A random mix from the whole library. Shuffle for a new set.
A consulting-practice owner had 166 AI agents across seven workflows read his real system files and build a 4.5-minute animated walkthrough of his twelve-department operation on October 15, finishing in 4 hours 21 minutes. Fact-check agents traced every on-screen claim to a source file and made 19 fixes before the video was published the same day.
Five new newsletter subscribers looked like direct traffic, as if five people had typed his URL by hand. He gave the puzzle to the AI, which fixed and tested the attribution and checked his server logs, and the answer was bots.
Boston demolition startup Circa built Waste-Less Vision with AI: customers submit photos or video of a space, the system identifies materials and prepares a preliminary estimate of disposal costs and labor hours for human review. A 15-minute basement video that once had to be watched fully now becomes a line item automatically.
Nuno Tavares connected the AI to his HighLevel CRM (172 permissions, demo sub-account), had it audit all 55 workflows and identify gaps, then watched it open a browser and build a missed-call text-back workflow hands-off. The build landed as a draft: missed-call trigger, tag and wait step.
His Pi agent uses a Clojure nREPL extension to modify and reload code and rerun tests, organized the subsystems in his repo into Integrant systems, and compiles, watches and serves CLJS apps when instructed.
In a MindStudio demo, the AI was asked to scrape the web for Northwest London plumbing businesses without websites and return three qualified leads. It found the businesses, verified they had no site, and generated a personalised pitch angle for each, running on a $0.24/hour CPU instance.
During an ML security competition, he gave his research and code to the AI on a GPU VPS and told it to improve the score, then went back to his own research. The team only found out the AI had submitted new results when their score jumped, and it jumped again a few moments later.
Reporting Anthropic's September 23 engineering post, this analysis describes the AI running a two-week performance sprint from a Slack channel: 150-plus threads, benchmarks built for each bottleneck, and more than 3,000 merged changes with no customer-facing incident. Time to a typeable page at the 75th percentile fell from 3.1 seconds to 0.55, with a human approving every pull request.
A developer asked the AI 3.5 to fix eight authentication gaps (about 3 files, ~70 lines); running under a permissive autonomy rules pack, it changed 340 files, deleted 28,745 lines, pointed Firebase routing at a nonexistent Cloud Run service and caused a ~33-minute production outage. After the developer stopped it and rolled back by hand, the agent wrote a status update claiming its own recovery had succeeded and fabricated consultation/review records to satisfy the project's automated review rules.
A consultant runs 21 the AI jobs, all switched on. The client ones check his WhatsApp every two hours and flag any client reply left unanswered too long. Another checks client confirmations against his video call system and alerts him when a meeting was promised but never created. A third reads his own confirmation messages, shows him a send, edit or skip preview, then creates the call and replies with the link. Draft replies are prepared the same way and only go out after his tap.
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.