For as long as I can remember, I've had a ton of ideas. But I never finished a single one.
I'd start projects, get excited for like 2-3 weeks, then abandon them. This happened dozens of times over 6 years. At some point I developed this legit fear that I'd never actually launch anything. I felt like I should, but I kept quitting.
What's the point of having ideas if you never build them?
The last 2 years I spent trying to figure out what was wrong with me. Why couldn't I finish anything?
Then 2.5 months ago, everything changed.
I took a freelance project with hourly billing. And immediately remembered how much I HATE explaining dev costs to clients.
"Why is this so expensive?"
"Why does it take so long?"
"Can you break down every single feature by hours?"
I've been estimating projects for 6 years. Every single time it stresses me out.
- Estimate too high → lose the client
- Estimate too low → work weekends for free
- Guess right → you got lucky
So I started using ChatGPT and Claude to help me estimate. But it was a mess - I had 15 different chats, Obsidian pages everywhere, trying to carefully manage context so nothing got mixed up.
Then I tried creating AI agents with Claude Code - Flutter agent, UX/UI agent, Risk Manager. Stored everything in MD files.
While I was doing all this, I randomly met a guy at a coworking space.
He'd launched 10+ projects. Listened to my problem and said:
— Dude. Make a landing page. Put fake Stripe on it. Run ads. See if anyone tries to buy.
This blew my mind. Don't spend months studying the market - just see RIGHT NOW if people want to buy.
That evening I knew what to do.
Spent a week building a landing page with AI help. Added Stripe dev mode, screen recording, bought a domain. Ran Google Ads targeting India (big dev audience, cheap clicks).
Here's the key: when someone went through checkout and clicked "pay" → they got sent to a page saying "no money was charged, thanks bro, you'll be first when I launch."
After 2 weeks: 11 people went through my fake checkout.
From that moment, I never doubted. Never thought about quitting. Never wanted to try something else.
The product vision was clear: backlog tool with AI agents that interview you about your project, ask clarifying questions, and give accurate estimates.
I spent 2 months building it.
Yeah, instead of spending 1 day on that client estimate, I spent 2 months building a tool to do it for me forever.
The whole time I fought the urge to add 1000 features. One of my favorites (that I use personally (at my main BigTech job) I loaded my huge GitHub repo and Confluence docs into RAG/vector database. Now when my manager dumps tasks on me, I throw them in my tool and get estimates in seconds, man!
This feature is only available locally for now - I need to focus on promoting what already exists first.
And that's the story of how I went from 6 years of abandoned projects to finally shipping EstimateFast
Honestly, I have no idea what I'm doing with marketing or getting users right now. But at least this time I didn't quit.
Any advice for a first-time launcher? What should I do next?
Following the journey: I'm documenting everything on Twitter @pavel_bekoev - the wins, failures, and lessons as a first-time founder. Would love to connect with other builders!
Top comments (0)