The solo maintainer of the karasu modeling language runs dependency updates through an AI skill that investigates each Dependabot PR before anyone merges: release notes, the diff between tags, publisher or ownership changes, install-time scripts, lockfile edges and known advisories, written up as merge, hold or reject recommendations in a design doc. In the week of Oct 10–17 three triage rounds fed 88 merged PRs (16 from Dependabot) and 12 architecture decision records, and the process caught a rebuilt lockfile silently moving a package off the reviewed version.
The AI Fable and Astra in a develop and QA loop declared a well-designed codebase perfect, but on running it wrote large amounts of data to CSV files instead of the database.
This one went wrong. See what happened before you try it.
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).
Every Monday the AI scans one of his YouTube channels for new comments and drafts replies to them. He reads the drafts, gives the go ahead, and the AI posts them with its browser. Nothing goes up without his review.
A Japanese Threads creator split his account's operation into six AI agents with one deliverable each (researcher, writer, poster, fetcher, analyst, supervisor) and reports 1,181+ posts and over 10 million cumulative impressions. The writer agent may only cite numbers stored in a single 'truth file' so it cannot inflate results, the poster must confirm the published URL rather than the button click, and the fetcher records 'not retrieved' instead of zero when a fetch fails.
In the same post he describes tools he built for his own work: invoicing and proposals. Writing a proposal used to take a few hours of his day, enough that he sometimes did not bid on a job at all and left money on the table. Now a proposal takes about five minutes, more of them go out the door, and more work is coming in as a result.
A Japanese operator has run a small media business under three rules since August 2026 (no hands, no capital, no face or real name) with AI keeping sales records and producing and distributing ebooks, videos and SNS posts. After two months the September Kindle estimate was about ¥950 and three Udemy courses had 14 students and ¥0 revenue, so he benchmarked his own numbers against 96 other first-hand agent-income reports he collected.
¥950a month
This one went wrong. See what happened before you try it.
Built with agents over about a year: a production billing system for his small telecom company, a multiplatform app, internal tools in use, and a coding agent harness now used by non-technical colleagues.
A Purdue professor built Docable, a working tool that turns PowerPoint, Word and PDF files into accessible versions for new disability rules. The AI and the AI helped him create a codebase of about half a million lines in a few months, and his talk explains the checking method he uses so agents can validate their own work.
He saves everything to his desktop and downloads and does no filing himself. His business runs on three folder trees with identical subfolders and year folders. Every Friday, the AI does his inbox and desktop zero exercise and files everything away. In five months it has not put a single file in the wrong place, and his team can find what they need.