Record your screen, point by drawing and speak, and hand it off to AI agent. Video prompts for Cursor, Claude, and Codex or any AI coding agent — local-only and free.
turning a screen recording straight into a structured prompt cuts out the part where I try to describe a UI bug in words and always leave something out. drawing the arrow while narrating is just faster than writing three sentences to say the same thing
What needs improvement
would like to see it flag when the narration and the drawn annotation don't line up in time, like if I talk about a button before I've actually drawn near it yet
vs Alternatives
compared this to just screenshotting and typing out the bug manually, or using Loom and pasting the transcript in after. both work but both lose the pointing gesture, you end up re-describing where on screen the problem is
You're the first one to review, 🎉 I appreciate you for trying the tool and for the insightful review @omri_ben_shoham1, your suggestion for improvement means a lot. Thank you.
Astra completely shifted XAnnotate from a simple screen recording to a branded title, loom for coding agents, it helped built new features seamlessly, to support windows, optimised local edge AI for lower end devices. implement new features that is important for the product to scale. allowing builders to implement their tasks faster than ever before after AI changed the workflow from basic prompts, to voice prompts and now this screen recording video with transcription prompt.
Hey Product Hunt 👋
I’m the maker of XAnnotate.
The short version: it’s a Free, local-only macOS and windows app that turns screen recordings into agent-ready prompts for Cursor, Claude, Codex, or any AI agent. Think of it as sharing your screen and annotating your thoughts to talk a developer through what to build.
I wrote long, detailed prompts to get better results, but the agent still guessed wrong. Screenshots didn't fix it either, they’re too static to capture workflows, form input flows, or real-time UI feedback.
So I built the exact solution I wanted, I use it on my daily tasks now, and it’s been a game-changer. It saves me so much time, I explain a task once, and it’s done.
How it works:
1. Start Recording: Press Ctrl + Shift + R or click record button.
2. Annotate Your Screen: Press Ctrl + 1 or 2 ... to toggle drawing tools. Standard drawings clears automatically,
but holding Shift while drawing keeps them permanently on scree, perfect for sketching layouts or UI flows.
3. Stop Recording: Press Ctrl + Shift + R again or click the Stop button.
4. Open in Cursor, or copy the session prompt into your preferred AI agent and let it cook.
No cloud upload. No login. Recordings stays on your Mac.
Since the previous release there's been new feature updates.
Features
Consumes fewer tokens: The agent reads recordings via Local MCP using keyframes and speech—not a giant video dump.
Multi-monitor support: Point or draw across different screens, switch context seamlessly, and let the AI understand what you mean.
Secure - Recordings stays in your device, we don't upload your recordings. Speech transcripts and frames are stored in your device locally.
Agent-agnostic: Works with any AI coding assistant (Cursor, Claude, Codex, and more).
Annotation tools: Easy-to-use drawing and highlighting tools so you can explain your idea clearly to the AI.
What’s new in this version:
File drop - drag and drop files like pdf, folders or images as an additional context to your recording.
Session auto handoff - You can create a session and send the recording to that session , while the agent is busy working it will automatically queue the new recordings, it's great for additional changes and rapid development, no switching windows and copy pasting recording prompts.
If you already vibe with AI coding agents and hate writing long prompts or already use voice prompting, I’d love for you to try it and tell me where it breaks.
Happy to answer anything — let me know how you can use it on your daily work flow,
Thanks for being here.
Annotate
You're the first one to review, 🎉 I appreciate you for trying the tool and for the insightful review @omri_ben_shoham1, your suggestion for improvement means a lot. Thank you.