A random mix from the whole library. Shuffle for a new set.
His team could not redact multilingual GDPR data from firewall logs fast enough by hand. He had the AI fine-tune a MiniLM model with EuroLLM as the teacher, and after two days of work and about 50 euros of GPU time the results were fantastic.
Guided the AI to build a fuzzer for Obsidian Sync without reading the code, functional prototype in about 30 hours, then the next 30 hours became a bug treadmill where the AI broke as much as it fixed.
The AI Flash took over his client document extraction work, now running 100 percent of 8 of 11 extraction flows, picked by a weekly eval harness.
He has the AI edit his YouTube videos end to end. It transcribes them, cuts the dead air, zooms the jump cuts, adds lower thirds, sound effects and music, and hands back a Premiere timeline.
He got the AI to hunt down all his various invoices and forward them to his accountant. It took a pile of dull admin off his plate.
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.
Pointed 11 cold AI agents at his own product and only 3 finished (result stated in the post title itself).
He asked the AI to tidy his todo inbox in milieu.cloud. It now files new todos into the right projects by itself, and it spotted a duplicate and removed it.
She pulled 50 local business leads for $0.44 and used AI to pick the ones with good reviews and a weak web presence. Then she built and published a live web app for one of them in one sitting, and says the hard part now is turning businesses like that into paying clients.
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.
In the same post he describes tools he built for his own work: invoicing and proposals. Writing a proposal used to take a few hours of his day, enough that he sometimes did not bid on a job at all and left money on the table. Now a proposal takes about five minutes, more of them go out the door, and more work is coming in as a result.
A man asked his agent to update a 1,000 line Python script using lessons from another project and left it running overnight. By morning it had made 180 Python scripts with maybe 100,000 lines of code, so tangled with imports and defensive code that it took him minutes just to find where a single action happened.
He builds the visual overlays used in car inspections in Blender. The AI creates and maintains the Blender files with him, renders them, and pushes the output to the iOS and Android repos.
She wanted to clean up her brand assets folder but did not know which images her site still used. The AI matched 242 files to the site by the fingerprint each file carries, then deleted or archived the old ones that were no longer needed.
A Google Apps Script trigger runs an AI routine that investigates issues and drafts an email before he looks at it; corrections are fed back as PRs to fix the prompt for next time.
A builder created JobAgent in an AI app: over a 13-week UK test it read and scored 8,585 job adverts against one tester's career record, wrote 481 tailored CVs and submitted 258 human-approved applications. The run produced 8 interviews and 3 offers — roughly one interview per 32 applications.
He built a small agent to sort and tag his team's incoming support tickets. It was fast and about 90 percent accurate, but the wrong 10 percent caused so much confusion that people spent more time untangling the mess than reading the tickets themselves would have taken. On edge cases the model was confidently wrong and nobody noticed for a week. They scrapped it after a month and went back to tagging by hand.
A Korean shop owner who quit his job to run his store built a two-month automation: he drops a one-line topic into a file and within about 20 seconds the system drafts the post, self-checks prices and banned words, generates four images, loads everything into the blog editor and waits for his one-word approval before publishing and cross-posting to Threads, Instagram and Facebook. Image cost is about $0.16 per post against $200 a month of AI subscriptions.
A user had the AI apply TurboQuant skills to optimise a Qwen3.5-9B model running locally via MLX on Apple Silicon. The agent applied, tested, documented and packaged the optimisation path itself, making the ML workflow repeatable.
A solo non-engineer founder building a salon SaaS commented that the AI handles his coding while an AI chat acts as strategic advisor; that week they shipped 7 PRs and found 12 production bugs in manual testing. The advisor vetoed two feature ideas and made him draft a formal contract change.
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.