Call the hospital about my X-ray coverage and get past its AI to a human
The AI phoned the hospital to confirm insurance coverage for the user's X-ray and escalated past the hospital's own automated system to reach a human who could answer.
A random mix from the whole library. Shuffle for a new set.
Health
Fitness, appointments and feeling better · 121 ideasThe AI turned my Apple Watch data into charts of my short rides
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.
Sync my Oura data - and go easy on me when I slept badly
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.
Review eight years and 1,000 pages of my medical records for my heart team
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.
Built an interactive workout tracker app ('DAY 1 UPPER PUSH') with weight
Angel Almenarez Jr. posted screenshots of an AI-generated workout tracking page built by the AI: 'DAY 1 UPPER PUSH' with exercises (Chest Press 4x8-10 Machine 120 LB, Incline Press 3x10-12 Dumbbell) plus an ACTIVE TRAINING BLOCK (Week 1, Week of Sep 21, BUILD phase) with a 4-day split (Upper Push, Lower Quads, Upper Pull, Posterior Chain) for logging weights and charting progress.
Her avatar 'CB' set a 237-to-180 lb goal, built a Mon-Fri home
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.
The AI filed my FSA claims for me, duplicates checked
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.
Grupo Marista Agents Cut Hospital Claims Analysis From 72 Hours to 4 Hours
Grupo Marista uses AI Enterprise agents to analyze hospital claims. Analysis that took 72 hours now takes 4 hours.
Dental practice booked $241,000 of treatment patients had left unscheduled
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.
$188,000one time
'Mila' coaches Day 19: three garage-workout options plus weekday reminders
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.
My AI turns my RingConn data into a health dashboard
He sends his RingConn 3 wearable data to his AI email address. It sends back a dashboard and tips to improve his health.
Autism Queensland Agents Handle About 70% of Administrative Requests
Autism Queensland, a disability services organization, has agents handling about 70 percent of its administrative requests, per Salesforce's customer disclosures.
The AI built him a working Cronometer clone in 20 minutes
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.
Built a 4-day home workout plan (dumbbells + bands) for Mon/Tue/Thu/Fri mornings
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.
Had the AI 'Munchkin' analyze ~14,000 saved Instagram posts and produce a 'Saved
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'.
Her agent keeps her full food record and puts the calories on her dashboard
She takes a photo of every meal and her agent identifies the food, estimates calories and macros, and logs it to a CSV. When the totals ran high it caught a unit bug (grams counted as pieces) and fixed it, and the running totals show on her Home Assistant dashboard.
Create my swim, bike, run, and gym workouts on my watch
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.
Handled doctor's-office admin in ~5 minutes: emailed the office, left a voicemail,
X poster someone had the AI do doctor's-office admin in about 5 minutes: it emailed the doctor's office, left a voicemail, filled out new-patient paperwork, and created a calendar entry.
Summarize my graphical Strava trends and correlate them with my Apple Health data
The AI reads the reviewer's Strava trend data, which is normally shown as charts a screen reader cannot use, summarizes it in words, and correlates it with his data from the Apple Health app.
The AI asks 12 questions and builds your gym plan in about 5 minutes
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.
My weekly check: The AI reads my Peloton data and spots what is slipping
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.
Built a 5-day PCOS meal plan hitting 100g protein/day (Mediterranean), with grocery
Creator asked her agent 'Everest' for a 5-day PCOS-friendly meal plan at 100g protein per day, Mediterranean style. It produced the plan, a grocery list, a Sunday prep schedule, and set a Saturday 6pm calendar nudge for weekly prep.
Asked how many days he trains, requested photos of his gear, and
Anthony (Neutron Toys, in his 40s) chatted with his agent 'Rodimus', which asked training frequency and injury history and requested photos of his home-gym gear. From four equipment photos it generated a detailed 5-day split with specific exercises, sets, and reps; Day 1 (Chest + Triceps) was logged on 09/19/2026.
Build me a marathon training dashboard from my own running data
Simmons asked László to learn his Zone 2 method from his training community and analyse three months of pace and heart-rate data ahead of the New York City Marathon. Finding Garmin's API needed a developer account, the Dot signed up for Intervals.icu on its own, pulled his runs, built a dashboard called Steady and set up post-run messages.
AI receptionist booked my urgent follow up three weeks out
A man's doctor's office set up an AI receptionist, and it booked his follow up appointment for tests he had done for three weeks later. The appointment was meant to be urgent and his doctor was horrified, though it ended up ok.
This one went wrong. See what happened before you try it.
Coach my running from my real Garmin and Strava data
A runner replaced uploading Garmin screenshots into AI with a self-hosted agent on a Mac mini that reads his Garmin data (sleep, HRV, resting heart rate, VO2 trend, laps) through MCP plus his Strava uploads: it messages him at 8am, designs the day's run and writes it to Garmin Connect, then grades each session against the prescription when it lands on Strava and decides when training load goes up. He hit his sub-20-minute 5K goal about a month later, and it saves him the hour a week he used to spend planning.
1 hoursaved a week
Turned a six-month marathon goal into a 24-week training-plan PDF
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.
The AI found $200 of overbilling on my medical procedure
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.
$200
My agent plans my workouts from my calendar and my own results, and I cancelled 20 dollars of subscriptions
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.
$20a month
Ran a 30-day 'train like a pro fighter' program via AI coach
MMA creator Nina Marie Daniele (verified, 5.3M followers, 48K likes) set a 30-day goal to train like a pro fighter; the AI assigned an AI coach 'Drama Queen' who built Day 1-7+ programs (warm-up, 5 interval sprints with 1-min rests, tire lifts, assault bike), recommended a 40g-protein tempeh grain bowl, and tracked a low sleep score of 45. Her final interval time beat her prior best (7:42 vs 8:48).
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.