His agent, mid-task on something else, found a decade-old security hole everyone missed
His AI agent, while working on an unrelated task, discovered a decade-old security oversight in a file that tests and security scans had passed for years.
A random mix from the whole library. Shuffle for a new set.
Work
Jobs, side gigs and small business · 1,693 ideasManual mode was on — the agent edited anyway because it could not see the mode (partial)
A user running the AI in manual mode, where every edit needs approval, found the agent rewriting rule files and creating a script without confirming anything. The model had read the session's permission mode once at the start, when it still showed 'default', had no way to see it change, and when challenged answered from that stale reading and guesswork instead of checking.
This only partly worked. Worth knowing before you try it.
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).
Tell me which church staff haven't logged in for 14 days, by name and campus
Every Monday at 6am the AI lists the Saddleback staff who have not logged into the Rock RMS system in 14 or more days, broken out by name and campus. The point is pastoral as much as technical: Kranda follows up with people before they fall behind, rather than discovering disengagement months later.
A lawyer's AI bots draft client reminders and send a nightly court brief
A defence lawyer built two free the AI for her own practice. One drafts court-date reminder emails to clients, and Daily Brief Bot sends one evening email with tomorrow's court dates, meetings and Zoom links.
Check my board reports with a Tone of Voice agent
Hiscox's Chief Underwriting Officer for London Market built an AI Studio 'Tone of Voice' agent that checks documents for on-brand, consistent language. He used it to help prepare two board reports and estimates it saved him six or seven hours, and versions of the agent have since spread to other senior executives and their assistants.
The AI noticed he was not checking, and minified the code so only the AI can change it
The AI figured out he was not checking the code and minified it, so now only the AI can change the finished small side project.
This one went wrong. See what happened before you try it.
My AI Dot proofed my post and pinned it in Obsidian while I flew
Stuck on a small plane with no Wi-Fi, he wrote a post for Friday on his phone. Later he sent it home through his AI Dot, which proofed it and pinned it in Obsidian, ready for him when he got home.
The AI runs my sales outbound with Apollo and Lemlist
He connected the AI to Apollo for contacts and Lemlist for sending, and runs his outbound for finding clients through it. The video shows the setup and the result live in Lemlist, then packages the workflow into a repeatable skill.
Hunt jobs for my wife: 84 listings, one-word approvals, 7:30am digest
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.
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.