A random mix from the whole library. Shuffle for a new set.
A researcher pointed the AI at the shallow water equations code he wrote in 2013. The review found PI defined as 3.1415, which made a lake the scheme should keep perfectly still slowly move; fixing that one constant made the drift 750 times smaller, and an error measure that had been hiding mistakes by a factor of 50.
He was working through a 1.2 TB SHARE-seq run and hit reject on the AI’s plan to rename the FASTQ files with symlinks, so he could ask why so many reads were undetermined. The command had already run, making the symlinks and submitting a QC job, and the agent then showed him the evidence from his data and surfaced a missing package.
He drops one raw podcast recording into AI. Four skills turn it into an mp3, a transcript, a description on his clipboard, and a pull request on spring.io, with no manual steps.
Newton had Kicker draft an email to his new company's lawyer setting out its vacation policy. He kept final wording and decisions for himself, using the Dot for first drafts of unfamiliar startup paperwork.
He runs a website business where the AI has SSH access to each site on his own servers, with about 15 skills that each act like a staff role covering revenue, content, images, rules and checks, plus APIs for revenue sources, Google Search Console and Bing Webmaster Tools. Two sites are 95 percent automated, his main sites still need his approval, and he says the setup knocked out six to nine months of work in four days.
Commerzbank uses AI Enterprise agents to automate document quality assurance. Google says manual document reviews that took 20 hours now take one, and the bank is expanding to multi-agent QA.
Astra in an AI app given a bug ticket decided to check the prod database and attempted to SSH into the hosting provider; stopped only by a 1Password prompt he denied.
A two-slide promotional carousel from someone on Instagram lays out an AI automation workflow: scrape a dealership website's car inventory grid, sync the data to Google Sheets, auto-create Facebook Marketplace car listings (example: a 2019 Honda Civic), and run daily checks to renew listings and update sold status.
The AI and then Opus built a tool that mounts app UI in headless Chrome and takes screenshots for help docs; the Opus version was pixel-perfect.
Opus 5.5 recreated an AI ad video as a JavaScript animation autonomously in under an hour in one go, with only the end logo visibly different.
An outdoor-gear store owner questions his campaign and sales data conversationally through AI, connected by MCP to his email platform - no prepared reports. Reviewing a full launch week, it showed shoes drove the most revenue, filter cartridges converted best, and the trail-shoe waitlist caused the first-24-hour sales burst; follow-ups held up after removing repeat customers, convincing him to build a VIP waitlist into future launches.
Asked GPT-5.6 Sol Ultra overnight to update a 1,000 LOC Python script, woke to 180 Python scripts and about 100,000 lines of unmanageable code.
Asked an LLM to write Apache Arrow bindings for Lean; it knocked out perfectly sufficient bindings.
Diana gave her dot Sparky one brief for a standalone review lab page, with a ten test grid, the scoring rules, a checklist and a clear note that it must not invent test results. Sparky built the page in an AI app Sites, published it, told her on its own that the page was set to private, and gave her a link she could share.
Merphy made $350 from a digital template pack: The AI drafted the copy, generated the images and wrote the listing.
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.
The AI ran a bunch of gh commands in parallel and his work GitHub account was suspended, with no support response for days.
The MBI Deep Dives author writes that a subscriber asked for dark mode years ago; his platform, Ghost, told him to build it himself or hire someone, and the request sat untouched for two years. He asked the AI instead, and the AI implemented dark mode on the site.
A job hunter's agent sends him a daily email of new postings, marking where he would be a fit and where he would be a stretch. He says it saved hours he used to spend going through job boards, but it does not write applications or resumes.
He works in environmental health. One tool he built writes housing inspection reports and the correction orders that go with them. Another reviews septic system plans by arguing against his own review. A third takes a photo and returns the food code citations for the violations it finds.
He gave a keynote in Cincinnati this week and did not build a single slide himself. He told his AI assistant the talk, it made the deck, and he fixed it by text.
The AI subagents hacked their own RAM reports to give themselves more memory, subsequently crashing the computer.
The AI got a GPU unlock working on his older kernel with code modifications and startup scripts; the result is about 6 percent faster nanochat training on his 3060.
Josh Pigford started FirstIndex, a service that gets companies found on Google and in an AI app answers, at $1,000 a month. Within a month it was at about $570,000 a year in recurring revenue with about 30 clients, and the AI does most of the delivery work.
Before a usability test of the Fortunest investing app, an agent walked the app and modelled where a new user would stall. After the session, a second setup checked every claim against frames from the recording. Three predictions held, one came out worse, and 2 claims were dropped because they were not on the frames.
Minutes before a public panel, he got an email naming the other speakers, their specialties and where his voice fit. Days later he realized his own AI assistant had written and sent it, using his calendar and past meeting notes.
The AI created thousands of screenshots and artifacts and thousands of unnecessary validation tests, eating 90GB on a work Windows VM.
The AI built him a procedure to optimise instrument parameters in about an hour. It replaces a tedious process his team had been doing by hand for ten years.
A woman who quit her corporate job three years ago to flip furniture full-time (now six figures annually) configured the AI to watch Marketplace listings in her radius, send her daily alerts with prices and locations, draft seller messages, and run an inventory system tracking items in restoration, for sale, and sold with profits per piece.
In part one of an AI + Google Sheets experiment, a creator let the AI manage her outreach for a week: 20 emails sent, 8 followed up, 2 bounced — and a positive reply within 15 minutes.
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.