Slideshot
Product demo videos, recorded by your AI agent
300 followers
Product demo videos, recorded by your AI agent
300 followers
Give your AI agent a product flow to record. Slideshot drives your web app through MCP, captures the walkthrough, and returns a polished demo video and GIF with zooms, cursor motion, and custom intro animation. No manual recording or editing.
Payment Required
Launch Team / Built With
Framer AI AgentsDesign and publish professional sites with AI
Promoted
This is a strong wedge. One place I’d watch is narrative intent: if the agent records exactly the flow you ask for, the demo can still miss the “why this matters” moment.
It would be useful to attach a tiny script/storyboard to each recording: audience, promise, steps to emphasize, parts to skip, CTA. Then the agent isn’t just capturing UI motion; it’s preserving the GTM/story context around the feature as the product changes.
@jim_jeffers Thank you, Jim! Yeah, 100% agree. I do have post-processing and auto-editing, but it doesn't take into account the story you want to tell with the video yet.
Adding the ability to attach a storyboard would be really powerful once I have a more robust agentic editing. I'm definitely looking in that direction
I'm also thinking about adding audio effects and narration in the future (not just generic AI voice, but specifically the voice cloning), but it probably makes sense to add once the editing foundation is there
That sequencing makes sense to me. I’d probably treat narration/voice cloning as downstream of the storyboard, not parallel to it — a cloned voice can make a generic script feel even more “official,” which is risky if the intent is wrong.
A simple control could be: objective → audience → approved phrases/claims → recording → narration. Then voice becomes the delivery layer for an already-approved story, not the thing trying to rescue it afterward.
The MCP-driven recording approach is smart — curious whether Slideshot can handle apps that use custom icon fonts or variable fonts in the UI. Sometimes those render oddly in automated browser sessions depending on font loading timing. Does the agent wait for fonts to fully load before capturing, or is that something you've had to account for separately?
congrats on the launch @geek_1001
Is the editing of video is ai driven or need manual intervention
Nice, great work @geek_1001 🙌
Thank you so much, Oskar! 😊
Thanks for launching..
@golaphazi Glad you liked it 😊 Let me know if you have any feedback!
Wow! Can’t wait to try it out ✨
@albychok Thank you, Alex! Really appreciate it 🙏