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 chat panel. Reviewing a long document there means scrolling, quoting passages back to the agent, and losing track of which point each remark referred to.
What you will need
- VS Code 1.95 or newer, or a compatible editor such as Cursor, Windsurf or VSCodium
- An AI agent that supports MCP and skills (this guide was tested with Cursor, Codex and GitHub Copilot)
- Node.js available as
nodein yourPATH
Step 1: Install and connect the extension
Install AI Artifacts from the VS Code Marketplace or Open VSX. The extension communicates with your agent through the Model Context Protocol (MCP) and a small skill that defines how documents are created and updated.
- Open the Command Palette (
Ctrl+Shift+P/Cmd+Shift+P) and run AI Artifacts: Install All Detected Integrations. This configures every supported client found on the machine and leaves other MCP settings unchanged. Client-specific installers are also available for GitHub Copilot, Cursor and Codex. - Run Developer: Reload Window.
- Restart your AI chat extension or agent, then start a new chat. A chat that was already open cannot load tools installed after it started.
- Run AI Artifacts: Verify All Integrations. The skill and the base runtime should both report Ready.
Step 2: Ask the agent to create an artifact
The agent creates a review document only when it is asked to. A request for "a plan" on its own produces a plan in the chat. Include the word artifact in the prompt:
Create a dummy plan with: a mermaid diagram, a comparison table, code blocks,
a task list, and open questions. Create an artifact for me to review.
You can also name the skill directly: create-review-artifact (in Codex, $create-review-artifact).
The review editor opens in your IDE automatically. If it does not, run AI Artifacts: Open Artifact Review from the Command Palette. When several VS Code windows are open, the artifact opens in the focused window.
Step 3: Review the document with inline comments
Read the plan as a document. Select any paragraph, heading, list item, quote, code block or table cell, type a comment in the popover, and press Enter to save it (Shift+Enter inserts a new line). Saved comments are listed in the Comments drawer, and the Review button shows how many are pending.
In the example plan, four comments were left:
- Interface sketch: add more detail.
- Tasks: add more detail.
- Acceptance criteria: delete the section, which is unnecessary for a feature this small.
- Rollback: delete the section for the same reason.
Comments can also be questions, such as asking why a particular approach was chosen.
Step 4: Submit the review
Four decisions are available in the editor header:
- Review sends all saved comments to the agent and starts the next round. It requires at least one comment.
- Proceed approves the document. For a plan, the agent begins carrying it out immediately.
- Just save ends the review without executing anything. It suits cases where you only want to keep an idea: the agent saves the document to a file so you do not have to copy it manually.
- Copy Markdown copies the raw text to the clipboard without changing anything.
The example plan still needed changes, so Review is the correct choice. The agent acknowledges the comments in the chat, summarizes what it is applying, and opens round 2.
Step 5: Verify round 2
The agent answers questions in the chat and revises the document only where changes were requested. If a review contains only questions, the document stays byte-for-byte identical and the round still advances.
Round 1 of the example, with four comments saved:
Round 2, after the agent applied them:
The task list grew from 7 items to 11 with more concrete steps, the API example gained its response, and the two sections flagged for deletion were removed. The review can continue for as many rounds as needed, ending with Proceed or Just save.
Step 6: Resume a review
An artifact remains available after its editor tab is closed or the chat ends, so a review can be resumed without starting over.
In the same chat, ask the agent to reopen the artifact.
In a new chat:
- Run AI Artifacts: Search Artifact from the Command Palette and type part of the title.
- Select the artifact to open it in the review editor.
- Click Connect in the editor header. This copies a prompt that points to that exact artifact.
- Paste the prompt into the new chat.
The agent reads the saved state and reports the current review round. Reconnecting never repeats an action that was already approved.
Step 7: Use artifacts for write-ups as well
The same workflow applies to documents written after the work is done. For example, after completing a feature:
Create an artifact describing the workaround we used for the date-parsing
bug and its trade-offs, so I can review it.
Use Just save when the document only needs to be kept for later.
Before you start
- The extension supports the local desktop VS Code. Remote SSH, WSL, dev containers and Codespaces are not supported yet.
- Artifacts are stored locally in
~/.ai-artifacts/and are deleted automatically after 30 days by default (setting:agentPlus.artifactRetentionDays). Use Just save or Copy Markdown to keep a document. - After updating the extension, re-run the installer and restart your AI client before starting a new chat.
Links
Feedback is welcome in the comments or as an issue on GitHub. Please include the editor and agent you are using.
Top comments (0)