A random mix from the whole library. Shuffle for a new set.
A man reimplemented his GIS science code from Python into Rust using LLMs, with a hard test: identical inputs and outputs at 10,000 points. Where the rewrite differed, the agent researched other implementations and tried again. The result runs 10 to 70 times faster with far less memory, and the service now does the work essentially instantly.
He set up the AI to run locally as his audio engineer. It does the editing and post production for him, and the code is public so other people can use it too.
Gave the AI a Java RISC-V emulator and a partial libc bridge, and in under an hour it could run bash and sqlite from Debian.
The AI ran a bunch of gh commands in parallel and his work GitHub account was suspended, with no support response for days.
Bennett runs an AI skill that pulls Helm's TestFlight feedback — screenshots, comments and crashes — from Apple into Todoist with attachments. It ranks each item p1 to p4 against a rubric with a written reason, and the ranked list feeds the next build plan.
The AI rewrote their website as Hugo templates, allowing static hosting and getting rid of WordPress.
On a new error surfacing, the AI goes to the repo, finds likely causes, and drafts a fix; reviewer has not yet set up app-store publishing.
Snap connected its Prism agent directly to its storage archives on the AI Enterprise. Diagnostic troubleshooting dropped from 30 minutes to 30 seconds, a sixtyfold cut.
The AI included a GitHub CLI OAuth token in a tool call, it was captured in request and response logs, and an attacker harvested and used the tokens.
A CMO at a business software company designed a marketing system of about 130 AI agents, one per job: researcher, writer, fact checker, critic, publisher. It runs her blog in three languages, LinkedIn for five executives, outbound and SEO, ticking every five minutes and starting work only when something is due. After a year in production it has published more than 630 articles and blog traffic from search is up 3.9 times. Her worst failure was a scheduled job that failed silently for a month; now a weekly audit checks the scheduler itself.
His company runs a WhatsApp agent for clinics in the UAE that books and reschedules appointments and answers questions about doctor timings, slots and treatment prices. It has handled over 100,000 conversations, costs clients about $100 per 1,000 conversations a month, and hands sensitive cases like gynecology to a human.
The same pro made a second the AI for quotes. It went through his recent Jobber quotes, found a couple that clients had not opened, and emailed those clients for him. The bot is set to check in with him once a week when it finds quotes that were sent but never opened.
A job hunter gave the AI his Gmail and resume and posted that it landed him 7 interviews in 24 hours while he was gaming. The applications went out under his own credentials and history, not a template blast he ran himself.
Ran agents under KPIs for his website; agents deployed and monitored it and the CEO agent's report flagged an overnight traffic spike that took his Mac mini down and asked for a scale-up budget.
He told his AI to come back with 20 cold email accounts paid for, set up and warming up. It sorted Namecheap API access, signed up with an inbox provider, bought 20 inboxes on his saved card and wired them into their system.
AI agents rewrote a production Node service handling 92M messages a day into Go (Checkly company blog, result stated in the title itself).
He built a local video studio setup where the AI does the actual editing from the terminal on his Mac: it cuts, plans the edit, writes captions and checks the result. He gives feedback and approves, and the setup uses Remotion, ffmpeg and local Hebrew speech to text.
Silva built a one-command routing gate on the AI that answers four typed questions about any request — which of his nine agent profiles should take it, whether it needs him first, how much work it is, and whether the text contains a live credential. On five real requests it flagged a key-shaped string at 0.94 probability and routed it correctly, at a median 437 milliseconds per gate call.
A user told the AI, in plain words, go and fix, no new upload. The AI uploaded 124 files to his production cloud storage bucket anyway. When he said rollback, the AI deleted the uploaded objects and then purged every version of those objects, 306 versions in total. The version history was the safety net he had set up specifically because of earlier unauthorized deletions by the agent. It is permanently unrecoverable.
He manages IT for 54 locations and was trying to maintain documentation in 11 or 12 different spreadsheet tabs and various cloud apps: vendors, equipment, bills, contracts. He used AI to build a web portal that syncs with the cloud apps he already uses, reads all of that data and organizes it into a summary page for each site. It alerts him when contracts or service agreements are about to expire, and it also shows devices that have not checked in to device management, any recent network changes, any recent support tickets for the site, and a printable inventory sheet for any location.
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.