Slideshot - Product demo videos, recorded by your AI agent
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.
Replies
Product demo videos are the one thing I keep putting off. Recording, editing, re-recording when the UI changes... it never ends. Having an AI agent handle this would remove a real bottleneck. Question: can it handle multi-step flows? Like "user signs up → connects YouTube → sees their first dashboard"? That kind of walkthrough is what I need for my landing page but I've been too lazy to produce manually.
Slideshot
@ytubviral Thank you Javier! Glad you liked the tool! 🙏
Good question! Generally, yes, it should be able to record multi step and multi-pages workflows. Under the hood it's the actual browser, so every newly opened page would be recorded as well.
But there might be some challenges with the "connects YouTube" part. Can you share a bit more about how you would need to "connect" it? Is it just copy-pasting the channel URL, or do you need to be authenticated into YouTube to approve it as OAuth?
As an example of a more complex flow, here is the video I generated for Slideshot with Slideshot to showcase how to connect the MCP. It was multi-page and also required double authentication. It's possible, but you just need to be very precise with your prompt because authorising into two different services isn't a workflow I optimised.
@geek_1001 It's OAuth — user clicks "Connect YouTube," Google consent screen pops up, they approve, and they're redirected back with their channel data loaded. So pretty similar to your double-auth MCP example.
That video is a great reference, thanks for sharing. I'll try it out for our onboarding walkthrough — being precise with the prompt sounds like the key takeaway here.
congrats on the launch @geek_1001
Is the editing of video is ai driven or need manual intervention
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?