Ran a salon's back office for a week: built Excel order forms
Rich Rose spent a week testing the AI on a salon's back office: it built Excel order forms from color charts and handled scanned photo order forms.
429 new ideas this week
Level up how you use AI
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.
The AI built a structured dataset of all 4,925 job vacancies
He got the AI to build out a structured dataset of all 4,925 vacancies, with job titles, organisation, salary and location. He shared it in a spreadsheet for other people to play with.
A daily the AI task watches his servers and only messages a colleague about real trouble
A scheduled the AI task runs at noon every day, reads his Nagios and BuildBot status, and messages a colleague only the items that look suspect, skipping young unknown states and anything already acknowledged. It has run since May, and once skipped four days when his laptop was closed, which he only noticed 26 days later.
An agent reads his email and PDF attachments and puts his kids' school dates on his calendar
His agent reads his email, including PDF attachments, finds the dates and appointments inside, and adds them to his calendar with a check for duplicates. With two kids at different schools sending home a stream of letters, he calls it a big time saver.
His agent transcribes his voice messages on his home server
He sends audio messages to his AI. It transcribes them locally on the graphics card in his home server, so his voice notes become text without leaving the house.
An agent migrated his whole setup to a declarative system, backups included
Migrated a fairly complex setup to NixOS 1 to 1 with an LLM agent and gained declarative services, backups and redeploy tooling.
He let a team of agents run a business for a week and it made no money
A user gave a farm of Opus agents on three AI accounts one job: make money. In week one they worked through 245 ideas and killed all but one, a German e-invoice checker, which they built, shipped and advertised. It drew 68 visitors and 6 real invoice checks and earned nothing. The AI manager went quiet on day one, the other agents opened a ticket about the gap and kept working, and the analytics agent reported a 200 percent click through rate and voted to continue.
This one went wrong. See what happened before you try it.
Agents pull his banking data, label every transaction and run his budgeting dashboards
Personal finance advisor system: agents with computer use extracted data from legacy banking portals, labelled transactions, set up rules and configured dashboards on his budgeting app built to replace Monarch, with tax-loss harvesting and wash-sale prevention.
Our costing sheets price a job in 8 seconds and caught a margin squeeze
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.
The AI reads my email and keeps my United status chart updated
A United flyer in a status match challenge had the AI set up an agent that checks his Gmail for upcoming flights and adds the bookings he expects to take. It builds a chart of his progress in the style of United's own graphic and updates the chart on its own.
His team let the AI handle Sentry alerts in Slack for three months
An engineer at Sumasate writes that his team connected the AI Tag to GitHub, Sentry, their database, log tools and Notion, and let it do the first look at every alert in Slack. After three months, fixes finished inside alert handling went from about 2 of 38 alerts a month (5.3 percent) to about 7 of 44 (15.9 percent).
The AI Science rebuilt my gene check report in 15 minutes
A researcher had slowly built his own pipeline to check which parts of a human gene model are backed by real evidence, then still had to judge the evidence by hand. He gave the AI Science the short prompt 'assess this gene' and it came up with much the same rules, built the report, and did the evidence judging itself in about 15 minutes.
Cursor created a folder literally named 'tilde' in his repo
Cursor created a directory named tilde in the repo root, a scary mistake to unwind.
This one went wrong. See what happened before you try it.
Booked two Korean Air Prestige flights (ICN–SIN KE643/KE648) and a 3-night Ritz-Carlton
VC Ian Park posted a Korean-language the AI chat confirming two Prestige-class Korean Air flights (Seoul Incheon–Singapore, Sept 26–29) and a Ritz-Carlton Millenia Singapore twin-room booking with free cancellation to Sept 24. After linking the Google Calendar connector, the AI added 11 Singapore itinerary items (flights, courses, jogging, checkout).
Banco BV Agents Cut Personalized Client Communication Time by 80%
Brazilian bank Banco BV uses AI Enterprise agents for personalized client communications. The time needed to produce them fell by 80 percent.
Searched every state's unclaimed-property database by name and past cities and found
In shipwithmuse.live's errands catalog, one 'finding money you forgot about' entry reports a full sweep of every state's unclaimed-property database by name and past cities, which turned up $88.92. The catalog notes it was as reported by the build author and not independently audited.
$88.92
My agent fought Amazon over a $152.35 recharge and got it canceled
His books arrived late and he returned them, but Amazon said some were missing and tried to charge him $152.35 again. His agent Henley queued in Amazon's support chat, talked to a human rep, and pushed until the charge was canceled.
$152.35
I set a daily search for my old car and it found the dealer listing in a week
After selling his car to CarMax he set a daily the AI search for listings matching it, because he wanted to see what a dealer would list it for. It found the listing within a week.
Find, qualify and deliver freelance work autonomously
A solo developer spent about half a year building an AI pipeline of research, qualification, delivery and ledger agents meant to find, win and deliver paid work on its own. Across two cycles it discovered 10 opportunities, qualified none and won zero contracts, ending at a net loss — the system worked, but no client would hire an unknown automated service.
This one went wrong. See what happened before you try it.
His only interface now is one assistant session that delegates to agents on other machines
Runs a personal-assistant session via Signal that tracks tasks and delegates to per-project agent sessions on other machines; it is now his only direct interface.
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.