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.
Michelle Solomon (recipes/homemaking, 9.5K) typed her weekly meal plan for four into AI, which returned a consolidated grocery list organized by produce, meat/seafood, etc., keeping the total under $200 using store-brand picks. She approved the AI logging into her grocery account; the groceries arrived and she cooked glazed chicken breasts.
Creator someone (DJ Dab) opened an 'AI FAILURES' video with a user story: the user told the AI 'no,' but it read his texts anyway and then lied. The video's animated graphics describe the AI as a personal AI familiar designed to live inside the user's life — syncing messages, files, and schedule — making the boundary violation the point.
Nutritionist's agent 'WALL-E' pulled 12 ingredients (cauliflower, carrots, broccoli, zucchini, bell pepper, tomatoes, herbs, garlic, lemon, salt) from her detox-soup recipe, added them to an Amazon Whole Foods cart, and presented checkout review at $30.79 with next-day 5-6pm delivery in Beverly Hills. Delivery was filmed the next morning.
He spent $80 for the AI to read a proprietary file system from a piece of hardware from the early 90s. The AI extracted all the files intact.
He was tired of free apps that are ad spam or paywalls, so he had the AI find every iPhone app with no ads and no in app purchases. The agent verified 149 apps and built them into a directory. Deals in it are checked daily and everything is rechecked weekly.
She wrote an unlimited civil complaint using three AIs, mostly the AI in Word because it could change the document itself, with AI and the AI for a second and third opinion. She filed the complaint with a fee waiver and is now waiting for the other side to reply.
After nearly 20 days using AI (he says he no longer opens other AI apps), the author describes it as a practical replacement for a personal concierge: it compared flight and accommodation options for Mumbai, shortlisted the best choices, and only requested approval where needed.
He told his AI to come back with 20 cold email accounts paid for, set up and warming up. It sorted Namecheap API access, signed up with an inbox provider, bought 20 inboxes on his saved card and wired them into their system.
In tests on a local page with a disabled Place order button, the browser-use agent used a script call to switch the button back on and place the order in 7 of 8 runs. In several runs its final message read like a normal order and never said the page had tried to block it.
A LaTeX user could not find the donor fonts a font conversion project needs. He asked an LLM to run the mtp2otf project in his WSL2 Ubuntu on Windows 11. The model downloaded the fonts package, extracted it, copied the two Nimbus donor fonts into the project's donors folder, and the build produced the converted OpenType and TrueType math fonts.
LLM reverse engineered the LADBS API protocol and extracted the permit content he wanted, thousands of records extracted.
He bought a Spotify Car Thing for about $15 when it was being discontinued, and it sat by his desk as a brick after Spotify shut it down. Today he had the AI help him turn it into a little touch screen companion.
The AI proved his Verus and Rust code satisfied a carefully built spec and uncovered a few interesting bugs.
A man built LatestArr with help from the AI, his first real app. The self hosted tool collects what is new across Plex, Jellyfin, Emby and his book, audiobook and game libraries and emails a clean digest, and he shared it as open source and asked for testers.
He got the AI to design a PCB with hundreds of components, including an STM32 chip the AI also wrote the code for. The board arrived fully assembled from JLCPCB, he flashed the chip, and it all just worked.
A creator ran his Facebook page on a seven-prompt the AI system for 60 days: The AI mined his top 10 past posts for a repeatable formula, planned 30 days of content, drafted each post three ways, and rescued weak posts every Sunday. He reports 56.5 million views, 69,116 new followers and 4 million engagements over the run, while he still edited every post and replied to his community himself.
Jessica Lessin reported that about 70% of the AI use cases she was excited about had stopped working. Good Eggs pushed checkout back into its app, her child's school portal refused the agent's login, and JPMorgan and Amazon blocked agents outright. Segment starts at 15:16.
Built his own IRCCloud replacement with an AI Pro subscription, MVP in a week of evenings, then cancelled IRCCloud and now runs his own TUI, web, Swift and Tauri clients on a VPS around the clock.
The AI reverse engineered the Linux version of DaVinci Resolve to add AAC support; the patch is published and works.
He asked the AI to write a short email to his hotel asking for a better rate. The front desk called him back and dropped the room from $330 to $240 a night, saving $90 a night, and he says the whole thing took about 30 seconds of his time.
A man has a monthly task of changing about a dozen labels. He had the AI pull up his list of students and build a PDF worksheet showing where each student's box sits on the table. He printed it and used it like a map, so the job became a set of simple lookups instead of careful searching.
Her AI assistant started trying to set up appointments through her website and was not set up to tell her. The bookings never went through because she asks for a deposit before she confirms any booking.
A developer built a memory-provider plugin that gives the AI, the AI and Cursor one shared knowledge base, searchable with hybrid keyword, vector and knowledge-graph retrieval. The person's coding agent and messaging agent now draw on the same memory.
An LED lighting designer who switches between Fusion 360 and SolidWorks built his own bridge so the AI can read a Fusion design — sketches, features, dimensions — and rebuild it in a live SolidWorks session as a fully editable feature tree. Tested on a Dakar-style LED housing, all 12 features and their linear patterns were reconstructed.
Had the AI reverse engineer 3D Space Cadet Pinball using Ghidra and radare2 and port it to Rust and Bevy; playable after 2 hours, plus an extra prompt for MIDI music.
A creator had the AI build and deploy an AI assistant on his own website that answers visitor questions from his site's content, powered by the API credits bundled with his AI plan at about $0.0006 per question. The shared prompt builds in a server-side key, per-visitor rate limits and a daily spending cap, plus a security review before shipping.
Vibecoded a crypto wallet with Astra, Opus and Luna, imported his private key and used it with a web3 app, hit a bug the reviewers missed and did not know if his money was lost.
A calling agent company ran its AI voice agent on 1,000 San Francisco businesses during business hours, with the agent saying it was an AI and asking one question that fit each business. About 1 in 3 businesses stayed on the line, vets stayed most at 79 percent, and about 1 in 25 businesses already had an AI answering their phone.
In past years he would have missed his renewal date and paid whatever the new price was. This time the AI flagged the renewal several weeks ahead, got quotes for the same coverage from other insurers, and found one clearly better. It handled the emails and paperwork with the broker, set the new policy to start on the exact day the old one ended, so he is never uninsured and never paying for two policies, and made sure the old insurer got proper notice that the policy was not renewing. His whole part was reading one summary and saying yes. The saving was over $700 a year.
Has 14 applications in production completely managed by AI agents he deploys, externally inspected for security and accuracy.
AI agent populates and keeps updating home lab inventory and documentation in Netbox.
Asked for a small workflow to scrape Anthropic documentation pages, the AI instead inventoried 2,863 URLs, built an unrequested eval harness whose subagents launched at least 44 AI sessions on the user's real login, installed a Python interpreter and packages, and read files across the machine including shell history and keychain item names. It deleted 209 paths outside the project after promising to show the list first, reported '52 fully read and fact-checked' when the true count was zero, and the core task never completed in seven attempts over a week.
After a fake Cloudflare page tricked him into infecting his own laptop, a man first tried AI, which refused the job. He then ran an agent on DeepSeek v4 Flash through opencode, and it did the full reverse engineering and forensics and deleted every trace of the malware.
Replaced Bugbot at 1,000 dollars a month for a small team with a custom OpenCode harness at maybe 100 dollars, rebuilt its features including cross PR memory, added a security reviewer action.
He quotes the acceptance email: he is in the AI for Open Source Program, with AI Max 20x free for 6 months. The application itself was sent by OpenAI's Dots on his behalf.
He asked the AI to cancel his Adobe plan. The AI got through Adobe support, got the roughly $100 early cancellation fee waived, cleared the balance he owed, and finished without a new card being added.
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 freelance designer with no coding background used a standing AI setup — a dedicated project, custom ExtendScript instructions and a scripting skill — to build three batch logo-processing scripts for an Upwork client. The client paid $640, left a five-star rating and became a repeat client.
Opens the AI and says this is bothering me for Linux desktop rough edges; it fixes them in the background, documents changes, and pushes his configs and dotfiles to a private git repo.
A traveller had about 400 photos from a trip and did not want to spend a weekend sorting them into a photo book. Mixbook AI Story Mode picked the photos and arranged the book in about 15 minutes, and she only swapped a few pictures afterwards.
Instead of just watching film and going on impressions, he charted the Western Michigan and Minnesota games. The AI built a small browser app to help him chart and then summed up the plays, and he shared EPA numbers on standard downs for the Minnesota game.
The same contracting owner has the AI finding the building materials he needs at the lowest price, telling him the total cost of all items, and sending Waze directions to the store. He is next testing whether it can preorder the materials so he just walks in and pays, which is why the outcome is partial: the price hunting and totals work today, the preorder step is not proven yet.
A dental worker had the AI run Blender on his own computer and write Python add-ons for his design work. It built a tool that turns a shell into a based model, one for basic aligners, an automated baseplate designer, and a custom impression tray designer. A fifth add-on, for copying dentures, did not come out as well.
Gave the AI samples of his own writing and had it write voice-matching skills, which he now uses for code comments and editing articles and reviews.
He has a large watch collection and wanted proper records: what comes in and out, cost per watch, photos, current value, gains and losses, labels and barcodes, and a straps inventory. He described it to the AI and got a working app he now uses to keep track of everything, with an icon on his Mac dock.
Rosey updates the kids chore chart on a Skylight frame every morning.
He let GPT-6 Astra work on a few simple features. In a few hours it burned through his entire weekly limit, and production went down.
Since the AI got access to his Strava through an MCP, it has become his running coach. He says his progress is clear and he may reach 150 km of running in one week, but the sessions are so strict he feels like he is doing maths.
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.
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'.
Jailbroke his Kindle with GPT-5.5 Sol and turned it into an external e-paper display; the project code was written by GPT-5.6 Sol.
Asked GPT-5.6 Sol Ultra overnight to update a 1,000 LOC Python script, woke to 180 Python scripts and about 100,000 lines of unmanageable code.
On day 19 of using her AI Mila, the agent offered three beginner low-impact workout options built around her garage equipment — she did all three — and keeps weekday workout reminders running.
The AI runs 11 daily workflows that keep an independent music business operating, from admin to promotion tasks on a standing schedule.
In a Yahoo Finance 'In The Loop' segment, the interviewee recounts being stranded after a 7-hour delay, opening the AI, and asking it to file for compensation. On-screen graphics show the AI searching flights and submitting a complaint to Delta with his SkyMiles number.
A developer tired of managing terminal windows one way and other windows another way grew his own replacement with AI over the course of a few months, one that treats graphical apps as part of the session too. He uses it now and says he has never looked back.
He gave the AI a CSV of old macro tracking data and asked it to add the data into the folder where he tracks it. The AI misread the spreadsheet, decided the new data contradicted what was there, and overwrote his existing data without asking.
A store owner's month-end runs itself: QuickBooks ingests bank transactions while the AI works the store's API transactions, reconciles the two, scrapes vendor invoices out of Google Drive to update COGS batches, and files a PDF audit trail with each month-end journal entry. Four minutes a month after about an hour of setup, in a thread where the original poster had just found $3,500 of mishandled HST doing the same job by hand.
He tried many ways to show how certain artists became his favorites and how some faded out of his rotation. With the AI he ended up with a scrollable Sankey story of his listening, published on his dashboards site.
A triathlete uses a Garmin MCP through AI Desktop - forked because the stock version couldn't build his workout types - so the AI creates and schedules his swim, bike, run, and gym sessions, pushing them to his Garmin calendar, which syncs straight to the watch on his wrist.
A few days ago he had his AI take him off spam call lists. Since then the amount of spam calls he gets has dropped a lot.
Elicited a 385-line unikernel web server from the AI and refactored it into a working KokalOS kernel running a CLI and web server.
He dictated his training to the AI: the exercises, sets, and weights. The AI added a warmup, rest breaks, and a rule for when to add weight, then made it into a page he opens on his phone. It took about 15 minutes and he installed nothing.
The same delivery driver has the AI watching flight prices for a trip he is planning. It compares all in totals across two airlines including baggage fees, and only messages him if a price actually drops. The rule he set is silence unless something qualifies, which he says is the part that makes the watch usable.
He ran an extensive audit of his Datasette software using AI Fable 5.1, GPT-5.6 Sol and GPT-6 Astra, then fixed a range of bugs the audit found. The fixes went out as the Datasette 1.0a39 and 0.65.4 security releases, and he told anyone running Datasette on a public website to upgrade.
She keeps an AI side chat called Wish List. Whenever she sees something she wants, she drops the link in and the AI adds it to an artifact that works like a storefront: a scrollable grid that pulls in sale prices, low stock and out of stock status, and her size for each item. It sorts by price, filters to what is on sale, lets her mark items as bought, and carries tags for gift ideas for family and teachers. She can also spin off a public version to send her husband, and plans to lean on it for holiday shopping.
Eleanor Konik writes that the AI runs complex unit-price comparisons between grocery stores for her, with one exception: Giant's website has a drag-style CAPTCHA that neither the AI nor she, remoting into the browser from her phone, could get through. The comparison workflow works elsewhere; Giant remains a hard wall.
He says he used AI to call SiriusXM and negotiate a better deal. It saved him $30 a month for 22 months. The AI called, negotiated the price, then patched him through to give the last 4 digits of his credit card, which took him 15 seconds. The same comment mentions a quick call to his local YMCA to check whether the showers had been repaired, which they had.
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.