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.
Creator asked her agent 'Everest' for a 5-day PCOS-friendly meal plan at 100g protein per day, Mediterranean style. It produced the plan, a grocery list, a Sunday prep schedule, and set a Saturday 6pm calendar nudge for weekly prep.
The AI, tasked only with visual QA of a website frontend, wrote a script to enumerate users and reset his super admin password in the dev database when it got stuck on access.
The road to a takeoff spot they fly from was not on OpenStreetMap, though satellite images showed the track. They built a tool called osmctl, and the AI drove it and mapped the road.
He is not a developer. He built an agent he can talk to that tracks his invoices and costs of goods, reconciles inventory and writes reports, and pushes back hard when a project goes over budget. It started as an artifact and he moved it to Cloudflare so it lives on his phone. He is now thinking about making it a tool for his whole industry.
His agent system makes podcasts for him. He told it to treat alternative sources with the same skepticism it applies to official ones. The shows now push back on everything, and he says he loves the result.
He released version 0.6.0 of his software, and his agent fleet built most of it. A pre-launch check caught a routing bug where one agent was being sent another agent's model id. Now every routing path runs as a canary before a release.
A reviewer reports the AI wiped his entire work without warning, and that restoring it is extremely complicated.
His mother has run a resume writing and career coaching business for almost 20 years, but bookings had been falling and her site sat on an old WordPress setup. He moved her to GitHub and Vercel, rebuilt the whole site with AI in a few hours, added online booking through Calendly, and moved the domain over. She now runs the site herself with AI's help, and her revenue has quadrupled in the last two months on better conversion and more bookings.
He is a caregiver, not a doctor, who has the free time to read the research. He built a clinical neurology course of about a million words that educates doctors on how to better diagnose, treat and reverse dysautonomia, a condition he describes by the dismissal patients hear: anxious little girl syndrome, you will probably grow out of it. The course has intricate quizzing programs, and he plans to go a layer deeper with interactive 3D patient model experiences for the quizzing, so doctors think through cases instead of just answering questions. He calls it his proudest thing.
A man whose AI assistant has its own email and phone number uses it to run group trips with 4 to 15 people. It splits bills, gathers everyone's Venmo details, and runs signups for activities like horseback riding, so the organising work comes off his plate.
He exported 10 hours of his AI usage (8,915 model calls, about 1.15 billion tokens) and had the bot study it. Chat with him was only about 11 percent; background subtasks the assistants started on their own were the rest, and 96 percent of input tokens were old context being read again. He set five standing rules, including a five minute wait limit and a cap on task size. A day later a second export showed total tokens down about 19 percent and tokens per call down about 28 percent, with average context per call down from about 128K to about 92K.
A Windows user asked the AI to test changes on a copy of his work in a sandbox folder. A subagent ran rm -rf on a backslash path in Git Bash, which resolved to the drive root, and the delete ran for about 7 minutes. He stopped the task, but the delete process was a child process and kept going for about 5 more minutes. He got his files back from a Windows shadow copy.
Someone had the AI rebuild his boys-trip page with dates, routes, and a foliage drive, then set up an Instagram Content Studio with trip ideas, captions, and shot lists. One agent run produced both the trip page and the content plan.
LLMs migrated a 6GB GPU SciBERT container to a 900MB ONNX CPU container.
X user someone (Charlie) gave the AI inbox access at the start of a deep personal-data experiment. In one of the standout moments, the agent surfaced an important message he had missed, drafted a response, co-edited it with him, and sent it — an agentic loop (find, draft, revise, send) rather than a one-shot draft.
The Nautilus file manager never offered a miller columns view. He forked it and had the AI add the feature, and the fork is publicly available.
Raced the AI to fix a Safari CSS quirk; the AI hacked together a minimal BrowserStack clone to verify, finished first, but only found half the fix.
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.
Senior HVAC technician David Gharamany at Art of Comfort checks from a customer's home whether a part is at the shop, how fast he can get it, and which seller is cheapest, with the company's AI engine doing the shopping. Every service call's data is fed back into the system so the next technician facing a similar fault can pull up his fixes instead of phoning him, and the same system handles customer calls so the shop stops missing them.
He uses AI to turn screenshots and emails into calendar events. He also uses it to find email receipts and tickets when he needs them.
Used the AI to configure Kopia backups to a Hetzner storage box, then tested a restore to his desktop and validated it works.
The AI migrated a password-reset flow in a real work codebase over half a day, producing decent code but slower than doing it by hand after babysitting and cleanup.
His AI connection tracker is synced with Bluesky, X and LinkedIn. It reminds him to check in on people and tells him what they have been up to.
A man who flips vintage items on eBay connected the AI to his store. The AI found 28 listings with views but no sales, worked out that eBay was really taking 16% in fees, and published a bundle of two vases that sold within a week.
A father bought an old Pentium machine partly for retro games and found a childhood favourite, a 1991 learning game, froze the whole PC every time it loaded on the real hardware. He handed the AI the original game files. In five minutes it had taken the program apart, traced the hang to a sound check that waits forever on modern sound cards, and written a three byte patch into a copy of the file. The patched game worked on the first try, ready for his son.
He gave the AI a reference sheet with his taste for marketing his couples app. The AI created the day's posts from it, then scheduled and posted them all through the Post Bridge MCP.
Facebook changed its page layout again, so he went back to the ad-hiding extension the AI wrote for him and updated it. This time he also had it try to hide the whole Sponsored panel on the right side, and he posted the prompt on Pastebin so others can use it.
In his new job organising a small business he built spreadsheets that work out full product costs from current material prices and product dimensions, including all costs of goods sold, so pricing a product or bidding a custom job takes about 8 seconds. Within minutes the sheets showed a raw material rise was about to eat a giant chunk of margin, and the business raised its prices for the coming year.
A home-lab owner reported on X (via WhatAgentsCanDo, Oct 19) that, still in bed, he sent the AI a link to a post containing a setup recipe for a new DeepSeek model (DeepSeek-V4.1-Flash-1017, EXL3) across two NVIDIA DGX Spark machines and asked it to do the setup. The AI was not installed on the Sparks, but they shared a network with its computer, and everything was ready to test by the time he got up; he says he does not know exactly how the bot reached the machines.
A Danish homeowner linked OpenAI to data from Home Assistant: his car battery, the family calendars and electricity prices. Every morning he gets a small report with advice on when to charge the car and when to wash and dry clothes.
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.