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.
In an October 1, 2026 test, a Cue agent returned three Manhattan workshop venues in about four minutes with capacity, price, accessibility and cancellation fields plus source links, flagging unconfirmed availability. A second agent's audit only started after an explicit follow-up prompt, and it caught that the headline 40-person venue seated only 30 in a classroom layout.
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 59-year-old Japanese logistics worker who has never coded has the AI run 38 routines, including daily posts for three regional 'free places this week' Threads accounts; the agent published 95 posts in Oct 9-15 and one AI-written intro post passed 51,000 views. He reviews output five minutes morning and evening from his 4.5-hour commute.
A contractor coach shows his working takeoff system: he uploads construction plans into AI, which reads every sheet, note and finish item against his existing JobTread cost group of rates, markups and formulas, cites the sheet behind each quantity, and produces a bathroom remodel estimate of about $44,000 at a 46% margin in roughly 10 minutes. The conversation is saved as a reusable skill, with guardrails to show numbers before writing and stop on contradictions.
A seller has the AI use AI in Chrome to run AI, turning his own product photos into lifestyle images in batches of 10 or 20. When a batch is done, the AI builds a web page with the images and a simple way to give feedback, then uses his feedback to redo the batch. He uses this route to avoid paying for API use.
He moved his reading history from Goodreads to BookHive, onto his own AT Protocol data, and pulled in Audible data too. The AI cleaned up 389 books along the way.
His wife runs La Condesa Baking Company, a one person wholesale bakery with four cafe accounts, and all her shelf counts and invoices lived in one yellow notebook that went missing. He used AI to build Cuenta, a phone app that counts shelf stock, builds each delivery, prints and emails her branded invoice, and shows who owes what.
Connecting the agency's own MCP-based SEO service to Toby took an afternoon of wrong turns between desktop and web plugin setups, but once authenticated it created both monitored sites and completed full crawls: 44 pages for the law firm and 111 for the medical practice. Google data imports were still skipped because the service had no Google connection configured.
He runs a manufacturing business with 17 employees and a day that bounces between projects and problems. His texts are forwarded to email, and Cowork sorts his emails, texts and CRM appointments into action points; a dashboard he built in an AI app ranks them as cards in time and project order, so he just works the top card and clicks done. It is learning how long his tasks take and how far away each one sits.
After employer approval to connect workplace apps, the Business Insider reporter gave Dots an old newsletter in Google Docs plus a how-to guide, and manually shared a temporary Okta two-factor code. The Dot produced a test newsletter draft in about five minutes that an editor called 95% good, with photos, a chart and links in the right places.
A Korean solo developer's two-day diary of putting the AI to work as his team: GitHub issue labels split between him and the AI across marketing, planning, design, QA, operations and finance, with a project board and roadmap milestones built in about an hour; the AI runs QA on each deploy event and files issues; customer inquiries are answered through an admin MCP connection; and morning routines from a one-time setup (7 AM English lesson, Google Analytics analysis, issue briefing) arrive unprompted. He burned through his provided tokens in two days and estimates a 70 percent workload reduction.
Opus spent about 30 minutes and 25 dollars in tokens producing a 9-file refactor that collapsed to a 4-line change, with no time benefit to him.
He produced a Mandarin grammar lesson video from his own writing from a few years ago. The AI made the visuals with Remotion, the AI did the drawings and BytePlus TTS did the voices, and the finished lesson is up on YouTube.
Daily the AI routine checks the health of the 53 price collectors behind his compute prices site.
Gave the AI a Java RISC-V emulator and a partial libc bridge, and in under an hour it could run bash and sqlite from Debian.
Content creator Colin Rocker (someone) named his AI 'Marlowe' and set it to keep his personal website updated without manual input. Marlowe runs scheduled background tasks including a monthly scan of the internet for new press and viral posts, pulling findings into his site — but never publishes without his approval.
A man reimplemented his GIS science code from Python into Rust using LLMs, with a hard test: identical inputs and outputs at 10,000 points. Where the rewrite differed, the agent researched other implementations and tried again. The result runs 10 to 70 times faster with far less memory, and the service now does the work essentially instantly.
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.
His team is replacing a client's 15 year old system. The new system has to produce the same 60 report types as the old one, some with up to 100,000 rows, and his developers could not match the output exactly: wrong fonts, misspelled headers, rounding differences, cells formatted as text. He gave Fable 5.1 both codebases and a dump of the client's production database, and within an hour it had found and fixed every difference, down to column widths and row heights. Matching the reports by hand would have taken weeks.
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.