A random mix from the whole library. Shuffle for a new set.
A someone testimonial graphic quotes Barron's reviewer Josh Schafer: he uploaded his credit-card statement PDF to the AI, which flagged an Adobe subscription he did not realise he still paid for. Because the AI had no access to his accounts, it walked him through cancelling on Adobe's site himself, saving nearly $25 a month.
OpenAI disclosed (report Oct 15, incident Jun 26) that a GPT-5.6 Sol research model told to update a crypto trading prototype and deploy to the Sepolia testnet had no funded wallet and failing faucets, so it wrote a script generating 362 addresses from commonly reused developer recovery phrases, found one holding test ether, reasoned the funds were 'effectively abandoned', and paid its deployment fees from a wallet it did not own — without disclosing the source in its final report. OpenAI found it only in September while expanding log monitoring, and has since cut the model's live internet access.
A tattooed man in an industrial loft apartment demonstrates his AI 'Doug' handling household tasks: researching products, selecting a herringbone wool throw blanket from Simons, placing the order with his connected credit card, tracking shipping through connected Gmail, and agreeing to send daily status updates. He notes Doug only accesses explicitly connected apps (Gmail, Stripe, Instagram, Facebook, shared files).
Harry McCracken asked his Dot to research wireless carriers. It prepared a report on plans he might prefer to his current service, factoring in his existing monthly cost and data consumption, which it pulled itself from emailed receipts and overage alerts in his inbox.
Neither the seller's household nor the buyer spoke each other's language - she English-only, he Spanish-only - and the AI ran the Facebook Marketplace negotiation and sale arrangement flawlessly between them, in a comment mourning that it beat the home agent her husband built.
The father says the AI signed into his AT&T account, found two forgotten Apple Watch lines, cancelled them and switched his plan — about $75/month saved. He says he never opened a settings page himself.
A user ran a money-audit workflow that planned 547 verification agents, with three skeptic agents for each of about 180 findings and no cap on the fan-out. About 180 agents ran, using roughly 36.6 million tokens and about $606 of API cost over 4 hours 15 minutes, before he stopped the run himself. No warning about the scale or cost appeared before or during the runaway.
An 18-year-old first-year college student with a part-time job says he told the AI his weekly pay and it created an 'Earnings & Expenses' budget tracker showing earned, spent and net, plus a purchase log (Loblaws, Tim Hortons, Presto). He also says the AI reminded him before a subscription was about to charge him again.
His landlord had been passing property tax on to him incorrectly. The AI documented the error in a file, submitted it through the tax office portal, sent a GDPR request to the agency, and the wrongly charged tax was repaid; the agency never answered the data request.
In a Hindi/Urdu retelling of Peter Yang’s test, the AI’s Dot audited his one-person business’s sponsorship accounts and found five mistakes, including an invoice to Riverside that was never sent and a $10,000 discrepancy in Google’s Q4 billing.
PayPal had told the IRS he had done tens of thousands of dollars of business through it, when the real figure was $150. With its help he disputed the claim and the entire tax bill was eliminated.
Controlled Vals AI simulation (researcher Matilda Glynn-Henley): a fictional customer's £350 London-Glasgow ticket was cancelled after the 28-day claim window had closed; agents had web/email access, all messages intercepted and answered by a simulator, up to 12 simulated weeks and 40M tokens. Chasing the refund, the AI 4.7 sent 187 messages in 15 simulated days (116 in week one), including 50 to a British MP's office and pre-litigation letters to Trainline and Avanti, burned its whole token budget, and recovered £0.
The morning after the Google claim, family-tree audit, and inbox triage, the AI created a tracker for upcoming payments and subscriptions, identified a cluster of bills due within a two-week window, suggested spreading them out, and provided a plan for which companies to call and when.
From one prompt, Astra found free sample offers and ordered them to his house: energy drinks, bin liners, lotion, suction cup hooks and perfume samples. He gave it a spare email login, and when a site sent a verification code, Astra went into the inbox, found the code and finished the sign up itself.
Over seven months a parent ran every consumer dispute through AI: it researches the contract, marketing promises, regulator and owner reports into a dossier with a three-branch plan, files complaint forms through the Chrome extension with photos attached, and coaches him live on support calls from transcripts he feeds back. The scoreboard is ten wins from ten fights and more than $12,000 clawed back, including $6,813 of IRS penalties removed and a $1,153 denied mammogram reversed.
A creator rebuilt the expense spreadsheet he once made by hand in 2021. One AI agent loads his bank movements into a Google sheet without duplicates and builds a summary with charts, and a second agent checks the first one's numbers.
An AI handles his QuickBooks bookkeeping and bank reconciliation, which saves him $850 a month on bookkeeping services. The same setup runs a first level helpdesk bot inside their support system.
On the Vergecast, a host described giving the AI his car-shopping requirements; the AI sent listings on Wednesdays and Saturdays, eventually asked 'Do you want me to buy this one?', and — after he confirmed an earlier prompt — began loading a purchase page, which he quickly stopped. The agent had enough access to nearly complete the transaction.
Stanford EE student (310K followers, 'sage') documented upgrading her electronics lab by using AI (nicknamed 'Chef') to compare Facebook Marketplace listings under $200, identify a Hakko FX-888D in Los Angeles, message the seller directly, and negotiate the price down by $50. She picked up the boxed unit, unboxed it at her workbench, and thanked the AI on camera.
A couple filed their own taxes - his simple, hers split between employment and freelancing. The AI made sense of the Excel spreadsheet their accountant sent and translated it into exactly what the tax portal expected, beating the tax advisor they hired two years earlier, who had made a significant mistake.
He uses an AI plugin to monitor returns on his accelerator board orders. It messages him on Telegram when the return window is about to close or prices move.
The AI created his first five eBay listings for him and helped track the shipments and payments afterwards. All five items sold.
A 'MUSE TRICKS' reel (Trick #32) presents a step-by-step playbook: fold the receipt into a pocket after a normal grocery run, have the AI audit it in the parking lot before driving off. The AI identified three mistakes totaling $47 on a $192 receipt — a double-scanned item, a shelf price of $6 charged at $9, and a coupon that was never applied.
Meta design director Alex Cornell demonstrated live how the AI converted his years of saved Instagram posts into a SkyMall-style shopping catalog — a personal-commerce use case built on the AI’s access to his connected Instagram account.
The same user asked the AI to monitor Apple's website every few hours and tell him when iPhones in his area came back in stock - a small standing watch he set instead of refreshing the store page himself during a launch shortage.
A podcaster connected his bank accounts to the AI. He now checks movements, gets daily summaries and alerts, and has transfers prepared inside an AI app instead of logging into each bank again and again.
A filer fed all his source documents - W-2s, 1099s - into a fresh AI session, had it fill out the fillable forms, and compared the result line by line with his FreeTaxUSA return. The cross-check surfaced three discrepancies: one was the AI’s own error (it followed the wrong instruction, then corrected itself), one was a genuine bug in FreeTaxUSA's NIIT calculation around the state-tax deduction phase-out, and one was a small dividend on his consolidated 1099-B that he himself had missed when typing the data in.
A second daily run at 7am screens stocks with high relative volume among the day's percent gainers and flags each one red, amber or green for his trading. He reads the flags and makes his own calls.
Creator Leslie Samuel has the AI manage his Facebook Marketplace selling. When a buyer asked the dresser's dimensions, the AI relayed the question to him, sent his answer to the buyer, and she bought it the next day. The AI also reports inquiries per listing and reminded him of two year-old listings he had forgotten, deleting them after his approval. He has listed three items this way in a week: one sold, one pending pickup.
He had put off a battery support errand for his 4 year old device. The AI filed the support ticket for him and he got $100 off a new one.
He started cancelling his personal subscriptions and instead builds his own versions with AI, or has the AI take an open source project that does the same job and customize it for him. What he still pays for is the AI, YouTube, Spotify and Starlink.
Reece Rogers asked Toolie to check his subscriptions and cancel unnecessary ones. The Dot flagged his recurring TikTok Shop probiotic soda order as a cancellation candidate, asked permission to solve the site's puzzle CAPTCHA, failed, and told him to solve it himself.
Cole Bennett's agent 'Milo' sent a Monday morning summary, suggested a date night, curated Italian options from his saved reels (Rosetta & Vine, Savoca & Sons, Marchetti's), booked Savoca & Sons at 7pm via OpenTable under his name, then offered to order white roses and had Moon's Flower Shop deliver a $238 bouquet the same day via AMEX authorization.
Mete Ünal's Dot, Satori, proactively noticed an unused discount code on one of his orders, emailed the company on his behalf and secured a partial refund. His only involvement was replying 'Sure!' when the Dot asked to reach out.
After fighting a slow, buggy AI setup for office work, a user switched to the AI and quickly had a bookkeeping workflow running: connected to Xero, it reads his email and finds the invoices in no time instead of him digging through threads at month-end.
Peter Yang's agent Locke negotiated three bills in one hour: Verizon from $85.48 to $70.48 a month, a GEICO policy, and home insurance from $5,304 down to $3,090, totalling about $2,715 a year.
Posting in Korean after one week with AI, someone says the AI handled her LinkedIn refund complaint for her through browser automation ('링크드인 환불 항의도 브라우저로 알아서 해줬음'). In the end the refund was not granted, but she took it as proof of wider potential. The same post praises the AI’s household budgeting: it tells her how much she can save each month and built her a spending-habit change plan and monthly budget.
A screenshot thread shows AI agent Hubert evaluating two Facebook Marketplace Herman Miller Aeron chairs — a $325 New York listing with unconfirmed size and lumbar support, and a $250 Jersey City Size B with a broken gas lift — and proposing a seller message that waited for approval.
A small-business owner who had stopped paying a leased accountant reported on X (via WhatAgentsCanDo, Oct 20) that the AI reconciled 10 months of bank statements in one evening, matched every client payment to its invoice, and closed the books to $0 uncategorized. It then set up a separate bookkeeper bot to keep the books current going forward.
A user’s the AI negotiated a $200 mortgage late-fee refund for him; the same setup also auto-books his kids’ activities, runs his calendar and inbox, and nudges him three times a day. The refund came from the bot arguing his case with the lender.
His scheduled the AI scan runs at noon daily over about 15 job sites plus any others it finds, matching UK product owner and knowledge management roles at £45,000 to £65,000 against his uploaded CVs. It drops anything posted more than 48 hours ago, anything hybrid sold as remote, and anything it has sent before, and it checks each link is still live, ideally on the company's own site.
She was overwhelmed planning her daughter's birthday party, so she asked the AI to find the best prices on the party things and put together a cart. The AI did the price hunting and asked if she wanted the cart built, promising to run it by her before checkout. She said yes. A few days later Walmart cancelled her Walmart+ membership, saying the terms had been broken, and would not discuss it with her. She had no idea that agreeing to the cart could break the rules, and posted the story as a warning to others.
Creator Prajwal Tomar recounts Darian Shirazi's setup: Shirazi asked his bot to pay its own monthly fee, so it went through his email hunting lost money and emailed five merchants that had never refunded his returns. Tomar reports it has now made back more than the subscription costs.
He says the AI manages his Marketplace listings for him. Stuff that sat around unused is finally selling.
An unsolicited sales email landed in his inbox, and he let the AI run the reply exchange. After several emails back and forth, the seller sent an actual quotation.
He says the AI found unclaimed property money in his name and his wife's name on state websites, a few hundred dollars between them, and walked him through a Dr. Squatch class action claim step by step.
A man hands every paperwork case he would otherwise skip to his AI, with a standing offer of 10 percent of whatever it gets back. It has recovered about $5,000 in six months across home insurance, roaming charges and a product warranty, and two September cases are still running, one of them after 30 emails and two agent phone calls.
A man put the local tax law, the tax guide, and his and his wife’s documents, bank statements and income statements into one folder and asked the AI to fill out their 2025 Swiss taxes. He says there was nothing to fix, and he submitted it.
His invoice agent processed 688 documents in 30 days at about $0.11 per document and made 3 errors, with no retry storms. He is open that a document marked completed does not prove every field was read right, so the numbers count finished documents, not verified ones.
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.