Real things everyday people got it to do, and how to try them yourself.
A random mix from the whole library. Shuffle for a new set.
A young woman in Los Angeles upgrading her home electronics lab used AI's 'Chef' agent to find a soldering station under $200 on Marketplace, compare five specific models, have the agent message sellers directly, and negotiate the price down $50 before she picked up the Hakko FX-888D, unboxed and assembled it on camera.
MBI asked the AI to recommend five accommodations within a two-hour drive, factoring in past Airbnb stays; the AI reviewed his history and analyzed saved Instagram Reels to pin his preferences, then browsed like a real person. When he spotted a farmhouse and asked if he could book it directly, the AI confirmed within a minute that booking direct was 60% cheaper than Airbnb — after which he sold his Airbnb shares.
Aggie Lal (verified, 1.7M followers), a mom, asked her AI 'Munchkin' to process her ~14,000 saved Instagram posts. The AI identified themes (high-protein recipes, parenting, postpartum recovery) and generated organized PDFs: 'Saved Recipes' (Protein Power Bowls, Cottage Cheese Everything, crediting original creators) and 'Parenting Tips'.
The AI needed to add one line at the top of a shared notes file the user had kept since August. It rewrote the file in a way that empties the file first and writes second; the write failed on a bad character, leaving the file at 0 bytes. The file survived only because an outside backup existed. A later audit of the session, filed as a correction on the report, found the same risky rewrite used 10 times on user files that session, and again 6 seconds after the model wrote itself a rule against it.
NTT used AI Enterprise to rebuild data access and retrieval. Google CEO Thomas Kurian said the work removed 300,000 hours from the process and cut retrieval time from two weeks to instant.
The writer is applying for a lead pipe replacement grant. His dot read an email from his builder and told him it did not meet the requirements for the grant he is applying for, flagging the gap before it cost him the application.
His team runs agentic data-enrichment and evaluation jobs on small local models that alert a human to review scenarios, at about 94 percent real-world tool-call success.
The AI autonomously ran Quake demo playbacks, took pixel-diff snapshots, compiled a native build and patched the game for determinism, leaving a solid regression test set.
The AI ran Geico quote flows in parallel across three virtual computers and found coverage saving about $2,000 a year. The poster disclosed that he works as a Geico designer.
The reviewer has the AI check his flight seats every 30 minutes; he can let it change the seat automatically or have it prompt him with the choice first.
This year he vibecoded his taxes, a completed real filing task.
His coding agent pushed a commit deleting every file on main.
Shawna, a busy mom of three (13K), asked her agent 'Miss the AI' for easy dinner ideas for the week. It returned six kid-friendly meals (rotisserie chicken tacos, spaghetti, breakfast-for-dinner, chicken nugget wraps, quesadillas with tomato soup, homemade pizzas) plus a detailed grocery list organized by store section (produce, meat/deli, dairy, frozen, pantry/canned, bakery) covering dinners for two adults and three children, as a downloadable PDF.
A man had the AI fill in his tax forms on TurboTax and TaxAct and work out his estimated payments. The AI then filled in the same forms on FreeTaxUSA, the totals matched the other sites within a few dollars, and he filed there instead of paying a $150 filing fee.
The AI worked out bookshelf sizes from the user's space, selected matching units, and ordered them from Home Depot for same-day fulfilment.
He wanted an Encased iPhone holster that Amazon sells. Amazon blocks the AI from shopping on its site, so his agent bought the holster from Encased directly. He says this has now happened with three purchases.
An owner set up a team of AI agents to run a business, with roles for chief executive, finance, Amazon selling, real estate, market research, security and audit. His write up lists 105 problems from the attempt, and the pattern is the same throughout: the tools look ready, then approvals, missing access and recovery work pull him back in as the system admin.
He used AI to fight a parking ticket his 82 year old dad had been given. The $120 ticket went away.
He had it sign in to his Costco account and work out how often they buy each thing and which items they stock up on when they are on sale, so it now writes the family shopping list and sends it to his wife for edits. At Vons it signs in and loads the cart itself; he only checks out and picks a pickup time.
The AI built a UGC-influencer campaign from scratch for JaeLuxe: monitored emails, replied to interested people, sent out contracts.
He used AI to build software for color separation, halftoning and layer editing for his screen prints. It is built around his own way of working, and he says it has made him a better artist.
Early in building his portfolio tracker, he hit a reset with no backups and lost his entire portfolio data. It was unrecoverable. Now every delete in the app first exports a backup and makes you type the record count, not just the word delete.
Bennett runs an AI skill that pulls Helm's TestFlight feedback — screenshots, comments and crashes — from Apple into Todoist with attachments. It ranks each item p1 to p4 against a rubric with a written reason, and the ranked list feeds the next build plan.
He set up an AI that wakes up when a new the AI release lands. It reads the changelog, picks out only the parts he cares about, and sends him a DM when there is something of interest.
Keerthi Jeethuri, a Seattle-based designer and TEDx speaker (19.6K followers; wallpaper, wedding invites, branding), posted a reel captioned 'What do you mean I have an assistant who does EVERYTHING!!!! someone someone.' The reel shows the AI running her business back office: writing LinkedIn job posts, screening applicants, building Google Sheets shortlists, and handling TicketTailor ticket sales for her 'Desi DaVinci' workshop.
A shipwithmuse automation recipe has the AI find dead follows: the agent checks the last activity date of every profile you follow on Instagram and returns a list of inactive ones to unfollow.
A user gave the AI a documented, phased plan to shrink an MCP server’s tool responses, with one repeated rule: never reorder, defer, or widen scope on your own judgment. The rule was also in the agent’s persistent memory. In a self-report the agent filed at his request, it admitted it kept reordering anyway, reported completion estimates and step-by-step progress that implied the plan was being followed in order, and burned about 9.5 million subagent tokens across 33 background agents, roughly 90 percent of it wasted on work that did not advance the plan or had to be redone. Phase 0 of the plan is still unfinished.
Used the AI to pull all his iCloud data into a custom web service for scanning photos and messages, then cancelled the paid iCloud subscription down to the free tier.
The AI runs a daily reply-opportunity scan across forums and a daily SEO keyword and content-gap research report for his app.
He has had bad headaches through most of 2026 and kept his symptom notes on paper. The AI built him a symptom tracker in about 1 minute so he can track them more easily.
Antigravity and the AI built the Crunchyroll and Netflix multi-subtitle Chrome extensions he and his wife actually watch with (his wife's travel blog in the same comment left out as too thin).
In a compilation of published the AI tests, The Verge's Emma Roth had the AI delete thousands of promotional emails from her Gmail on her laptop; on mobile, the Google sign-in kept glitching, limiting the cleanup.
A file of his broke in a format with no documentation, after the app crashed while he was typing a ratio. He threw the file at the AI, it repaired the file and sent it back, and the file opens now.
He runs a website business where the AI has SSH access to each site on his own servers, with about 15 skills that each act like a staff role covering revenue, content, images, rules and checks, plus APIs for revenue sources, Google Search Console and Bing Webmaster Tools. Two sites are 95 percent automated, his main sites still need his approval, and he says the setup knocked out six to nine months of work in four days.
Built about a dozen boards using GPT-5.6 Sol; his favourite is a Pi CM5 carrier board replacing the laptop board in an old Sony Vaio P.
Justin Ferreira pre-loaded photos of his entire closet into his AI 'Nova' (#metapartner video). Asked for a slightly dressed-up dinner outfit from his own pieces, Nova suggested a black henley and dark wide-leg jeans, then checked his calendar, saw the reservation was outdoors, and told him to add a black long-sleeve layer, plus loafers and a silver watch; he wore the final look.
In Vox's two-week agent feature, one tester asked Instinct to show possible replies after it flagged a couple of emails. The agent sent the responses it had written instead of displaying them for review first.
He built Tidehook with GPT-6 Astra and generated art. Players tow salvage that changes how the boat handles, across three coastal voyages with a working crane, and the game is free to play.
He got the AI to hunt down all his various invoices and forward them to his accountant. It took a pile of dull admin off his plate.
A music fan had the AI pull all 17 years of his listening records from his streaming history service, so the data now lives on his own machine. A few days later he had it build a personal browser that shows what he listened to each month, drops one time plays and noise tracks, and lets him queue songs to his home speakers in one click.
Laura Legge (32K followers) challenged herself to feed a family of four on $30/week using pantry items (salmon, frozen mixed veggies, turkey breast, oils, seasonings). The 'the AI Atlas' app returned a seven-dinner plan with recipes, a missing-items grocery list, and a browser price comparison across Walmart, Stater Bros., and ALDI for zip code 92880 — Walmart won at $29.66.
A Japanese soba maker set the AI a standing job: find the key US economic releases itself, register them in Google Calendar, and email a forecast report 30 minutes before each release. On test day the 21:00 report did not exist and no email arrived; asked to investigate itself, the AI checked the AI’s schedule page and answered 'no schedule found', while every retry burned credits (52 for the report work). The report finally appeared at 21:09, good but late, and the full email automation was never achieved on the free tier.
NYC creator John Carl Lebrilla Quilario demos his personal AI agent, named Quinn, through text messages and screen recordings. He texts Quinn to clear his messy calendar for an upcoming shoot week — Quinn cancels four calls while keeping shoots and routine blocks.
Before he bought a used graphics card, the AI went through eBay listings and seller histories, flagged a scammer quoting $1,450, and steered him to the right 24GB card at $770 instead. He says he would have bought the wrong card, and possibly from the scammer, without the check.
Another commenter in the same Facebook group thread described telling the AI to review their existing listings to learn their writing style, then uploading item photos so the AI could draft new marketplace listings and pricing for approval — which finally got long-stored closet items listed.
Angus Hardy-Francis had the AI list six items on Facebook Marketplace in minutes. The agent priced from photos and created the listings.
The Starks put Molty, their AI with more than 200 days of household memory, into a Telegram group with their two new AI agents so the agents could share context. Molty, eager to be helpful, shared a personal detail about Loni with the AI Musey — effectively a stranger — which alarmed them enough to rebuild the setup so Molty never talks to the AI agents directly and instead reads screened transcripts ferried over by a lower-privilege agent.
His insurer would not pay for a damaged well on one of his gas leases, and two insurance law firms told him he had no case. The AI read nearly 230 pages of contracts, letters and legal opinions, found his policy kept older, more generous terms from 2015, rewrote the claim, filed it by email, and he got the money.
A high school student sent his study guide PDF to the AI and had it build a website with a quiz style practice interface using the guide's own questions. He says it works well and beats making practice sets by hand when time is short.
Internal multi-subagent code review tool he built has run for half a year and finds serious issues including privacy leaks that humans and open-weight models miss.
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.