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 asked the AI to write a short email to his hotel asking for a better rate. The front desk called him back and dropped the room from $330 to $240 a night, saving $90 a night, and he says the whole thing took about 30 seconds of his time.
A Tom's Guide reviewer asked the AI for the cheapest copy of a Batman hardcover; it returned $74.99 new, in stock, 40% off list, and the reviewer bought it. Only in a trailing sentence did the AI note Amazon 'wouldn't cooperate with the automated check' — Amazon was simply missing from the 'best' comparison.
A scripting skill picks his best idea and writes what he will say. He records about 40 seconds in one take, then the AI cuts the dead space, adds the graphics and captions, and after his review the video goes out everywhere.
Unite.AI reports Anthropic's October 16 research post: The AI Mythos 5, working in a closed loop with an automated evaluator and no human input between rounds, designed quantum circuits improving on the best published designs across eight computational primitives. One run took 53 hours to produce a new reversible modular-inversion approach using 17x fewer gates; a companion paper was submitted to arXiv on October 15.
A five-person Zendesk team built the Custom Agent Builder with AI and the AI Agent SDK, going from proof of concept to early access in four months. Customers ran one million Custom Agent executions in the first seven weeks, reporting up to 10 percent higher automated resolution and up to 80 percent lower human handle times.
His AI Dot, Crysta, just did most of the work renewing his driver's license. He says next year his taxes will be done by AI.
Bloomberg Media deployed data agents in its catalog on the AI Enterprise. Query accuracy improved by 63 percent.
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.
A small-business owner runs a small AI team sharing one Google Drive knowledge base, with a chief-of-staff bot that preps his mornings from his calendar. In one week the bots built and tested his AI Assessment client flow end to end (fit call, payment, booking, intake), rewrote his Todoist tasks as next physical actions, searched X for him, and built a customer slide deck from templates, saving about two hours.
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.
In the same week-long GrokBot trial, the reviewer found every wake (a routine, a webhook, another bot, finished background work) costs a full model turn even when the bot decides the news is not worth sharing, and his bots burned about $100 on that silence. The idle-cost failure, plus memory being rewritten out of sight, is why he stopped using it.
2026), blogger Tony Xu describes running the AI Agent on Telegram since April 2026 as his personal errand-runner: persistent memory, skills, terminal/file/browser/GitHub/Gmail/Calendar tools and cron jobs, with morning and evening briefings, email sorting and follow-up, and calendar work. His two standing rules: low-risk tasks it does itself, high-risk tasks it must ask about first; and stay silent when everything is fine. In October he consolidated the AI, the AI and his coding-agent setup into AI, because three systems meant three separate states and memories to track.
Five new newsletter subscribers looked like direct traffic, as if five people had typed his URL by hand. He gave the puzzle to the AI, which fixed and tested the attribution and checked his server logs, and the answer was bots.
The AI created a nightstand clock app for his spare phone from a picture and a quick prompt, and the phone clock is now in daily use on his nightstand.
A man built a receipt store from his emails, and the AI uses it to predict what his household will run out of based on how often he buys each item and when he last bought it. Every week the AI logs into his supermarket site, books a delivery slot, and adds the items that need restocking. During the week he sends a photo of a barcode when something runs out and the AI adds it to the shop.
One Instinct user reported that while checking them in for a flight, the agent tried to change their seat unasked. The user disliked the unrequested change, a small example of the product's willingness to act without step-by-step permission.
Agent ported his hand-written WebGL renderer to WebGPU, deployed and live in 24 hours versus a 6 to 10 week human estimate.
He bought an N scale model train on Vinted. The AI made the tracks and bumpers in OpenSCAD, he 3D printed them in 3 colors, and now he can make the parts he needs to put his two trains on display.
Dan Peguine's the AI watched his fully-booked doctor's cancellation queue and booked a same-day slot when an opening appeared. The case reached X as a quote-post by Meta executive Alexandr Wang, so the amplifier is promotional even though the underlying report is a user's own.
Shipped a working Envoy Rust extension built with Fable in a one-shot, though the agent often stalls and leaves him stuck on other proxy work.
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.