Monitored Newark-to-Haneda fares for a 3-month January trip; found a $2,000 United
The Tremendous blogger asked the AI to watch Newark-to-Haneda fares for a January trip. It searched well and found a $2,000 United ticket.
$2,000
427 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.
I updated a whole website with AI in under an hour, and it edited the video too
He updated kim-olsen.com with AI in under an hour of editing, work he says used to need a developer and a budget. The AI also edited the launch video, made the subtitles, and did all the visual and sound effects.
The AI read an 860 page climbing index and mapped 35,125 entries
He set the AI to work on the 860 page American Alpine Journal master index, covering 1929 to 2024. It read 35,125 entries and 94,081 page references and mapped each one to a mountain region.
The AI matched about 40 web pages to their designs exactly, where screenshots had failed
Set up the Figma MCP with AI to match web pages exactly to Figma designs across about 40 pages, where feeding screenshots had done poorly, and it did what he needed.
I asked the AI to make the piano more expressive and it did
She gave the AI a music score file and asked it to make the piano more expressive, saying a large part of it was pulsing the big beats in 6/4, and told it it could download YouTube videos for reference. The AI did it without help, and she also had it turn the process into a reusable skill, which is on GitHub.
The AI converted several thousand firewall rules into the global rulebase
Had the AI convert several thousand firewall rules to FortiManager global rules.
The AI built it, and my todos now sync across my devices
He keeps all his todos in Things, but Things has cloud sync and no official API, so his AI could not reach them. He told the AI to build it, and a minute or two later his todos were syncing from his LLM across all his Apple devices.
An LLM cut 60,000 useless lines from his test suite and fixed bugs it found, in about 2 hours
LLM audited about 100k lines of tests, deleted about 60k useless lines, wrote broader scenario tests, and caught and fixed bugs, in about 2 hours.
Audit two years of my grocery receipts and build me a Kroger-vs-Amazon lineup
A homeschooling mom posted on Facebook on Oct 20 that she handed the AI (her agent 'Mira') two years of grocery data — all 140 Kroger orders plus her Amazon history, line by line. Mira found her worst leak (cat treats bought 16 times in nine months, at full price 14 times; the subscription price would have saved about $96 a year) and built a categorized lineup assigning every staple to Kroger or Amazon with prices shown.
$96a year
Three blogs run by an agent stalled for three rounds on an AI review gate
A Korean content operation handed three channels (Naver blog, Threads, WordPress) to an AI agent publishing at 9:00, 13:00 and 17:00 daily, logged over Oct 15-18, 2026. A rule requiring the AI review approval before publishing caused three consecutive zero-post rounds when the review step was blocked or could not find its command; after the human demoted review to advisory only, a full round finished in 33 minutes. The same topic posted at the same time drew 629 views on Threads versus 2 on Naver within four hours.
This only partly worked. Worth knowing before you try it.
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.