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.
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.