What it does
A progress automation for an online course with live cohorts. Course activity shows who has missed a week, who keeps failing a quiz and who stopped mid-lesson. Each of them gets a short personal message naming the next lesson and how long it takes. Students who don't respond after two nudges land in the coach's queue for a personal message or call.
The problem
Most students who drop out of an online course simply drift: they miss a week and never catch up. With a large cohort the coach couldn't see who was slipping until it was too late.
Approach
The rules for "slipping" are simple and visible to the coach: days since the last login, lessons behind the cohort and quiz attempts. Nudges are written per student from their own progress, never as a group blast. After two unanswered nudges, a person takes over.
- Input
- AI step
- Rules or code
- Person decides
- Result
Screens
Swipe sideways to see the whole screen.
Client work is shown under confidentiality agreements: no client names, and screens are recreated with sample data.
Stack
- Course platform data
- Rule engine
- Gemini API
- Email and WhatsApp
Impact
Typical for systems like this.
