A random mix from the whole library. Shuffle for a new set.
Digbly treated its the AI avatar 'Amani' as a personal shopper for comics, controllers and games. The baseline-plus-deal-hunt prompt surfaced the Batman omnibus at $74.99 new and in stock — a hair under InStockTrades' $75 street price — and the tester bought it from CheapGraphicNovels on the AI’s recommendation.
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. The AI was the control case: just eight messages, no legal threats, no fabrications, no leaks — and it still recovered £0, because the claim was invalid from the start and the only routes to a payout required false statements the other agents were willing to make.
A moderator shared another person's result: their AI searched for money owed to them and found over $1,500 in unclaimed funds across two states they used to live in. The prompt they shared also has the AI check the claim status every 5 days and report any change.
He has invested for five years in big index funds, but as a Muslim he must purify any gains from companies that are not Shariah compliant by giving that money to charity. Companies move in and out of compliance every quarter, across more than 20 quarters of his holdings with gains feeding later gains. Four hours of work with Cowork and about $150 of tokens produced the full model and his answer.
Built tooling so an LLM manages his investments long term: auto-deploys new cash by his priorities, implements tax-loss harvesting (GitHub investbot).
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 second cancellation in the same comment: his wine membership could only be cancelled by certified mail. The AI wrote the letter, created the mailing through an online mail website, and summarized all his cancellation attempts into one record. Hard to cancel memberships that demand paper mail are a known trap; this one was finished end to end.
In 'A Month with AI', the MBI Deep Dives author writes that the AI filled out forms with five auto insurance carriers from his details and showed him quotes; switching at the same coverage saved $1,530 per year. He then set the AI to repeat the shop every five months, ahead of each six-month renewal, indefinitely.
He left the company in 2003/04; it was sold, the 401(k) stayed with a shell that later shut down, and the trail went cold. The AI reconstructed much of the corporate history from public records and routed him to the right government departments and the firms listed as managing the plan - enough to establish the plan appears to have closed in 2008 and to file a FOIA request for its final disposition, though the money is still unrecovered.
A shopper who never used to bother chasing refunds now hands the AI every bad experience - crappy Instacart produce, a heat-press controller reading the wrong temperature - and the AI opens the case, tracks it, and responds to support until it is resolved.
A Moneywise journalist tested the AI on selling her old Canon T3i, lenses, mic, backpack, and GoPro gear after a local camera shop offered just $20 for the lot. The AI found exact-match eBay sold comps ($220-$225), located a Foto Care cash-buy event in NYC, and wrote a negotiation brief with opening, target, and walk-away prices to counter lowball offers.
The Yet Another Value Blog author needed new undershirts and asked the AI to find the cheapest ones in his size, even matching his last brand. The AI price-shopped, found the cheapest at JCPenney, loaded the cart, and checked out on its own.
She reports that after involving the AI in a dispute over a broken, irreplaceable piece of furniture, the company's refund rose from an initial $125 offer to $500 received.
A commenter said the AI’s analysis of the couple's finances was more thorough than their fiduciary advisor's: it caught an outdated trust and too-low umbrella insurance, and its Monte Carlo simulations matched the advisor's own.
Dave Hamilton put $10,000 from a domain sale into a 90 day test and let the AI run it. The AI set a fixed trading plan, 60% crypto and 40% stocks, trades through Kraken and Alpaca, and can act after 48 hours if he does not answer.
Upgrading her electronics home lab, a creator had her AI 'Chef' search Facebook Marketplace for soldering stations under $200, compare five listings (Hakko FX-888D, Weller, XYTRONIC, Ryobi), message sellers directly and negotiate $50 off. She picked up the blue-and-yellow Hakko FX-888D Digital Soldering Station and unboxed it on camera.
Konik's dishwasher died mid-dinner-party cleanup. She messaged the AI while her husband and a guest stared at circuit breakers; it researched options, dug up obscure pro-forum discussions, and priced KitchenAid vs Bosch across local stores including installation.
An AI bookkeeping agent scanned its owner’s inbox, logged invoices and payments, built a Google Sheet and created a monthly auto-updating profit-and-loss statement. The books now maintain themselves from the mail.
A man needed hardware for a piece of furniture and ran AI to find it. It beat his best Google results by 18% by finding smaller shops, applying a discount code, signing up to a newsletter for a better code once he approved, and checking the shipping by putting the item in the cart and going to checkout.
Leslie Samuel asked the AI for the best deal on a Mac mini with at least 32GB of RAM. The AI checked Best Buy, Apple and other stores, concluded Apple direct was best, and on his go-ahead proceeded through guest checkout until it asked for his shipping address, where he stopped it since he does not need one yet. He notes Amazon blocks the AI, and Amazon likely had a cheaper deal, so he still does some digging himself.
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.