In one year I shipped a local AI notes tool, a small RAG demo on my own docs, a portfolio OS, and a weekly writing habit. I did it from Kathmandu with no team, no funding, and one laptop.
A year ago I promised myself I would build AI projects in public and write down what I learned, even if it meant looking unfinished online. None of those projects were perfect, but all of them exist. This post covers what worked, what was hard, and what I would change.
The location was never the limit
I expected being outside a tech hub to hold me back. It did not. The models, the docs, and the communities are all online. My zip code only changed my time zone and my internet, and I learned to plan around both.
If you are waiting for the "right" city or job before you start, that wait is the only thing stopping you.
Ship rough, then ship again
My first public project was rough. I almost did not post it, but I posted it anyway. The feedback on that rough version taught me more in a day than a month of private polishing would have. Shipping early is how I got useful feedback fast.
Get the project to exist first. Polish is a later problem.
I also learned this the hard way. I waited too long to post one rough project, and by the time I shared it, someone else had shipped something close. That mistake cost me a week. Now I post when a project is at 60 percent.
Posting every week mattered more than talent
I am not the best coder or writer in any room. But I showed up every week. A small weekly post built an audience that one perfect essay never would have. People stayed because I kept showing up.
What grew my reach
The big launches did not grow my reach much. The honest notes about what broke and how I fixed it did. People trust a builder who admits mistakes more than one who only shares wins, so I stopped hiding the errors.
The free tools that kept me going
My stack was a free chatbot for drafting, a free coding assistant for fixes, and a local model for private notes. Because it cost nothing, I could keep building through months with no budget. People on the outside underestimate how far zero dollars goes when the habit is strong. That free stack is a big part of why I could keep this up.
The hard parts
- Power and internet. I learned to save my work constantly and keep a backup plan.
- Isolation. I had no local peer group for this niche, so online communities became my office.
- Burnout. Shipping weekly is a marathon. When my energy dropped, I cut scope hard.
What I would tell past me
Start smaller. Post sooner. Care less about likes and more about keeping a log of what you ship. A portfolio built by shipping in public is worth more than any certificate, and it keeps growing with every project you add.
For the next year, the plan is more agents, more local models, and more writing, with the same habit of shipping in public. If you are in a small city wondering whether you can take part, you already can. Start, and keep posting where people can see it.
FAQ
Do I need to be in a tech city?
No. The work and the audience are both online. How consistent you are matters far more than where you live.
How do I handle slow internet?
A local model covers the offline work, and I save constantly. Plan around the weak link instead of fighting it.
About the author. Diwakar Ray Yadav writes about AI tools, prompt engineering, and automation from hands-on experiments in Kathmandu. Read more about Diwakar.