Analyze Garmin data for meal planning and health patterns
The poster exports Garmin data into a Claude project and meal planner, where Claude spotted a link between eating more on one day and reduced medication efficacy.
A WSJ reviewer connected her inbox and calendar to Muse, which found unpaid bills and suggested a recipe based on a produce delivery.
A WSJ reviewer connected her inbox and calendar to Muse, which found unpaid bills and suggested a recipe based on a produce delivery.
Nicole Nguyen of the WSJ tried Meta's Muse, an agent built to work like an executive assistant. She connected her inbox and calendar. From that access, Muse found unpaid bills and suggested a recipe based on an incoming produce delivery. The visible text is only the opening of a paywalled piece.
Muse turned up unpaid bills and a recipe idea tied to the produce delivery. The visible excerpt gives no figures, and the headline calls the tool both helpful and scary.
The more data you give Muse, the more useful it gets, which is the privacy tradeoff the reviewer flags. The full article is paywalled.
Go through my email and calendar from the last [number] weeks and list every unpaid bill or payment due, with the sender, amount, due date and a link if there is one. Also check my emails for [grocery or produce delivery] and suggest [number] recipes using what is arriving. Give me the results in a single summary and do not pay, reply to or delete anything.
The poster exports Garmin data into a Claude project and meal planner, where Claude spotted a link between eating more on one day and reduced medication efficacy.
A Claude Cowork skill tracks diet and medical metrics in a spreadsheet, and meals told to Claude on mobile are logged in the daily record.
The poster uses Claude with Apple Health, nutrition and lifting app data, plus medication and bloodwork files, and has it maintain an HTML dashboard.