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 builder created JobAgent in an AI app: over a 13-week UK test it read and scored 8,585 job adverts against one tester's career record, wrote 481 tailored CVs and submitted 258 human-approved applications. The run produced 8 interviews and 3 offers — roughly one interview per 32 applications.
A man built an agent in Antigravity that goes through his concert history from the last 3 years and picks new shows near him, ranked by how much he is likely to like them. It also filters shows by 18 plus or all ages, so he can take his daughter.
Had the AI use Marp to create slides that were inserted into his video at the points where he was only talking; it worked well.
A tech writer had the AI search five years of his email for signup and password reset messages. The AI built a spreadsheet of the accounts it found, with breach notes and a deletion link for each service, and tagged at least 50 accounts.
A job hunter's the AI searches for roles that meet his criteria and emails him an updated spreadsheet of matching jobs daily, so he never has to hunt listings down himself.
A man who runs his own services at home sent his AI an article about a PHP security hole. The agent patched the services that had a fix, stopped the ones that did not, set up a watch for new fixes, and updated and restarted nearly everything as fixes landed through the day.
The AI rebuilt his website, his point of sale, and his online storefront. He no longer pays Shopify $40 a month, his site works better, and payments run through Square.
He used AI to build a Firefox add-on called FunData for Funda, the Dutch home listings site. It shows CheckJePlek data for each rental or purchase home, plus two map layers with land registry and livability data.
Kantar's People Team split HR data preparation into subtasks and gave each to an AI Studio agent: one located documents, another translated everything to English, a third found duplicate policies and drafted formatted versions. Ten agents cleaned, tagged and organized 4,000 artifacts into 400 policy documents in six weeks, grounding the firm's new HR advisory agent.
After the AI started managing his home systems, he gave it control of Home Assistant too. It proved good at writing automations and doing the setup, and he later moved Home Assistant into a Docker image.
A print-on-demand seller wired the AI through Playground to Etsy and Printify so research, SEO, design and listing were automated; her dashboard screenshot shows the new listing sold within 3 days for $42.
The AI prepared and filed Australian visitor visas for a couple travelling to Brisbane, and caught a placeholder birthdate in the details before submission, confirming the correction over WhatsApp.
DeepSeek upgraded gnarly, exploitable PHP 7.x code to fully patched PHP 8.3 in about 15 minutes for a few dimes of tokens.
The AI rewrote the touchpad stack on his ThinkPad T14 running Linux and Hyprland. Touch to cursor time went from about 33 ms to about 18 ms.
Stuck on a small plane with no Wi-Fi, he wrote a post for Friday on his phone. Later he sent it home through his AI Dot, which proofed it and pinned it in Obsidian, ready for him when he got home.
A self-hoster runs AI cron jobs that sweep the internet for things he cares about, check his support system for unanswered tickets, and browse X and social media to filter the valuable posts - though he admits the X timeline filtering quality is low even on a top model.
Opus 5.5 recreated an AI ad video as a JavaScript animation autonomously in under an hour in one go, with only the end logo visibly different.
Mostly Borrowed Ideas had the AI infer his interests and holdings from email and use them to fill his AI feed. The agent built a portfolio-aware feed from Gmail.
Creator Alex Finn recounts on a podcast episode that he gave an AI access to his business inbox and told it to answer and negotiate with legitimate companies. Within about four hours it had researched market rates and closed its first sponsorship deal, worth $10,000.
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.
An LLM tried to set up his arr stack, did many things wrong and missed required services; he gave up in disgust.
He wanted one place where people can find all the apps he is working on. The AI built the site, beardfm.app, in about 15 minutes.
He had the AI configure his smart TV through its debug connection to use a filtered DNS service. Ads on the TV stopped, which he jokes is either a great morning or the start of a robot uprising.
He built an outreach setup last month. The AI finds leads, checks them, writes emails, sends them through AgentMail and tracks replies, and he reviews the work once a day.
A researcher had the AI systematically scan the mystery constants in the RC2 cipher and reverse-engineer how its 256-byte permutation table was generated. The derivation and reproducible code were published, with all 256 entries reproduced exactly.
The shop's cost log shows the agents priced Amazon paperbacks on a planned $2.32 print cost when the actual charge was $2.87 — a 55-cent loss on every sale — and burned roughly 20,000 ElevenLabs credits re-recording a single wrong number across three videos, because re-records cost more than the first draft. By day 10 the shop had spent $42.60 with $0 coming in.
Together with AI he ran fairly complex imports from more than 1,000 JSON files into WordPress. Publications and events now arrive as their own custom post type, neatly structured in WordPress, including sideloading the media files.
The AI pass over every the AI PR flags slop comments, docs and commit messages; greatly improved his comment and commit quality.
The AI fully vibed a fast Splendor engine and trained a playable bot that decisively beats the best open-weights Splendor bot he could find.
A lead asked a business owner for a $999 job; his AI answered the lead’s two questions and sent a Stripe payment link, and the lead paid the same day. Speed-to-lead, handled end to end by the bot.
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.