I Tried Building a Real App with AI. It Took a Year
alexhyett.com
July 24, 2026
10 min read
🔥🔥🔥🔥🔥
51/100
Summary
Alex Hyett and his wife sought to build an app for tracking habits, hobbies, and chores after finding existing options unsatisfactory. Despite the abundance of habit tracker apps available, the development process took one year.
Key Takeaways
- The author and his wife sought to create a habit-tracking app that met specific requirements, including a long list format, offline data storage, and customizable icons.
- After testing several existing apps, they found none fully met their needs, particularly in terms of functionality and pricing.
- The author began developing their own app using AI tools, starting the project in March of the previous year.
- The author expressed frustration with the subscription model of many habit-tracking apps, which he found to be too expensive.
Coverage & discussions
Hacker News · alexhyett.com
Community discussions
Hacker News discussion ↗
Historical count: 5 · 5 saved in sample · Historical sample
Analysis ready
Community Sentiment
Positives
- Using LLM tools can greatly accelerate development when used effectively, enabling smaller teams to be more effective — that's a game changer in a world where time is money.
- AI is making it easier for developers to dive into projects without extensive planning, which could spark innovation — who knows what wild ideas might come from that spontaneity!
- There's a real shift towards trusting AI-generated solutions, as they seem to be pushing back on unnecessary features, which might lead to cleaner, more relevant products.
Concerns
- AI has made it very easy to make a lot of bad apps quickly — this raises serious questions about software quality and user experience.
- Making production software is still hard; LLM tools can hinder rather than help if not used correctly — it's not magic, and over-reliance could lead to disaster.
- The skepticism around trusting lifetime licenses for apps is growing; many developers jump ship after selling out, leaving users in the lurch.
