What's your current workflow for giving AI coding agents architectural context?

Hey everyone. I built SpecRabbit to solve a problem I kept hitting personally: AI fills in architectural gaps you never specified, and you spend more time fixing wrong decisions than you saved.

Curious what workflows you're currently using before you start generating code with Cursor, Claude Code, or similar tools. Text descriptions? Markdown specs? Just winging it and fixing after?

Would love to hear what's working and what isn't - it directly shapes what I build next.

Try it free at https://specrabbit.com - would love your feedback.

Screenshot from SpecRabbit: