Edu Peralta

Making the terminal where your AI agents actually live. Multiple agents, one window, zero context lost. Sharing the journey runlinea.com

Recent activity

An AI-agent boundary is only a hypothesis until a live run leaves a receipt

700 downloads and stuck — five months later...

I’m building a Product Hunt alternative for indie makers — what would make you actually use it?

I built a two-sided marketplace and never once asked anyone to use it

I could not tell if Google's AI Overview was citing my sites, so I built a way to check

The Hostage Trap: Why "AI-Generated" Apps Feel Like Borrowed Tools

My first paying user told me I was charging too little. It took me 4 months to listen.

Most AI browsers hide what the agent is doing. I wanted to see it happen live, and run it locally. So I built one.

I built an AI that answers support questions. Founders still hated it. Here's what I learned.

My AI agent leaked my API key — so I built the guardrail and launched it on Product Hunt today

I built Code Factory because I kept getting fooled by passing tests

I built two websites before talking to users. I think I see the problem now.

Shipped my AI tool 3 weeks ago. 0 paying users. Here's what I'm doing wrong.

Maybe we don’t have a productivity problem. Maybe we have a context problem.

What 100B+ Claude tokens actually look like inside a tiny company

What should a coding agent be structurally unable to do in a CRM?

23 days of distributing a SaaS. Here's exactly what happened.

Why vibe-coded apps are still leaking user data in 2026

The hard part of delegating to an AI agent is knowing what evidence would let you trust the stop point

Solo-built Pistly for months. Launching on PH this week and I still don't know if the market wants it.