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.
A random mix from the whole library. Shuffle for a new set.
Grupo Marista uses AI Enterprise agents to analyze hospital claims. Analysis that took 72 hours now takes 4 hours.
Agent ported a moderately complex workout app from web to native iOS in a couple of evenings, with a test battery.
After UnitedHealthcare denied coverage for his out-of-network spinal surgeon, Donald Grant used Claimable's AI appeal service to build an 11-page legal and medical appeal, which he emailed to the insurer's CEO, officials and reporters. UnitedHealthcare approved both the surgeon and the procedure at the in-network rate ahead of his October 14 surgery.
He just subscribed to the AI and is setting up a Strava link. The AI gives him a weekly training plan based on his goals, his past workouts, his time, and his injuries, and it got to know him fast.
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 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.
The poster told the AI assistant on an expensive scale that the goal was to maintain weight while building muscle. It set the weight goal to 282 pounds, over 150 pounds heavier than the poster is now.
NYT reporter Eli Tan, reviewing the AI over two weeks with connected bank accounts and email, had it call his dental insurer Anthem. The AI supplied his member ID, answered the security question, waited on hold, then rang him through to the live representative.
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.
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.
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.
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 built a personal fitness display, a website to manage his training plan, and an MCP link that lets the AI control it all. The AI adjusts the plan around his races and the weather.
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 reviewer gave the AI rules based on dates and locations and had it rename his Strava activities that carried generic names like 'Morning Run', adding who he was running with to each name, while the AI kept a log file of the changes in case he wants to review anything later.
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.
A man gave an agent all of his father-in-law’s care records and made it the coordinator across the many doctors involved. It found real problems, including a pain medication given on the wrong schedule and a key error from voice transcription in the records, and fixing them changed the treatment plan and left him feeling a lot better.
A solo builder started runclub.events in May 2026 with an idea and no code, opening the AI for the first time. Sixteen weeks later the app is in production with 990 commits, more than 53,000 lines of code, and 160 features live, helping run club members connect on upcoming races.
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).
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.
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.