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
Floot MCPBuild and ship web and mobile apps inside Claude or ChatGPT
Promoted
absolute fan of Ahmed's work.
the maker of @Katalog and @Arcmark keeps cooking, introducing @Slideshot, a simple and elegant agent-driven screen recorder.
if you use @useloom or @Screen Studio and want to automate this work, give it a spin! you'll enjoy it.
Hey everyone! 👋
Excited to launch Slideshot on Product Hunt today!
Huge thanks to @fmerian for hunting! As always, extremely appreciate your support 🙏
I built Slideshot from a simple realization. AI agents made it so much faster to ship features. At the same time, I felt the speed of how fast you can market these new features is lacking behind. Especially when it comes to video demo preparation. I'd need to manually walk through the flow, record it, then edit it, adding some nice zoom effects, then generate a GIF. It takes a while...
Slideshot is my attempt to make that workflow "agentic".
Instead of opening another screen recorder, you connect Slideshot to the agent you already use through MCP. It supports Claude, Codex, Cursor, ChatGPT, or any other MCP-capable agent. Then you describe the product flow you want to show.
The agent drives the browser, walks through your web app autonomously, records the demo, and Slideshot returns a polished video with built-in zoom effects, cursor motion, and an intro animation.
Here are the main use cases I'm optimizing for:
✻ Product marketers creating launch videos, changelog assets, in-app educational videos, and feature announcements
✻ Product teams keep demo assets up to date as the product changes. Think of a Help Centre that automatically shows how a video of the feature works in the latest version.
✻ Customer success and support teams creating walkthroughs for help docs and customer education
What I’m most interested in is whether demo creation can become part of the same AI-assisted workflow as product building itself.
If an agent can help ship the feature, it should also be able to help market that feature.
It's is still early, so I’d love feedback from teams that regularly need product demos but do not want to spend time recording and editing them by hand.
---
Because I'm building Slidehsot as an agent-first tool, the pricing model is also different. Usually, video recording/editing tools charge a monthly subscription per seat. For Slidehsot, I opted for usage-based pricing. You only pay for the videos you generate.
For Product Hunt, the first 25 people who use the PH21SLIDE code at checkout will also receive $5 worth of credits for free.
@fmerian @geek_1001 Thanks for free credits!
@fmerian @yelyzaveta_dziuba Of course! Free credits for all! 🙌 😅
@fmerian @geek_1001 so cool for the community!
@fmerian @geek_1001 will it record chrome extension's demo video?
@fmerian @mohsinproduct Good question! Unfortunately, Slideshot only works for websites and web apps. Browser extensions or native apps won't work, at least for now. It's also a much larger product area, so I decided to leave it for later.
Would be curious to know how you would like to use Slideshot if it were supporting extensions?
@fmerian @geek_1001 in my case, record demo for an extension that can interact with DOM...
@fmerian @mohsinproduct Nice! Yeah, recording a demo for an extension like would definitely require a proper "computer-use" agent. I'd for sure love to get there with Slideshot eventually
@mohsinproduct Thanks! 🙏
@fmerian @geek_1001 tried Slideshot for in app messages, really loved how fast it was to make polished gifs 👏👏👏
@fmerian @valia_havryliuk Thank you so much, Valia! Really appreciate it! 🙏
Do teams ever push back wanting truer pacing for onboarding or sales videos? Or it it more like everyone just wants the cleaned-up version? Congrats on a well-executed product
@artstavenka1 Thank you so much! 🙏
Yeah, I'd say it's more about getting clean version with effects already applied, so they don't need to do that manually. But ensuring a good pacing (and overall timing) for the video is a nice thing to have
this would've saved me so many hours. recording product demos manually and then adding zoom effects and cursor animations in post is the most tedious part of marketing. does it handle multi-step flows where you need to show different pages or is it single page only
@tina_chhabra Thank you! Really happy you found it useful! Let me know if you have any feature suggestions :)
Sure, it does handle multi-page flow as well. For example, here is the gif I generated for finding this launch page. It opened the search view, and then when clicking on the item, it showed a new page.
Okay this is actually so cool — the fact that it drives your app by itself and just hands you back a finished demo video is wild to me. I'm always putting off recording demos because it takes forever to get right, and this just… does it for you. Really curious how it handles things like popups or slow loading screens though. Definitely upvoting this one.
@vedika_kulkarni Really appreciate it, Vedika! 🙏
Yeah, there are so many nuances when recording a video like that via an agent. For long loading screens, I'm trying to either speed up these segments or cut them out entirely from the final demo in post-production.
Also, things like typing a really long text are sped up, so that the video feels more snappy.
When you kick off a recording, you'd get the edited demo video (the one with zoom effects, cursor, improved timing, etc.), and you also get the raw recording, which is basically exactly what the agent saw with the same timing. The raw recording is mostly there as a fallback, so if you really need to, you could edit the video manually.
Using MCP to let an agent drive the app rather than relying on brittle scripted shortcuts is clever. It's a guarantee that demos stay reproducible when the product UI shifts. How does it handle apps that need auth flows or complex stateful setups before the walkthrough can begin?
@dhiraj_patel5 Great questions! There is built-in support for email-only and email+password authentication.
You can define the login credentials in the Slideshow web app; they are stored in an encrypted state, and whenever the agent needs to log in, we programmatically inject the credentials. This way, the agent never sees the actual values.
If it's an email-only login, then the agent would ask you to provide a magic link or one-time password to continue the login flow.
@geek_1001 Got it, thanks
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.
@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.