AI visibility is all the buzz right now and IMO the products out there are way to expensive for they do. We just open-sourced auto-geo: A CLI-based GEO engine you can use to create GEO optimized content that gets your brand cited and mentioned by OpenAI, Claude, Gemini, Perplexity, and Grok. You can also track your citations and visibility over time.
I've been letting Claude and GPT run commands in my terminal for the last year. Most of the time it's great. The other times I lose half a day to AI mistakes: rm -rf the wrong folder, force-pushing to main, "fixing" a config by quietly overwriting it.
So I built Verlox.
Every command the AI proposes gets turned into a plan first: numbered steps, the real commands, the files each step will touch, and a risk score (low / medium / high) per step. Nothing executes until I approve. Risky things (deletes, force-pushes, production access) always stop and ask separately. Anything the AI deletes or overwrites is copied to a Recovery Vault first, restorable with one click.
I'll go first: it's the 20 tabs. Google Flights in one, Skyscanner in another, a third just to check whether the 14th is cheaper than the 16th, and by the time I've compared everything, I've half lost the will to go.
Four years ago, I took my first international trip and completely fell in love with travel. Ever since, I've been a little obsessed with one question: why is finding and booking a trip still this much work?
So I've been building something where you just talk to it. You say where you want to go, and it finds the cheapest days to fly and books the flight, all in one conversation. Her name's Skye and we're launching on Product Hunt soon.
I've been working on WorkZo AI, a platform designed to help job seekers prepare for interviews with realistic AI-powered recruiter simulations.
Instead of practicing generic interview questions, users can upload their resume, add a target role or job description, and experience personalized interviews tailored to their background and career goals.
I'm a solo founder, and I just shipped something I've been thinking about for years.
The problem: senior architects and staff engineers at scaling startups spend days drawing diagrams in Lucidchart or Visio, debating system boundaries, only to ship something that breaks under load. The diagrams are manual, static, and disconnected from actual reality. Tools like draw.io don't validate anything they're just boxes and arrows.
So I built Archivolt. You describe your system in plain English. Tell it your tech stack and expected scale. It analyzes your design for failure modes, load bottlenecks, single points of failure, anti-patterns the stuff that actually breaks production systems. Then it generates a validated blueprint and production-ready scaffolds in 60 seconds.
Not a diagram generator. Not another AI that hallucinates. A validation engine that tells you what will actually break before you build it.
