A creator documents the system his content business actually runs on: a main the AI chat ('HQ') dispatches jobs to director chats for two YouTube channels, posts on five social platforms and three SEO projects — 66 jobs and 195 chats on his board — with state in files, job cards and evidence receipts, a second AI reviewing everything before it posts, and 59 scheduled tasks doing the posting and merging. One traced job went from a radar-flagged topic to posts live on all five platforms, three hours late after Chrome dropped, with every URL logged.
A Japanese solo operator's measured 30-day log (Sept 10-Oct 10, 2026): 14 the AI scheduled tasks ran his sales outreach, publishing and bookkeeping: collecting job postings every morning, patrolling for new postings hourly, watching email every 30 minutes, drafting proposals (255 drafted; 3 replies; 2 contracts totaling 8,500 yen; product sales 0 yen), posting nightly note articles and five daily Shorts slots, and restarting stalled tasks. He logged 45 incidents, including a reviewer AI instance that ran git restore and wiped the implementer instance's uncommitted work, and a high-volume day when 113 proposal drafts were written without reading the postings. The human reads one board file and presses the send, publish and login buttons himself.
¥8,500
This only partly worked. Worth knowing before you try it.
A team ran an AI pipeline over a usability test of an investment app and saved about half a day of manual analysis. Every claim the AI made about the screen was checked against a video frame, and two claims that did not hold up were left out of the report.
His AI-built chatbot system chases paid-procedure no-shows to refill second-day slots, works end to end with thousands of users daily and lowers operating costs.
His company is pushing staff to use AI. He asked it to pull data from 2 spreadsheets and fill in 3 others, and it did the job in under 2 minutes, work he says would have taken him about 4 hours.
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 researcher runs a coaching-history project under two written skills he authored for exactly this work. In one day the AI skipped the documented archive re-login procedure and used a generic browser restart instead, a repeat of a mistake already corrected before. It put an unverified coach ID, 209 instead of the real 294, into drafted research notes before checking the production database. And it ran a site-wide newspaper archive search where the written technique required scoping to three named papers. Every error was against a procedure that already existed in writing.
This one went wrong. See what happened before you try it.
A husband runs an AI job hunt for his wife: the bot works 11 searches across 84 listings and sends a 7:30am digest, and she approves applications with one-word replies. The search runs daily without either of them opening a job board.
He runs Qood News. When the AI 2.5 was retired, moving to the AI 3.1 would have tripled his AI bill, so a decision model called Jev now decides what counts as good news and costs stay about the same. In testing Jev approved 39 of 110 stories while the AI approved 53, mostly dropping filler.