When we landed our first big client paying $2,000/month, we were ecstatic. They were a massive logistics company, and they had one specific requirement: they needed a completely custom reporting dashboard that synced with their proprietary internal software.
We didn't want to lose the deal. So, my co-founder and I spent six weeks building this custom integration. It was a massive hack duct-taped together with webhooks and custom database queries. But it worked. The client was happy, and we had our first real revenue coming in.
Then the nightmare started.
Because we hardcoded this custom feature into our core app, every time we tried to push a new update, the custom dashboard broke. We spent the next three months firefighting bugs for this one client instead of improving the product for our other 150 users. Our overall churn rate ticked up by 5% because our standard features were falling behind, and the codebase became a mess to maintain.
Everyone talks about building the next unicorn. But what if that's the wrong goal entirely?
Here's a different mental model worth considering. Instead of spending 5 years chasing one product to $10M ARR, what if you built 10 20 smaller products (each generating $10k $50k MRR) managed entirely by AI agents?
Six weeks in, and I still haven't touched a desktop. Everything architecture decisions, debugging, database migrations, the whole thing happens through a phone screen and an AI agent doing the actual typing.
What's strange is how different the failure modes are from what I expected. I thought the hard part would be not knowing how to code. It wasn't. The hard part was learning to think in prompts instead of logic how to describe a bug precisely enough that the agent fixes the real problem instead of patching the symptom, three times, in three different wrong places.
I keep wondering if this is a preview of something bigger, or just a novelty that works because I happen to have a lot of patience and a phone that doesn't die. Curious what others here think: for the people who've built with AI agents has it changed how you think about programming as a skill, or does it just feel like outsourcing typing?
And for anyone who hasn't tried building this way yet what's stopped you? Time, trust, or just never having a reason to?
Every time I ask an agent to tweak a small utility function, it decides my packages are outdated and tries to migrate half my project to a new library or beta version .Next thing I know my build is broken and I'm spending an hour reverting package json changes. How do you lock down dependency changes in your agent rules?
I'll start with one I've often debated: "urgency". As in, fake countdown timers, or saying "you have 1 spot left" when there are infinite spots available.
The annoying part is that they work. Conversion rates go up by a few percentage points. So saying no isn't some clever long-game arbitrage where I secretly win in the end. It's just leaving money on the table because it makes me feel gross.
When we set up credits, one credit meant one generation. Easy to explain, and wrong.
A generation isn't one thing. The same request routed to a cheap model versus an expensive one can differ by an order of magnitude in what it actually costs us, and a retry after a bad output costs full price again. So a flat credit means the people doing simple work subsidise the heavy users, and the users you most want, the ones pushing the tool hard, are the ones losing you money.
