Urgent.News

What's breaking now, across thousands of outlets.

AI

This extension lets your AI agent create artifacts for plans, workarounds and designs in Cursor, Codex and GitHub Copilot

This guide uses an extension called AI Artifacts to let Cursor, Codex or GitHub Copilot produce a plan, workaround note or design as a separate document, an artifact, inside your IDE. You can comment on exact passages and send all feedback back in a single step. AI coding agents are most useful when they propose a plan before changing code. In practice, that plan usually arrives inside a narrow…

This guide introduces an extension called AI Artifacts that enables AI agents like Cursor, Codex or GitHub Copilot to generate documents such as plans, workarounds or designs within your Integrated Development Environment (IDE). These AI-generated artifacts can be reviewed, commented on and even revised directly within the IDE. The process starts by installing the AI Artifacts extension from the VS Code Marketplace or Open VSX.

The extension communicates with the AI agent through the Model Context Protocol (MCP) and a small skill that defines how documents are created and updated. Once installed, you need to reload your VS Code window and verify all integrations before starting a new chat with the AI agent. To create an artifact, simply prompt the agent to generate a review document using specific requirements such as a mermaid diagram, comparison table, code blocks, task list and open questions.

The review editor will then open in your IDE where you can leave inline comments on various sections of the document. These comments are saved and can be viewed in the Comments drawer. After saving comments, you can submit the review which will send all comments back to the AI agent. The agent will then process these comments and revise the document accordingly.

The artifact remains available even after the chat ends, allowing you to resume the review process later without starting over. This workflow of creating, reviewing, and revising artifacts using AI agents can greatly enhance productivity and collaboration in software development tasks.

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

Read the original at dev.to →

More in AI

Five-Minute Field Notes: a local Gemma card that sends me outdoors

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built Five-Minute Field Notes makes a tiny observation mission for a place I can already access: a park…

  • Five-Minute Field Notes app generates observation missions
  • Users specify duration (5, 10, or 15 minutes) and activity type
  • Local Gemma 3 1B model runs on user's Mac after download

Incognia launches AI agent detection tool

As AI agents begin making purchases, payments and account changes on behalf of consumers, financial institutions face a new challenge: knowing an AI agent is legitimate does not necessarily mean the…

More from Wednesday 7 October →