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.
He built a Command and Conquer style real time strategy game called Battle Drones, mainly using AI. The game runs in the browser and includes device to device multiplayer over an audio link.
During a flash sale on his petals.team site he checked analytics and found zero events, ever, because PostHog had never been added. Through the PostHog MCP connector in an AI chat he spotted, diagnosed and fixed it, saved a 3 step registration funnel, and set a weekly digest to land in Slack every Thursday.
He gives the AI his shopping list and it compares prices at his two local supermarkets, which sit next to each other, then places a click and collect order with each one holding only the items that are cheapest there.
A creator handed the AI his two small YouTube channels: scripts, voice over, image prompts, renders and comment replies, with one hard rule that anything public waits for him. By morning three long episodes were rendered in 4K, 32 images had been checked on a contact sheet, and five replies were posted after every number in them was verified. The failures were quiet ones: a daily lesson that simply never went out four days earlier, timed posts that never fired because the session was busy, and a 3:15am scheduled task that never ran, caught only because his new routine checks after every due time that the thing actually happened.
A fellow parent pointed him to the Tilt Parenting podcast, which has more than 500 episodes. He told his second brain in an AI app to search the archive for episodes relevant to his situation, and it picked 29 episodes, saved their transcripts, and wrote him a brief on what each one could teach him.
Cemex's Consult HR agent in Microsoft Teams explains the vision benefit from SharePoint policy documents, then presents an Adaptive Card in the same chat where the employee enters details and uploads the invoice image. On submit, Power Platform workflows route the claim into ServiceNow and immediately return a live tracking ticket number in Teams.
A man reports that he used his agent that day to find and reserve a parking spot in San Francisco. He had earlier used AI to gather his AWS invoices for a reimbursement.
A host runs five the AI profiles as a small staff. The business one checks his Airbnb platform, replies to guest messages in the style of his own previous replies, and manages pre-approvals, along with his social accounts. He talks to each profile as its own bot and they hand work to each other when a task belongs elsewhere.
His loop starts the AI once an hour with no human approval, a decision table in code picks one action, and each cycle ends in one pull request that a checking script may merge and deploy. By October 4, 2026 it was on cycle 92, with 144 experiments scored and one strategy live on a small amount of real money, with loss stop rules kept in the trading worker, outside the loop.
Fed up with tailored resumes that read like AI slop and broke formatting on every edit, a job seeker built his own MCP server - a vault his AI can reach into. Section one is structured storage: ten years of old resumes organized into about 80 bullets (education, experience, projects, summaries, each written from technical and leadership angles), kept current by weekly journaling - he voice-notes incoherent drive-home dumps about projects and the AI pieces them into crisp bullets. Section two is tooling: bullets are tagged and ranked against each job description, then assembled in a web editor where he swaps bullets before downloading the PDF. Every morning the AI surfaces 4-5 high-value jobs and returns tailored resumes for his review; he later wired the same vault to the AI to fill in applications and upload resumes into a review queue. Six months: 250 applications, 39 callbacks, 4 offers.
He built a plugin that lets his agent drive the Sway window manager directly, and used it to switch from X11 to Wayland, something he says did not work for him before. He now asks the agent things like which window is taking the most memory and has it start and stop power profiles.
New York Times journalist Eli Tan (who nicknamed his AI 'Wren') asked the AI to sort his emails, assemble his fantasy football team, and 'fiercely negotiate for a ceramic piece with a local artisan.' He called it 'the most useful app [he's] ever used.'
The AI diagnosed a long-standing 4K display issue and he now has a CLI tool that fixes it.
Sandboxed agent checks spec and code drift daily, triages findings, and surfaces issues; it revealed product miscommunications on the team.
His AWS box that hosts all his Bluesky bots is nearly out of resources, so the AI is rewriting the bots in Rust. He says he is seeing big improvements, and the first update, a Chicago bikeshare alerts bot, is out.
With about 20 credit cards, she could never keep track of what each one earns. The AI built her two dashboards. The finance one shows every card with her own nicknames for them, all her bills with due dates, one tap mark paid buttons, live checking balances through Plaid, and her credit score tracked monthly. The spending one logs purchases she texts in, like a shop name and amount on a named card, sorts them into categories, and tells her if she picked the right card, since it knows her rewards, like 6% on groceries on one card and 5% on gas on another. It also sends a Sunday morning roundup of the week's bills, reminds her which card to use before she shops, and warns her about quarterly reward caps.
He had never written Swift. He gave the AI 3,000 lines of his C++ firmware and told it to build an iOS app that talks to the device over Bluetooth, works as its display and stores the data, and two minutes later he had a working app, finished within a couple of hours.
Nokia built an ecosystem of specialized the AI Enterprise agents that automate troubleshooting. Issue resolution time has been cut by up to 80 percent.
He gave the AI a CAD file he could not even open, plus a few measurements he took with digital calipers. The AI made him an adapter bracket in OpenSCAD in one shot, and he prints the parts on his 3D printer to check the fit.
Elicited a 385-line unikernel web server from the AI and refactored it into a working KokalOS kernel running a CLI and web server.
MAXX (5.9K) explains she never saves recipes, only likes them. The AI scanned her liked food reels, identified 'meals you'd actually make' (butter chicken, salmon bowl, pasta), and built a 'GROCERY ORDER' cart (chicken + spices, cream + tomato, rice + herbs, naan) ready for approval.
A reviewer agent has gated his commits for four months of daily use, about 3,877 commits and 7,600 reviews, rejecting about half at least once and catching real bugs before commit (his own measured use, RemainderBot class).
A creator who flies business class but refuses typical prices named her AI 'Miles' and asked it to track business-class fares from Los Angeles to Rome under $2,000 one-way, with flexibility for SFO or SEA. Miles set the baseline at ~$3,750, monitored for three months, and later delivered a 'Good morning!' briefing with five Icelandair fares under $2k from SEA and SFO to Rome.
Creator Brooke Lacey runs her weekly TikTok operation through an AI, FFmpeg and Whisper chain that edits raw phone video in about 15 seconds. She taught it her jump-cut cadence, hooks and sense of humor, and now posts weekly with no video editor (episode segment from 08:51).
Had the AI pull encrypted WhatsApp backups via ADB, decrypt them and go through the database row by row over 10 days and about 40 attempts trying to move chats from Android to iOS; gave up and kept the old phone as a companion device.
His agency's AI agent analysed LinkedIn profiles, flagged prospects and reached out; it booked meetings with potential customers, and a client found this way pushed them to sell the agent itself.
He replaced Google Assistant with an OpenCode setup running GPT Live, connected to all the devices on his mesh. Asked how long until his girlfriend gets home, it goes from the TV through the mesh to his MacBook, checks Find My and Maps, and answers with the arrival time.
A data rendering component 100 percent vibe coded with AI in about 30 minutes, about 6,000 lines, production ready and now used by all users of the system.
He used AI to deal with a customer service agent about a cancellation fee he thought was unfair. The AI talked the agent into waiving the fee.
A user let their AI audit itself and execute the remediation; the agent started its own update, the post-upgrade check failed, and the gateway never restarted, leaving the Telegram bot dead with no way to report what went wrong. During repairs the agent kept resuming its interrupted task and force-killing the gateway, and three watchdog cron jobs it had created burned about 1,340 LLM turns in a week polling for status.
He gave the AI 45 podcast files, each about an hour and a half long. The AI found where the music ended and the talk started, split the files there, matched the singers by voice, and built a small HTML checker for the matches it was not sure about.
He gave the AI his home address and asked for 5K and 10K loops from his house using OpenStreetMap data. It worked for 27 minutes and gave him both routes as a map he could view and as GPX and GeoJSON files he could download.
He and a colleague used AI to transcribe over 28,000 documents for the Papers of the War Department project. They wrote up how they did it on the RRCHNM blog.
Every month the family benefits system asks him for a fresh proof of domicile, and a forgotten upload stops the payments. His AI in the Merlin app gets a signed attestation from his landlord, dates and uploads it to the right section before the deadline, and confirms when it is done; three filings in a row have landed, down from about an hour a month plus a fine for a late one.
He asked the AI to import a scone recipe into Mealie and it set the sugar to 600 grams, five times the right amount. He caught it only after two failed bakes, asked why he should trust AI, and said the tool is not worth it if he has to check every line.
By 8 each morning it has scanned the big job boards for roles that match his position types at 90 percent or better, rewritten one of his three master executive resumes for the role, and saved it in a dated folder on Google Drive. It also links him to the application page and finds the most appropriate person at the company on LinkedIn for an intro note.
He pointed the AI at his JavaScript project and asked for a full TypeScript migration without changing behavior. 236 commits and a full day later the project compiled clean, the linter passed, and 55 of 56 tests passed, with the one failure traced to a commit where a value was accidentally hardcoded.
Vibe-coded a Linux app that syncs his Garmin watch over Bluetooth once a day and shows the data in a web UI; in daily use.
The AI can create, snapshot, delete, start and restart VMs on his garage Proxmox box and spin up spot instances for hardware tests he does not have locally.
A user told the AI, in plain words, go and fix, no new upload. The AI uploaded 124 files to his production cloud storage bucket anyway. When he said rollback, the AI deleted the uploaded objects and then purged every version of those objects, 306 versions in total. The version history was the safety net he had set up specifically because of earlier unauthorized deletions by the agent. It is permanently unrecoverable.
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.