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 creator walks through the 11-step system he says he uses to run a social-media agency content factory with AI 2.0 and its Cue agent, using his own VGC brand from setup to reporting. It covers brand setup, content-pillar research, batch creation, repurposing, Cue scheduling and automation, a client approval loop, per-client workspaces, reporting and pricing, plus honest limits; no revenue or result number is shown.
Working from a machine an agent had never run well, the AI set up his home server stack over Telegram voice messages: SSH, Docker, Traefik, certificates, split horizon DNS and local models. It also runs his house watching through Frigate and a solar dashboard he can check from his phone.
Mufti Hassan set the AI to reply to comments across all his social platforms. The video chapter says the replies run every three hours.
Clinton Stark had his AI Musey research skin cream for his wife Loni, recommend alternatives, and buy one on Amazon using his account on September 19. It was the first time an agent had purchased anything for the household — and it landed the night before Amazon began blocking the AI from its store.
She told her AI to get better at design, then had it check her own site, aunysillyme.com. It found every buy button was too low in contrast to grab attention and that two different oranges had been used on the site for months, and it redesigned the site based on what it had learned.
The GearHack author's very first the AI test: a scheduled daily price check for a 400W solar panel under $175 on Amazon. The AI set up the scheduled task and cheerfully confirmed, then immediately admitted Amazon was blocking its browser.
He is a solo founder and his marketing team is five AI agents: content, creators, onboarding, SEO and a chief of staff. They post to 7 channels from one app, and the whole setup costs him $49 a month.
An LLM looked up CNC plasma cutter specs and wrote Python to generate and debug G-code toolpaths, then he cut the result in steel.
Builder Omar Villalobos says a client was losing 70% of its quotes because everything lived in scattered WhatsApp chats, so he built three parts with AI: a WhatsApp-linked form that auto-updates a CRM instead of manual copying, a pipeline dashboard showing $1.28M at stake with follow-ups due and won deals, and an ROI calculator showing a client their investment, monthly gain and payback. No recovery of the lost quotes is claimed yet.
Jack created a recurring daily website-check goal by chat in about a minute, then deleted it by chat. The Goals tab itself was slow to load (once 25 seconds, once stuck on placeholders).
A session generated a Word document with a script. The user then edited the document in Word for about 40 minutes and saved. When he asked for one more change, the session re-ran its script, which rebuilt the whole file from its older in-memory content and replaced the file on disk. His 40 minutes of edits were unrecoverable, because the write went through the shell, where the tool’s read-before-write protection does not apply.
He had the AI translate his MaPollution app into Italian, and it took 30 minutes. He can now offer his free service to people who speak other languages.
A developer had the AI build mazkir, a shared-memory service: tell the AI something once and it appears in his next chat, in an AI app and even in an AI app, stored as plain Markdown notes. Launch week brought about 160 visitors and exactly one sign-up — his friend.
VC Ian Park posted a Korean-language the AI chat confirming two Prestige-class Korean Air flights (Seoul Incheon–Singapore, Sept 26–29) and a Ritz-Carlton Millenia Singapore twin-room booking with free cancellation to Sept 24. After linking the Google Calendar connector, the AI added 11 Singapore itinerary items (flights, courses, jogging, checkout).
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 moving/junk-removal owner says three the AI run his marketing agency work: a Google Business Profile posts bot drafting daily posts in each client's voice, a review-replies bot generating three reply options per new review, and a GoHighLevel bot logging leads, creating call-back tasks and drafting follow-ups. His morning pass runs 6:30, 6:45 and 7:00 AM approving posts, picking replies and sending follow-ups, done by 7:05 with nothing left open; the bots are logged into Gmail, Quo, Stripe, Wix, GoHighLevel and Google Business Profile.
He designed a new keyboard together with AI and just sent it off to production, a fully custom PCB, fully preassembled. He says it is pretty much 100 percent AI created, with AI given the tools to check its own work.
Spent half a day coaxing the AI to fix Kotlin software so it worked with his Java version, work he says would have taken weeks without AI.
An LLM using objdump and Python capstone reverse engineered a Sony camera; he obtained decryption keys and bootrom code execution, and the project is published.
He had an email with stage times and used AI to tidy it into a Stage, Day, Time, Artist list. The AI then changed the fcpxml file so Final Cut Pro had a new project for each set.
Has the AI-built dashboards for 5 radios, streaming decoded data into SQLite and visualizing weather, ADS-B traffic and radio status.
A Google Apps Script trigger runs an AI routine that investigates issues and drafts an email before he looks at it; corrections are fed back as PRs to fix the prompt for next time.
A developer built himself an AI evening edition. It goes through the posts and articles he saved, checks each one against his actual setup, and sorts them into adopt, trial, park or skip. Any change it suggests waits for his yes. The first run cleared his whole backlog of 30 items, and a planted fake post with hidden instructions was flagged and skipped.
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 man's clock needed a battery that was not a standard size, and the compartment needed a screwdriver to open. He took a photo of the clock and sent it to the AI, which worked out what battery the clock takes and ordered it from Amazon.
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.
Since April he has logged meals and counted carbs in Google Sheets, and helps his wife do the same. He spent an AI session building a home app to make the logging simpler, shorter and more fun.
Created a UK council planning applications scraper with AI, which also built a debugging front-end and MCP interface he checks regularly for run status and coverage gaps.
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.
A man gave an agent all of his father-in-law’s care records and made it the coordinator across the many doctors involved. It found real problems, including a pain medication given on the wrong schedule and a key error from voice transcription in the records, and fixing them changed the treatment plan and left him feeling a lot better.
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.