My AI assistant runs all day. The expensive model only does the thinking.

Most requests need no AI at all. "Call me in 30 minutes" is handled by plain code. Reminders, schedules and limits are code too.

Short tasks like sorting and scoring go to fast models on a free tier.

The big model only gets planning and long conversations, where it actually has to think.

If it hits a limit, a backup model answers instead of the app going silent.

If your AI app's bill keeps growing, check what really needs the big model.

What does your app send to the most expensive model?

Same pattern holds in outbound tooling. Filtering, dedupe and enrichment lookups are plain code. The model only writes the first line once the row is already verified. Cuts cost and the weird outputs.

In between my regular work, I’ve been busy with a side project a way for me to learn two things at once: personal finance and coding. The result? Meet "Temen Ngatur." It’s a simple web app designed for personal financial management. I originally built it to meet my own needs, fueled by my genuine interest in exploring assets and financial literacy. ✨ Key Features: ✅ AI-powered smart budget analysis ✅ Setting priorities for financial goals ✅ Daily expense tracking ✅ Monthly history & comparisons I intentionally kept this app simple and personal. It started as a private project, but who knows perhaps it could end up being useful to many more people down the line.

For expense tracking, I’d store each amount in minor units with its currency instead of relying on floating-point values. Is the app single-currency for now, or can a user track spending across currencies?