rtrtarun/agentic-notification ? reverse-engineered prompt
Reverse engineered prompt
Build me an attention orchestration app that sits between incoming events and the channels they get sent to. I want a web dashboard where I can see notifications from GitHub webhooks and AI agents, decide which ones are critical, standard, or background, and then either deliver them right away, hold them for a digest, merge duplicates, or record them with a clear reason.
Please include a clean inbox, digests, traces for agent runs, rules I can edit live, and a channels page where I can test delivery and see failures. Critical alerts like outages or security issues should always go through immediately and never be delayed or merged. For everything else, show a plain language explanation of why the system made its choice.
It should be self hosted, with a Go backend, a React and TypeScript console, PostgreSQL storage, and support for email, Slack, Teams, SMS, plus a simple agent API and Python SDK. If you need to check current docs for any libraries, look them up online.
Are you gonna build this?
make sure you review the code using coderabbit