Add visual feedback to your Replit Agent app

Why Replit Agent teams need visual feedback

• Replit Agent can ship a deployed app fast, but reviewing it across a team still means scattered Slack threads.
• A hosted URL is easy to share, yet there is no way to comment on the deployed page itself.
• Without an element anchor, the agent re-interprets feedback and may regress something that worked.
• Patchrooms keeps every comment pinned to the live deployment and structured for the agent.

How Patchrooms works with Replit Agent

1. Add the script to your Replit app

   Ask Replit Agent to include the Patchrooms embed, or add it yourself. It runs on the hosted preview.

2. Gather feedback on the live deploy

   Reviewers click elements to comment; Patchrooms captures selector, screenshot, and context.

3. Return context to Replit Agent

   Export Markdown and paste it into the agent so it ships a precise fix instead of a guess.

Add it in one prompt

Add in one promptPaste a script tag

Ask Replit Agent to wire Patchrooms in for you, paste this prompt:

Add the Patchrooms review widget. Insert this script tag into the served HTML before the closing </body> tag, exactly as written:

…then give it the snippet below. It loads on the live preview and turns on artifact-review mode: pinpoint comments anchored to the elements your reviewers click.

<script src="https://room.patchrooms.com/v1/patchrooms.js"
        data-project-key="pr_xxx"
        data-source="replit-agent"
        data-mode="artifact-review"></script>

Or try it locally: no account, no key, no server

Reviewing a Replit Agent artifact on your own machine? Run Patchrooms in local mode: no account, no project key, zero network calls. Pinpoint comments stay in your browser and export to Markdown you paste straight back into Replit Agent.

<script src="https://room.patchrooms.com/v1/patchrooms.js"></script>
<script>
  Patchrooms.init({ storage: 'local', mode: 'artifact-review' });
</script>

Review workflow

Share the preview link with your team or client. Anyone clicks an element, types a comment or records a voice note (Patchrooms auto-transcribes it to clean text), and captures the selector, a screenshot, and the page context. Every comment carries a status (new, triaged, in-progress, closed) so nothing falls through the cracks. See the full UI review workflow.

Export feedback to your AI agent

Each report exports as clean Markdown with the element selector, a screenshot reference, and the artifact goal and constraints. Paste it straight into Replit Agent and the agent fixes the exact issue: this is the heart of AI artifact review. The Patchrooms MCP server lets agents read reports directly (list_reports / get_report) and triage them (set_status). Available now; extended MCP tools (create_room, issue creation) are planned, and a @patchrooms/react package is coming for tighter React integration.