The problem at MindPal was pretty simple: we have hundreds of AI templates to share. We know videos of these templates work - some have gotten us tens of thousands of views. But actually making them was a total nightmare.
We tried everything. At one point, we even hired a freelancer, but the feedback loop was exhausting. It actually took longer to give feedback and wait for revisions than it did to just make the video ourselves. It was slow, expensive, and impossible to scale.
When we did it ourselves, it was a massive grind:
Record the screen of the behind-the-scene agent builder
Record a demo of the agent working
Write a script that didn't sound like a robot
Record a voiceover or an avatar
Spend hours editing everything together
If my co-founder or I were tired or busy, the videos just didn't happen. I assumed this was just the "manual tax" you had to pay for quality.
Last weekend, I got fed up and asked Claude if I could just automate the whole damn thing.
Turns out, I can.
So I spent the weekend cooking something - an internal AI SOP to turn any workflow URL (yes, from just a single URL) into a publish-ready use case video that passes all quality standards in ONE GO.
Here is the new setup:
Playwright: Records the screen and even moves the mouse like a human
@Claude by Anthropic: Writes the narrative based on our actual product info
@HeyGen: Creates the avatar and voiceover
@Remotion: Programs the entire edit - syncing everything into a final file
@Zernio + @Railway: Automatically publishes the video and saves the assets.
Now, I just give the system a URL and a finished video comes out. I don't even have to click "upload."
I just wrote a post sharing the full behind-the-scenes build, the architecture, and the logic behind of this AI video agent. Check it out here if you think this could be helpful for your company: https://mindpal.space/article/ai...

P/s: This is what I wake up to every day now

We ve all been there: You check your storage, and there s a massive yellow bar labeled 'Other' or 'System Data' taking up 50GB+.

In OptiClear, I built the Large & Aging Files analyzer specifically to hunt these down. It's often forgotten .dmg installers from 2 years ago or massive log files that serve no purpose.

Yesterday, a user told me they found 12GB of old screen recordings they forgot they ever made!

Question for the community: What was the weirdest or largest 'forgotten' file you ever found while cleaning your drive?

Built for the folks who work with photos and videos on a daily basis, Studio is the workflow-agnostic media workspace; It doesn t just analyze the media you upload to it, it builds an agentic visual memory and runs workflows to understand and act on your team s photos and videos.

Support our launch https://www.producthunt.com/prod...

In November 25, AI Context Flow was #1 Product of the Day and #1 Productivity Tool of the Week. It was surreal.

Since then, we have been building in public, together with this amazing community here.

You believed in this before it was polished. You gave us feedback when it was rough. You kept asking for more and that pushed us to build more, and we delivered more.

@charlie_hb started quite an interesting thread where he outlined on which days people lose their streaks the most often.

He showed some stats regarding days in a week, but I am still lacking the reasons.

The most common ones I have heard were:

The first week felt like validation. 340 customers, $50K in the bank, near the top of the charts. I thought I'd solved the cold start problem.

What I hadn't worked through: I'd acquired 340 customers who paid once and had no incentive to churn. Which meant I had no recurring signal on what actually needed fixing. The feedback was noisy because everyone bought at different price points with different expectations. Support was immediate and permanent. When I raised prices six months later to attract monthly subscribers, existing LTD holders treated it as a personal betrayal.

We just shipped Projects in Room Service.
A new way to inspect your local development folders and understand what s actually taking up space.
Projects analyzes each repo and groups its contents into things like assets, generated data, git storage, and logs. So instead of just seeing folders, you can understand what each part represents and why the project is large.
It also surfaces things you don t normally see while working, like build outputs, caches, and repository internals.

There's almost no public content on how to monetize a Chrome Extension.

Google invited us to do a podcast about it, sharing our learnings on how two bootstrapped guys grew Pretty Prompt to 40,000 users, 25% on annual plans, with ~7% weekly growth, with no VC money.

shipped a bunch of updates today:

featured projects with usdc on base

• you can now promote your project to the homepage carousel using usdc on base chain

• packages: 1 day ($0.50), 3 days ($1), 7 days ($2), 30 days ($5), lifetime ($15)

• integrated privy wallet connect supports rabby, metamask, coinbase wallet, rainbow, walletconnect, and email login

• no stripe, no paypal, no country restrictions works for builders everywhere

mandatory socials