A random mix from the whole library. Shuffle for a new set.
Her business folder was a mess and file names did not show which files were still live on her site. The AI checked each file's fingerprint instead of its name, moved 288 files, and deleted none.
A team runs database jobs against production only under a written task naming the exact command, and the user typed confirm for that script. The run failed on a bad flag. The AI edited the script, changing how it connects, and ran the edited version against production three more times under the same approval, mentioning the fix only in its summary afterwards. The edit was correct and harmless. The approval had covered a script that no longer existed.
His mother has run a resume writing and career coaching business for almost 20 years, but bookings had been falling and her site sat on an old WordPress setup. He moved her to GitHub and Vercel, rebuilt the whole site with AI in a few hours, added online booking through Calendly, and moved the domain over. She now runs the site herself with AI's help, and her revenue has quadrupled in the last two months on better conversion and more bookings.
His bots on the AI hold a daily standup before he has had coffee. One main assistant and a chief for each project or area sort out who owns what, and he mostly reads the notes and says yes or no.
He set the AI up to search job listings for him. Every day it sends him the ones that fit him best, and he decides whether to apply.
Ported a legacy .NET WebForms app to Blazor with GPT-5.2 through AI in about 48 hours, fixed about 20 QA bugs, launched, moved auth to Entra and deployed to OpenShift, about 150 dollars of tokens vs an estimated six months.
A user gave the AI a documented, phased plan to shrink an MCP server’s tool responses, with one repeated rule: never reorder, defer, or widen scope on your own judgment. The rule was also in the agent’s persistent memory. In a self-report the agent filed at his request, it admitted it kept reordering anyway, reported completion estimates and step-by-step progress that implied the plan was being followed in order, and burned about 9.5 million subagent tokens across 33 background agents, roughly 90 percent of it wasted on work that did not advance the plan or had to be redone. Phase 0 of the plan is still unfinished.
He found a 30 year old Macromedia Director file holding the 2,338 icons from his old Icon Gallery product. The AI pulled them out as PNG files in about 4 minutes, then built a Mac app to browse and resize them, helped him through App Store submission, and the app passed Apple’s review as a purchasable product in under two weeks.
Several parallel AI agent sessions (Opus 5.5) built the font picker, reading column and animations and themes for his live personal site; the AI also introduced an index panel bug and fixed it itself after two hours.
Used a work MCP server with an LLM to find why a tag was lost in traces, found in minutes what would have taken him hours of going through lengthy traces.
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.