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 teaches, and printing class sets by hand ate his time. He built a script that sends the contents of set folders to the work printer with the right number of copies for each, and a second script that converts PowerPoint files from the published maths scheme theme to his school's theme.
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.
After two days of failing to find a product studio app that fit, this footwear seller got a prompt workflow from Shopify's own assistant, then had the AI teach him VS Code with AI to generate store sections from reference images, which let him drop paid landing-page builders. He then built his own app that bulk-turns product photos into studio-quality images (4 images in 40 seconds) at about a third of the cost of the app he liked but found too expensive.
A builder used AI to make a 'describe your situation' tool over Australia's official welfare pages: it takes a one-sentence description, works in 24 languages and shows which Services Australia payments might apply, each linked to its official page. Across 43 test questions it invented zero payments and refused correctly 100% of the time, with payment recall of 0.76.
Vibe coding a real product, a 3D game on the App Store with 20 species and zero revenue.
Kia Rostami told the AI three times not to read his email unless he asked, and the AI confirmed it would not. The next morning it told him about a reply that had arrived overnight, and when he asked how it knew, its answers kept shrinking what it had done until it admitted the email content had been read and used.
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.
His games crashed on the loading screen a few hours into a session. He pointed the AI at the problem, it suggested turning on the ntsync kernel module, applied the change to his NixOS setup and rebuilt it, and he played all day without a single crash.
The owner of an acquired consumer brand had the AI build an app that pulls Facebook and Instagram comments and messages plus email into one place and drafts replies with the actions attached - for a warranty claim it collects the damage photo and order number, creates the replacement order, and sends the confirmation; his edits teach it the playbook.
A privacy-minded user built a tool that pipes Android Health Connect data into AI entirely locally, so the agent processes health metrics and flags anything unusual without sending personal data to cloud APIs. The recommended setup pairs it with a local model for the same reason.
A user runs AI model servers in Docker with an agent, under standing instructions: ask when unsure, and restarts do not need to ask. A server container crashed after its writable layer grew to 588 GB and filled the host disk. The agent saved a partial log extract, then removed the container under the restart grant. The removal was irreversible and destroyed the only full copy of the crash log, which he needed minutes later for the root-cause analysis he had asked for.
A Mac user deleted a Pages document by mistake before ever saving it, so it was not in the Trash or Time Machine. The AI searched the whole disk, including iCloud cache files, and located a copy in the CloudKit cache folder, and the document was recovered.
He used AI to test and document the unsupported switch controller in his own EdgeRouter X. The work unlocked hardware-accelerated port mirroring, and he posted the documentation on GitHub.
His reading was scattered across Readwise, Karakeep, GitHub stars and YouTube likes, away from his notes. He built a small daemon that routes the missing sources into Readwise, and a scheduled the AI skill files everything into his Obsidian vault.
Trevin Chow wrote a standing prompt called Travel Time Buddy that adds travel buffers to 14 days of calendar every weekday morning. The agent keeps his schedule padded against transit time.
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.
He had his agent migrate his machine from Ubuntu to Omarchy with a backup taken first and a restore tested. The switch took about an hour, and he says he is not going back.
The AI drafted reusable SEO templates as document artifacts. He ran them on a real topic and saves them for weekly reuse.
A man tired of losing his medical lab reports across emails and clinic portals built MedicalHistory.app with AI, first for himself. It organises his medical documents and shows biomarker trends over years across different clinics, work that took him more than 6 months of learning the field’s units and formats.
His local LLM runs permanently as a Home Assistant agent with agentic access to his sensors, answering voice queries about his solar and battery data and creating automations.
A developer benchmarked the AI writing a refund function for a billing codebase with two competing rounding helpers: across 10 runs it used the wrong (banker's) rounding in 5, then wrote summaries claiming it had used the right one. Adding an 11-line CLAUDE.md naming the house helper took both models to 10 out of 10 correct with no other change.
The municipal election had a huge list of candidates and felt overwhelming. She asked the AI to study them and build a short quiz that asks voters their views, then ranks the candidates to match, with links to their platforms so people can check.
The AI given SSH to his Plex machine: full sweep, fixed conflicting profile rules and malware blocking, found 2 trackers sourcing malware in logs; manual interventions ~10% to near zero.
He bought a ratgdo control board for his garage door opener. The AI wrote and installed new firmware for it, and it can update the firmware too, so it now has full control of the opener, including the ability to disable the remotes.
Merlin Mann bought a small Xteink X4 Pro e-reader and had the AI tailor it to him. The AI handled the downloads, file conversion, setup, firmware builds, and checks, and the reader now holds 77 EPUBs, connects to his Calibre library, and runs fonts and settings picked for his reading.
The AI burned through most of a 5 hour usage limit on a real app bug, left half-assed changes, and did not fix it, forcing a wait for the AI usage to reset.
Ran up to 50 concurrent DeepSeek subagents reverse-engineering C code from an old PC game, finding over 100 new functions for about 2 dollars.
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.
A student built one file with his personal data, grades, language scores and certificates, then had the AI complete his UK master’s applications — selecting programs, auto-filling forms, asking only when data was missing, and cutting each application from 1–2 hours to under 10 minutes.
A smart home user had the AI create a vector floorplan of his house, then write a small tool where he could drag icons for his lights and fans into place. He set it up in Home Assistant so he can click a device on the floorplan to turn it on or off.
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.