Half the threads here are about accuracy and fewer iterations. One source of rework I rarely see named: when I paste a screenshot, Cursor has to guess which element on a busy screen I actually meant, and it edits the wrong one. Then I'm re-prompting, which is its own iteration tax.
Curious how much of your rework is this specific thing versus raw model quality. And what's your fix, crop hard, or describe the element in text?
Hi, I'm Ross Hancher ex Lead Developer with 25+ years in enterprise software, now semi-retired and building full-stack products solo using AI-augmented workflows (mainly Cursor + Python/JS).
I spent most of my career leading end-to-end delivery at a global market research firm legacy VB/C#/Oracle/SQL Server systems, migrations, AWS, DevOps, and CI/CD. These days I focus on turning ideas into deployed apps in days or weeks, not months.
I'm not here just to generate code with AI I bring architectural guardrails: scalable design, solid data models, secure deployments, and maintainable code.
House hunting in England or Wales? Nosey Neighbour puts sold prices, schools, amenities, and area insights on one interactive map.
ā Sold prices as pins (HM Land Registry)
ā Schools, shops & amenities nearby
ā Flood risk, crime & planning overlays
ā Filter by property type and price
Try the demo instantly ā no signup: noseyneighbour.co.uk/?ref=producthunt
UK-only. Built solo. Feedback welcome.
