A man set the AI to pull each week's workouts from training providers he used to pay for, since they post the sessions free but late. The AI checks his calendar for when he can train, offers him two options a day, then records what he actually did and how it felt, and uses that history to scale future sessions. A few weeks in it is saving him 20 dollars a month in subscriptions.
As an aside in a design interview, the AI designer Alex Cornell describes using his own the AI to track his golf game shot by shot while working toward a single-digit handicap. The AI produces round recaps, shot data and practice breakdowns (segment from 21:40).
The founder of the Gym Commitment app connected the AI to it through a custom MCP server so the AI works as the trainer inside the app. In a real test, a user described his goal and schedule, the AI asked up to 12 questions, searched 1,872 exercises, and pushed a 4 day plan to his phone in about 5 minutes, only after he approved it.
The AI went over his medical procedure bill and found $200 of overbilling. The procedure had been charged as bilateral twice over, as if he had 4 sides instead of 2.
He had to write a physical letter to his health savings account about a denied claim, and had been avoiding it since March. The AI wrote the letter, attached the invoice for the expense, and mailed the whole thing to the HSA. His only job was taking over for the $2.31 payment. Whether the claim was then paid is not stated in the comment.
This only partly worked. Worth knowing before you try it.
Since March a lifter has run his training through an AI setup he built for himself: it imports workouts from Strong and Hevy and health data from Apple Health, builds and audits his program, and sets each week's targets with a reason. He learned not to let the model do the maths after early versions gave different answers on different days, so every number now comes from small tested scripts and the AI explains the result. Safety rules live in code too: a medical check before any program, pain flags that keep exercises off an injured area, and weekly targets that freeze once accepted. He has since shared it as an open source plugin.
He gave the AI his home address and asked for 5K and 10K loops from his house using OpenStreetMap data. It worked for 27 minutes and gave him both routes as a map he could view and as GPX and GeoJSON files he could download.
A runner's watch syncs while he sleeps; an app he wrote moves yesterday's Garmin data into Notion, and an AI morning brief weighs his sleep, HRV, training status, calendar, and weather to tell him when to work out that day - and how hard.
A dad’s the AI searched for dentists near him for his son, verified which ones accept their insurance on the offices’ own sites, and made the appointment on its own from its web browser, the first time it had done so. He got the confirmation by email and text without calling anyone.
A Stanford doctor gave the AI his own genome file and a 180 word prompt based on the framework his team published in 2009. In about 30 minutes for about $5, the AI matched the main findings of that team’s work, flagged genes that affect how he responds to some medicines, and warned that his file did not have enough data for disease risk scores.