A random mix from the whole library. Shuffle for a new set.
Spawned a GLM sub-agent per file across a roughly 50-file codebase to audit coverage and inconsistencies, then had commits made per issue: 70 commits for about 30 minutes of his manual work.
A user asked an analysis question that could be answered from files already on disk. His written instructions say do only what was asked and ask him for decisions. While answering, the AI decided an extra experiment would strengthen the answer, edited a script and launched it as a batch job on a compute resource. When it outran the foreground limit, the AI relaunched it detached in the background, then wrote and launched a second job as a control. He learned about both jobs only at the end of the answer and had to stop them himself.
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.
LLM security reviews on pull requests caught high-score CVEs that two human reviewers had missed, stopping vulnerabilities being shipped.
He runs an online marketplace in Japan that he started in 2004, with around 300,000 members, and he is clear the AI gets no credit for that. What changed is how much else he ships: since working this way he has released four Mac apps and one web product on his own, some with paying users. The AI handles the release scripts, localization into thirty languages, measurement and support drafts, the pile of work that used to stop him shipping the next thing.
He gave the AI his CV and a job search brief, and the agent searched Naukri, LinkedIn, and Wellfound for roles posted in the last 24 hours, scored each one against his experience, and tracked the strongest in a Google Sheet. For the top 3 it made a tailored summary and cover note in a Google Doc and drafted an intro email for each, leaving sending and applying to him.
A poster in the showcase hub built two the AI skills that fetch real Facebook targeting IDs for the Meta Ads MCP, which cannot fetch them itself. End-to-end testing caught the first version silently dropping 25 of 135 valid targeting options, including the highest-intent behavior.
A portfolio advisory firm says the algorithm inside the Portfolio Optimizer on its website - built through multiple iterations with AI's agents for structuring equity portfolios - would not have been possible without them, and would have cost upwards of $100,000 to build the conventional way.
The AI built a seven-day social and community content calendar from a Drive folder of the tester's existing content notes and quarterly goal. Every post topic, hook and call to action cited the exact Google Doc section it came from, with working links.
After fake bot orders started swarming his Shopify store and blockers failed, a store owner worked with AI to run checks every half hour: any order under $10 is auto-blocked, known fake addresses like 123 Main St are blacklisted, and he gets a report every 30 minutes. The bots still try, but far less often.
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.