I use .md files to keep Cursor on track, the flow I use is something like...
Define a feature in detail (using trascription) -> Get o3 or Gemini 2.5 pro to break it down into very small testable tasks. -> review this -> then paste into a tasks.md file -> write and architecture.md file or similar for any additional context needed. -> then prompt Cursor to work through tasks.md step by step.
This keeps it on track, with the whole feature defined from the outset.
But eventually... it will try to ignore the dockerfile and setup up locally, create multiple .env files, write code with placeholders, ignore a files it's just created and written...
It's impossible to get it back on track - it gets into a debug loop of making things worse rather than getting back on track.
I've tested it for:
1. portfolio analysis 1. scrape portfolio 2. analyse it with ffn
2. make a meal plan, add all items to shopping basket from local supermarket within budget
I'm looking at the simplest way to monetise various API's I have. Without building from scratch things that are common across paid API's. Like whitelisting IP's, rate limiting, usage monitoring, different ways of charging/pricing models and enforcement.
For example I have a Factsheet API for Mutual Funds and ETF's, we have the most extensive repo of available factsheets. I'm unsure if Financial Institutions will switch, so simply want a framework, where by I can easily try and monetise it.