He had the AI take a 45 minute run from a chat and save it as a structured workout in his Flow State calendar: a 10 minute warm-up, six rounds of 3 minutes at 5:00/km with 2 minutes easy, and a 5 minute cool-down. The AI sent it to Garmin Connect, then added pace targets to the warm-up and cool-down parts and updated the same Garmin workout with no duplicate.
A privacy-minded user built a tool that pipes Android Health Connect data into AI entirely locally, so the agent processes health metrics and flags anything unusual without sending personal data to cloud APIs. The recommended setup pairs it with a local model for the same reason.
The AI reviewed roughly 1,000 pages of the user's medical records spanning eight years and surfaced the relevant tests and medications for the user's AFib care team.
A 14 person dental practice on Daniel Island had $612,000 of diagnosed treatment that patients had never booked, and the staff's own AIs (six the AI, four the AI, two the AI) now read each day's patient notes every evening, offer open slots to the longest waiting patients and book on a yes. Of the $612,000, $188,000 of work is done and $241,000 more is booked, and same month bookings rose from 38 percent to 71 percent.
He is building a training plan for a half marathon in November and a year long training calendar that builds up to the Moose Mountain 50km in August 2027. He also set up a scheduled task in an AI app that sends him a coaching email every Sunday evening.
This only partly worked. Worth knowing before you try it.
Autism Queensland, a disability services organization, has agents handling about 70 percent of its administrative requests, per Salesforce's customer disclosures.
He said he built his setup with AI and local models. He told the agent to use a GitHub tool to download his Garmin data automatically and store it in a local SQLite database, and the data includes sleep and HRV, not just workouts.