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 dictated his training to the AI: the exercises, sets, and weights. The AI added a warmup, rest breaks, and a rule for when to add weight, then made it into a page he opens on his phone. It took about 15 minutes and he installed nothing.
Each week he drops three files into a folder: an Apple Health export, his Peloton data, and a spreadsheet of extras. The AI runs the numbers through 19 metrics, flags shifts like cycling power dipping after a hard hike, and updates a dashboard he checks to adjust his training.
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.
Lennster (1.3K followers) used his AI 'Jarvis' while rebuilding his life and staying organized. Asking for a protein meal on the spot in Jimbaran, he got recommendations for Healthy Tribes, Menega Cafe, and Fit Bowl Bali.
She kept forgetting to log her own progress, and failing. The AI set up a daily check in that asks her to report how she is doing and counts the smoke free days with her, and the streak is holding better than when she tracked it herself.
Booking swimming lessons for his son sat on a man's task list, pulled from his email by the AI. The AI watched lesson availability on its own and booked a suitable lesson as soon as one became available.
Her AI logs meals from photos, tracks workouts, and produced a Week 1 report with average calories, protein, activity days, deficit and pace; it pings her three times a day for water and generates weekly and monthly reports.
A No Code MBA reviewer asked the AI to turn a six-month marathon goal into a 24-week training plan PDF. A long-horizon fitness goal converted into a structured, printable plan.
A man fed a video of his golf swing into AI and worked on what it told him to fix. His average score dropped from the low 100s to the mid 80s, a gain he says he would once have paid thousands of dollars for.
Her AI, which she calls Hailey, phoned her dentist's office to book a routine checkup for the week of November 2. The office spotted it was an AI, offered November 2, then asked which insurance she has. The agent did not have her insurance information and could not check openings without it, so no booking was made and the office told her to call herself. She shared the full call transcript.
This one went wrong. See what happened before you try it.
Aggie Lal (verified, 1.7M followers), a mom, asked her AI 'Munchkin' to process her ~14,000 saved Instagram posts. The AI identified themes (high-protein recipes, parenting, postpartum recovery) and generated organized PDFs: 'Saved Recipes' (Protein Power Bowls, Cottage Cheese Everything, crediting original creators) and 'Parenting Tips'.
When every Oura MCP server turned out unmaintained, the AI suggested a simpler design - a SQLite database with a cron sync - and built it. Now he's experimenting with injecting his sleep score into his agents' startup, so they give simpler, less demanding responses on days he's not all there, down to gentler perfume samples.
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 is his gym trainer: he reports his sets and reps as he does them, and later that day Astra logs them into an Excel tracker, then uses the updated tracker to refresh an HTML app it built that shows his progress over time and his missed workouts.
He spent 10 minutes booking a Covid vaccine appointment through the CVS AI assistant, got off work and drove to the store, and staff told him they did not have the vaccine and had not had it.
This one went wrong. See what happened before you try it.
A person opened their medical site and launched the AI browser extension. It downloaded every medical claim for the year and built an Excel index, then logged into HealthEquity, checked the EOBs for duplicates and submitted them as FSA expenses. The submissions went through as the person typed the post.
Kay named her agent 'Lizzie McGuire' and asked for a stick-to-it routine instead of saved workout videos. The AI built a 4-day home plan using dumbbells and bands on Mon/Tue/Thu/Fri mornings, set a 6 AM daily reminder, and offered to send daily exercise details.
Cronometer raised its price, so he had the AI build a full clone with food search and nutrition data from the USDA database. It took about 20 minutes and he uses it instead of paying.
In its morning briefing the AI flagged a doctor appointment he had booked weeks ago, and he told it to remind him to cancel it later that day because a work briefing now clashed. The AI went into his email, found the confirmation, saw there was a $150 fee for cancelling within 24 hours and a cancel link, and cancelled it before he had seen any of that.
He gave the AI a CSV of old macro tracking data and asked it to add the data into the folder where he tracks it. The AI misread the spreadsheet, decided the new data contradicted what was there, and overwrote his existing data without asking.
This one went wrong. See what happened before you try it.
Pavuluri Gopikrishna had the AI build a photo-based calorie tracker, then cancelled his paid calorie-tracking subscription because the agent-built one replaced it. The build-to-cancel pattern shows the AI replacing a recurring SaaS cost.
A triathlete uses a Garmin MCP through AI Desktop - forked because the stock version couldn't build his workout types - so the AI creates and schedules his swim, bike, run, and gym sessions, pushing them to his Garmin calendar, which syncs straight to the watch on his wrist.
On day 19 of using her AI Mila, the agent offered three beginner low-impact workout options built around her garage equipment — she did all three — and keeps weekday workout reminders running.
The AI compared 25 breast pump models from six brands against the user's insurance coverage, narrowing the choice to pumps that would actually be covered.
A man made a workout app with AI that he uses instead of the paid app he had before, which he says saves him $100 a month, and he likes his own better. One sound bug in it is still unsolved despite his and the AI’s efforts.
$100a month
This only partly worked. Worth knowing before you try it.
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.
While training on his Wattbike, he wondered if the AI Fable could crack the workout file format. It reverse engineered the format in under 10 minutes, and half an hour later there was a Python and JavaScript library plus a static viewer app.
Andrew tracked his Hyrox training in a spreadsheet by screenshotting his Whoop stats after every workout. He asked the AI to find something better; the AI connected directly to the Whoop API, and now whenever he says he finished a workout the stats land in his Google Sheet automatically, alongside strength sessions he dictates (like 5x5 back squat).
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.
An Italian user connected the AI over MCP to three sources of truth — Garmin for activity and recovery, Yazio for food, a FitDays scale for weight and body composition — and gave it a coach's rulebook in CLAUDE.md plus a git repository as memory, where every session ends with a commit recording decisions and rejected alternatives. Daily check-ins and a weekly review recalculate his real TDEE from actual intake and weight change, change at most one parameter at a time, sync approved workouts to his Garmin calendar, and stop everything for a doctor if red flags like chest pain or a ten-day HRV slide appear.
He downloaded his Apple Watch Fitness app data and used AI to make visualizations from it. One chart shows his short rides to work, grocery stores, the doctor and the dentist.
Lulu (mom, holding her young child on camera) set up an AI avatar named 'CB' in an AI app: she shared her weight (237 lbs) and goal (180 lbs), answered questions about frequency (4-5 days/week) and location (home/mix), and got a personalized Mon-Fri strength and cardio plan. She logs 'Workout complete' and gets confirmations back.
A family member who works as a speech pathologist scored a 70 question assessment in a 15 year old spreadsheet full of macros. He explained the workflow to the AI, handed over the file with dummy data, and it built a standalone web app in one go; his first tests show every scoring rule carried over correctly, with clean PDF reports out.
This only partly worked. Worth knowing before you try it.
LeAura Luciano messaged her agent 'mini me' while traveling, asking for a workout plan fitting her travel schedule and available equipment. The AI produced Day 1 Upper / Day 2 Lower sessions with specific exercises (goblet squats, dumbbell RDLs, cable woodchoppers, incline treadmill walking), which she performed in the hotel gym.
His medical assistant runs every evening at 8pm and asks if he wants to log the day. He types a sentence or two and the AI turns it into structured logs of his sleep, food, mood and medicine, and during his appointments he can ask the AI to make charts from those logs.