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.
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.