I'm from an accounting/finance background and spent about 10 years in Big4. I was always into tech, but never software development because writing code (as I thought) takes years to master, and I had already chosen accounting.

Fast forward to 2024 when I saw Cursor (the IDE coding agent tool). I immediately felt like this was going to be the way for someone like me.

Back then, it was brutal. I'd fight with the models for 15 prompts just to get a website working without errors on localhost, let alone QA it. None of the plan modes or orchestration features existed. I had to hack around context engineering, memories, all that stuff. Things broke constantly. 10 failures for 1 success. But it was fun. To top it all off, most of the terminology sounded like science fiction, but it got better in time. I basically used AI itself to hack my way into understanding how things worked.

Fast forward again (only ~2 years later). The AI not only builds the app, it builds the website, the marketing, full documentation, GIFs, videos, content, screen recordings. It even hosts it online (literally controls the browser and configures everything). Letting the agent control the browser and the tooling around that is really, genuinely, just mad science fiction type magic stuff. It's unbelievable how often these models get something mostly right.

The reality though is that it still takes time. Time to understand what works well and what works better. Which agent is good for building apps, which one is good for frontend design, which one is good for research. Which tools are free, paid, credit-based, API-based. It all matters if you want to control costs and just get better outputs.

Do you use Gemini for a website skeleton? Claude for code? Grok for research? Gemini Deep Search? ChatGPT Search? Both? When do you use plan mode vs just prompting? Is GPT-5.x better here or Claude Opus? Or maybe Gemini actually is.

My point is: while anyone can start prompting an agent, it still takes a lot of trial and error to develop intuition about how to use them well. And even then everything you learn is probably outdated today because the space changes constantly.

I'm sure there are people using AI 100× better than I am. But it's still insane that someone with no coding background can build production-grade things that actually work.

The one-person company feels inevitable.

I'm curious how software engineers think about this today. Are you still writing most of your code manually?

▲

butILoveLife 2 hours ago | parent [-]

> it still takes a lot of trial and error to develop intuition about how to use them well.

I used to think so. Then a customer made their own replacement for $600/mo software in 2 days. The guy was a marketer by training. I don't exaggerate. I saw it did the exact same things.

▲

suheilaaita 24 minutes ago | parent | next [-]

It's true. We're also at the point where the models and the orchestration around them are so good that any beginner to those tools who knows how to use a computer can build working apps. Interesting times.

I was pointing out that practice helps with the speed and the scope of capabilities. Building a personal prototype is a different ballgame than building a production solution that others will use.

	▲	butILoveLife 11 minutes ago \| parent [-]
		I said this 4 weeks ago... Buddy its outdated.

▲

shinycode 42 minutes ago | parent | prev [-]

It’s true there’s some magic effect from Claude code’s work. But still, often it’s not exactly the same infra and scaling than production grade. But for a customer I guess that’s perfect, they have a mean to make their own tools instead of relying on platforms to build those tools.

	▲	suheilaaita 5 minutes ago \| parent [-]
		I Agree on the customer empowerment point. I'd push back slightly on the production grade point. The models aren't the ceiling, the user's mental model of software is, depending on his experience/knowledge. Someone just starting out will get working prototypes and solid MVPs, which is genuinely impressive. But as they develop real engineering intuition — how Git works, how databases behave under load, how hosting and infra fit together — that's when they start shipping production-grade things with Claude Code. Based on what I'm seeing, the tool can handle it. The question is whether the person behind it understands what they're asking for. Anthropic, for example, mostly uses claude code to develop claude code.