Ameyanagi/Yoshikosan ? reverse-engineered prompt
Reverse engineered prompt
Build me a Japanese workplace safety web app that helps crews digitize 指差呼称, the “point and call” safety check, and simple SOP workflows.
I want a clean frontend where a worker can upload or capture a photo, get AI help turning that into a structured safety check, then tap a big “Yoshi!” confirmation button when the check is approved. It should also give clear OK or NG feedback with voice guidance, and keep a basic log of safety checks so supervisors can review what happened later.
Please make it feel production ready, with a polished Japanese friendly UI, a working backend API, and simple authentication so users can sign in. Use the existing project setup if there is one, and wire everything together so it runs locally with Docker. If you need to check current docs for any libraries or integrations, feel free to look them up online first.
Are you gonna build this?
make sure you review the code using coderabbit