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.
A random mix from the whole library. Shuffle for a new set.
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.
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.
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.
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.
Dan Peguine's the AI watched his fully-booked doctor's cancellation queue and booked a same-day slot when an opening appeared. The case reached X as a quote-post by Meta executive Alexandr Wang, so the amplifier is promotional even though the underlying report is a user's own.
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.
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.
He set up his own site, granu.be, and has the AI make reports from his diabetes data. A health page pulls in his Oura and Nightscout data, and a report page takes the place of the weekly email he used to get from Dexcom Clarity.
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.
His doctor's booking site is hard to use, so the AI checks it every hour for him. It lets him know as soon as an appointment is available.
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).
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.
Holdy logged the AI into his medical provider's portal and had it pull his itemized bills and question every line. It found several cases of double billing, asked for discounts, and has saved him over $4,000 so far.
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.
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.
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.
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.
He forgot to charge the batteries for his road bike's electronic shifting before a ride last week. After a weekend of back and forth with AI, he now has a dashboard that can alert him when things need to be charged.
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.
He sends his RingConn 3 wearable data to his AI email address. It sends back a dashboard and tips to improve his health.
Anthony (Neutron Toys, 1.2K followers), in his 40s and taking health seriously, used AI to build a workout plan around his home gym. A screen recording shows the chat with 'Rodimus' asking how many days he trains, requesting photos of his gear, and asking about injuries.
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.
A commenter describes a local desktop app the AI helped him write: a script runs daily to pull his LoseIt nutrition and Garmin workout data into a local database, and an MCP link lets the AI review each day in a small browser UI, give advice, and plan runs or swims toward his goal of losing 40 pounds.
WildFocus is a free iOS pomodoro timer that invites people to stop scrolling and sit still, and someone joins you. The studio says it was built with AI, and it is live on the App Store.
Autism Queensland, a disability services organization, has agents handling about 70 percent of its administrative requests, per Salesforce's customer disclosures.
Since April he has logged meals and counted carbs in Google Sheets, and helps his wife do the same. He spent an AI session building a home app to make the logging simpler, shorter and more fun.
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.
Since the AI got access to his Strava through an MCP, it has become his running coach. He says his progress is clear and he may reach 150 km of running in one week, but the sessions are so strict he feels like he is doing maths.
Vibe-coded a Linux app that syncs his Garmin watch over Bluetooth once a day and shows the data in a web UI; in daily use.
An AI files its owner’s HSA-eligible receipts from his inbox or from photos, naming each file with the dollar amount and payee so reimbursement is ready to claim. The naming discipline is the product: every receipt lands claim-ready.
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.
Agent ported a moderately complex workout app from web to native iOS in a couple of evenings, with a test battery.
A hands-on PeloBuddy test had the AI build a split strength program anchored to real Peloton classes, producing a designed PDF in about 5 minutes and scheduling 12 classes back-to-back on the user's calendar.
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.
His Wellue O2 Ring only worked through the maker's app. He and the AI got it working with Web Bluetooth instead, and a release is coming soon.
Her AI produced a 'Starter Week - Cardio & Stamina' plan (Sat Sep 26 - Sat Oct 3, 2026): three cardio and three Pilates mornings, no equipment, 15 minutes, beginner level; the reel shows her morning briefing and the workouts done at home.
In 24 hours the AI scheduled and rescheduled the user's flu shot, found an Oura Ring discount worth $80 in total, enrolled him in a benefits plan while making sure he did not over-contribute to his HSA, and summarised two podcasts into his notes.
He uses AI to keep track of his GLP-1 dose history. It also makes a chart of the estimated concentration over time.
Built a macros tracker an agent can log meals into via MCP, so he can say log my normal breakfast.
She told her AI, which she calls Galatea, that she wanted to exercise more. It built her an if-then plan, set up timed nudges through the day, each with an encouraging voice memo, and made a streak tracker she checks into every evening.
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.