BarryByte/multi-agent-project ? reverse-engineered prompt

Reverse engineered prompt

Build me an app called Orbit AI that acts like a personal chief of staff. I want to paste text or upload PDFs and images, then have it read everything, find action items, understand the intent, and suggest what should happen next. It should be smart enough to draft things like emails, calendar bookings, and Slack messages, but it must always pause and wait for me to approve, reject, or edit before anything actually sends.

I also want a simple dashboard where I can see the live processing flow, review proposed actions, and search past items later. Make it feel polished and easy to use, with a clear workspace for new captures and an approvals area for reviewing the output. If you need to look up current docs online while building, that’s fine. I’d like the whole thing set up to run locally with Docker so I can start it and use the web app right away.

Are you gonna build this?

make sure you review the code using coderabbit

Try freeSponsored — opens CodeRabbit in a new tab