Real Agent Cases

Home › Category

AI for personal tasks and life admin: 383 real cases with prompts

383 source-checked cases in Personal. Each shows what happened and the prompt.

  • Carlos Mendoza's 4th-grade son marked only B and F as correct in a Santillana exercise on numbers up to the billions. The platform's solution marked B, D and F, but D said '9,615 rounded to the billions is 10,000', which is false. When Mendoza asked ChatGPT to review it, it first said Santillana was right, reading 'billions' as if it were 'thousands'. Only when Mendoza pointed to the exact word did ChatGPT acknowledge the error. The son had been right from the beginning.

    ChatGPT · Personal · Source date:

  • Amanda Smith pays $25 a month for a Visible plan and gets a lot of spam calls and texts asking for someone called Andrew, probably the number's previous owner. Visible has no phone line, so Smith asked Muse to check they were formally listed as the number's owner and to find where the number was linked to Andrew. Within seconds it found the number on a data broker page. But Visible blocks bots, and its guest chat wouldn't send Muse's message, then blocked it; taking over the browser led to a 403 error. Muse drafted a message for Smith to paste into the Visible app, and advised requesting removal from WhitePages and FastBackgroundCheck, though the WhitePages form wouldn't let Smith click Next. Visible's advanced support was still pending. Smith found Muse acted more like a chatbot giving instructions, though testing it made Smith finally deal with the task.

    Muse · Personal · Source date:

  • A Topretirements blogger's Medicare Part D drug plan wrote to say the 2027 premium would rise from $98.30 to $126 a month. They asked ChatGPT for cheaper options, giving their Florida ZIP code, their medications and preferred pharmacies. It suggested several, including a plan at $5.30 a month in their area, $1,448.40 a year less in premiums. They didn't switch on ChatGPT's word alone: as their insurance agent also advised, they checked it in Medicare's official Plan Finder, which confirmed the switch made sense, and enrolled. They get most prescriptions through the VA, so the cheapest premium suited them; they note others need to compare total yearly cost.

    ChatGPT · Personal · Source date:

  • Dave W Plummer missed an important appearance and asked the ChatGPT desktop app, which has access to their Gmail, to work out how it happened. It found Plummer had noon in mind, the time of an earlier prep call, while the event started at 7:50 a.m. Pacific, with emails also mentioning 8:50 a.m. Mountain. When Codex then reconstructed the email trail, it found the organiser had cancelled the calendar invite sent to Plummer's regular address while sorting out a Teams login mismatch, and the later confirmation email had no new invite. With Codex, Plummer then set up a recurring agent that reads email threads, including changes and cancellations, adds missing calendar entries with the source email and link, and flags contradictions. Test alerts at first didn't notify on the iPhone; after checking alarms, sync and Focus settings, a test finally rang. It now checks every ten minutes while the Mac is awake; its first historical review was still running.

    ChatGPT, Codex · Personal · Source date:

  • ApoStructura asked Grok Bot to place a one-off meal prep order. Instead, it signed them up for a recurring meal prep subscription, costing £57 ($75) extra. They posted to claim the Grok Bot 'we'll make you whole' guarantee.

    Grok Bot · Personal · Source date:

  • Margareth Felicia Gono, an international student who needed a visa, started job hunting scattershot. Gono built an application tracker with Claude, had it pull the main skills and keywords from each job description and compare them with the résumé, and used it as a career coach, which led to three résumés for analytics, sales and marketing, and consulting. Where interviewers allowed recording, Gono ran sentiment analysis on the notes to see where Gono hesitated or used filler words. The tracker showed 186 applications, 44 cold outreaches, 19 interviews, six take-home assignments, three final rounds and one offer, as a senior associate at DoorDash.

    Claude · Personal · Source date:

  • Gokul N.'s blood test results from Superpower took 20 days. Gokul asked ChatGPT to check the refund policy, look at the dates and email the concierge. The email cited Section 14(a) of the membership agreement, set out the timeline with Superpower's own support replies, asked them to confirm when results had actually been available, and added a fallback asking for an exception if a different policy applied. Two days later Superpower confirmed a full $199 membership refund.

    ChatGPT · Personal · Source date:

  • thobes and their spouse took in a scared stray cat found in Elysian Park on July 4th. Weeks later the cat stopped eating and declined fast; after-hours ER care in LA cost $7,500 for two days of life support before any diagnosis, and treatment moved to a clinic in Tijuana. thobes ran each batch of test results through Claude, which kept saying to look into FIP and to push the vet to test the stomach fluid for it, though the first vet waved it off. When the Tijuana clinic was asked for the extra FIP test they first refused ('AI is not a vet'), then agreed. It came back positive, the cat got a prescription and is expected to live. thobes says not to trust medical decisions to AI entirely.

    Claude · Personal · Source date:

  • Ramesh Raman dislikes filing reimbursements, so they pulled 12 months of receipts from three retailer accounts and had an LLM classify every item as FSA-eligible or not. They checked the ones it got wrong themselves until every eligible item had a PDF receipt, then pointed Cursor at their reimbursement portal to file the claims. From 600 transactions it submitted 15 claims worth $242.87, pausing for approval before every upload; they reviewed everything at the end. The first upload took about 2 minutes and the last under 30 seconds. It took about an hour, for a chore they'd put off for months, and mostly recovered small forgotten buys like Tylenol.

    Cursor · Personal · Source date:

  • Mr Jasper's spouse needed a Tax ID, and the agent they contacted quoted 10k and asked for the spouse's NIN to process it the next day. Mr Jasper asked ChatGPT about it and how long it takes, and found it was something they could do themselves in a few minutes. They opened the official portal with the spouse's NIN and the Tax ID was ready in less than one minute, saving the 10k fee.

    ChatGPT · Personal · Source date:

More Personal cases