GitHub launched computer use in public preview for Copilot CLI and the Copilot desktop app, letting agents interact with macOS and Windows apps by clicking, typing, scrolling, and dragging. GitHub says the feature is best used when no API, terminal command, browser tool, or MCP server is available, and warns that reliability and permission handling depend on the interface and enterprise policy settings.

  • 3Hacker News·8/25/2026framework_update
    How Universities Can Better Prepare Startup Founders

    The piece argues that universities should prepare future founders primarily by teaching them to build things well, especially through fields like computer science, engineering, biology, and design. It also says schools should make startups feel like a normal, achievable path and encourage students to work on their own projects.

  • 7The New Stack·8/21/2026product_launch
    Anthropic adds structured Browser Use for Claude

    Anthropic introduced Browser Use, a browser tool that lets Claude interact with web pages through the accessibility tree instead of screen coordinates. The release also adds support for batching multiple browser actions in one turn and brings Computer Use, Skills API, and Files API to general availability.

  • 4Hacker News·8/1/2026research
    AI Can Speed Up Prototypes, Not Production-Grade Software

    The article argues that AI dramatically shortens the time needed to build a first working prototype, but it does not remove the harder work of making software reliable, secure, scalable, and maintainable. It also says computer science fundamentals remain important because they help developers evaluate AI-generated code and avoid production failures.

  • 4Hacker News·7/18/2026product_launch
    Guide to running Claude Code on a spare Mac

    The article walks through setting up a spare Mac as an isolated machine that Claude Code can fully control, including computer use, while being driven remotely from a main Mac or a phone. The goal is to reduce risk on a primary computer while preserving access to a full macOS environment for research and development tasks.

  • 7Google DeepMind·6/24/2026model_release
    Google DeepMind adds computer use to Gemini 3.5 Flash

    Google DeepMind introduced computer use in Gemini 3.5 Flash, expanding the model’s ability to interact with software through a computer-like interface. The update is aimed at enabling more agentic workflows where the model can operate applications and complete tasks across screens.

  • 7OpenAI Blog·4/16/2026product_launch
    OpenAI updates Codex with computer use and new workflow tools

    OpenAI has updated the Codex app for macOS and Windows with computer use, in-app browsing, image generation, memory, and plugins. The changes are aimed at speeding up developer workflows by letting Codex handle more tasks inside the app.