A random mix from the whole library. Shuffle for a new set.
In the same CEO's US business line, an agent reviews the call-center operators' calls, transcripts and CRM results every day, then writes the human supervisor's task list with numbers and deadlines and sends each operator 3–4 small skills to fix from their own recent calls. Each skill is marked pass or fail every evening and closes after three consecutive passes; the agent only suggests — people decisions stay with people.
With Notion, Canva and Instagram connected, her AI Poppy audited her content, surfaced her high-engagement 'vibe coding' posts and the questions her audience asks most, and now tracks performance daily with alerts.
A peer reviewer put a manuscript's reference list into AI and asked it to find a web link for each one. Two references were fictitious and 13 more looked suspect, so the reviewer rejected the paper.
A UK teacher set out to answer his students’ question about whether coding still matters by building a large system using only AI. Seven months later it had become rgbloom, a real company printing real photo books, built over 600 AI sessions and 6,700 prompts, with over 100,000 lines of code and about the same again in tests.
He resells Amazon liquidation pallets on Facebook Marketplace. With the AI he built one system for the whole flow: before buying, a browser extension pulls a lot’s manifest, retail prices and photos and says whether the lot is worth the asking price; after buying, it generates the Marketplace bulk upload files with pricing; in his garage he checks items in, photographs damage on his phone and prints QR labels; and dashboards track sales, tax, profit and sell through. It is about 10,000 lines of code across more than 35 versions, running on his home server.
Haiku 5.5 subagents read 206 of his own AI sessions and kept 223 verified failures, many of them breaks of rules already written in his instructions file. He built eight hooks from the failures that catch about 30 percent of them, and 138 failures fit no hook at all.
Since July 2026 a Japanese creator has run a political clip channel with a pipeline the AI built: it watches source channels, fetches new videos, transcribes them locally, picks highlights from voice peaks and wording, fixes subtitle typos and names, makes thumbnails and titles, exports long videos and Shorts, uploads them unlisted, then collects view and retention data to feed the next round. In 3.5 months it shipped 319 videos for about 1.05 million total views and 1,080 subscribers, though the median long video reached only 268 views; he publishes the failures too, including the agent claiming 'fixed' when it was not.
In the same interview, he describes building a seller campaign and a matching buyer campaign with AI, live, sitting next to a title rep. The campaigns feed the intake stack that his AI follow-up then works.
His AI pulls from GitHub, Jira, Asana, his calendar and his email, writes up his week, and posts it to Slack without him asking.
LLM made human-like fuzzing sessions for his text editor; local Qwen babysits, investigates, writes repro and files ticket; bugs found after 1-2h runs.
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.