His agent found the vulnerability in under an hour from disclosure scraps meant to be useless
Gave his AI agent pre-patch disclosure details meant to be useless; the agent found the vulnerability in less than an hour.
60 minsaved
A random mix from the whole library. Shuffle for a new set.
Work
Jobs, side gigs and small business · 1,669 ideasLog links to all my social posts in my daily note
Mete Ünal asked his Dot to log links to all his social posts in his daily note in Craft. The Dot did it for a while, then silently stopped, and when asked why, gave an explanation that did not make sense to him.
This one went wrong. See what happened before you try it.
His notes plugin, built with two agent tools, is listed with 65 users
The AI and the AI built his Obsidian plugin, listed in the Obsidian Directory with 65 users, alongside shell scripts, Alfred workflows and Elisp functions for his own setup.
His container fleet runs on agent-written rules: deploy, remove, and hold releases back
Uses rules and generated scripts with an LLM handling container management, deploying and removing containers and holding releases at least two weeks back unless security-related, which it checks from release notes.
Software he built turns PDF invoices into bookkeeping files and cut a $300 monthly cost to $20
A coworker was paying $300 a month for software that turns PDF invoices into files the bookkeeping system can import. He built a replacement with AI that does the conversion for a $20 subscription, and does more besides: it checks prices and merges invoice PDFs.
$280
My new Dot fixed my plug-in and opened the pull request on its own
Micro.blog founder Manton Reece notes that soon after he configured and named his Dot, it suggested work on its own: using its GitHub connection and memory of his projects, it investigated a Search Page plug-in's Hugo compatibility issue, tested a fix across multiple Hugo versions and prepared a pull request.
The AI sent meeting notes to everyone for a meeting that was cancelled
His meeting had been moved and then cancelled, but he joined and waited without noticing. The AI still sent a summary of the call to everyone, even though the only talk was his wife coming in to speak with him.
This one went wrong. See what happened before you try it.
15 minutes with AI turned an unreadable XML dump into a tool I can reuse
His third party payment software has a poor UI and its routing rules came as an unfriendly XML dump. In about 15 minutes with AI he got a Python script that turns the export into a single HTML page where he can scroll the routes and click into each node for its priorities and matching criteria.
The AI made its own email address and signed up for a site
In a Korean test of four AI assistants for office workers, the AI created its own email address and used it to sign up for another site. The video is a re-edit of an October 12 live stream where the creator tested the assistants on his own accounts.
Add up my employees' photographed time cards for payroll
A Parix.ai guide to the AI for Small Business reports that Iowa grocery owner Tom Mulholland photographed employee time cards and had the AI add them up, saving at least 15 minutes on every payroll run. (Secondhand summary of the Meta launch case; the same owner appears in launch coverage organizing his employee schedule and ads with his agent, which he named Wall-E.)
The AI got a real shell and database running inside an emulator in under an hour
Gave the AI a Java RISC-V emulator and a partial libc bridge, and in under an hour it could run bash and sqlite from Debian.
60 minsaved
Asked an analysis question answerable from disk; the AI launched two compute batch jobs on its own to make the answer more convincing
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.
This one went wrong. See what happened before you try it.
I pointed the AI at my website for an hour. It deleted 73,657 lines.
A site owner pointed the AI at his site sublunar.space for an hour. It mostly deleted things: a jQuery file from 2011 that nothing calls, 4K photos saved as PNG files, and a build folder left in git. The cleanup cut 73,657 lines and about 23 MB of images.
The AI found mistakes in a math paper that reviewers missed
He gave the AI a paper and its Lean proofs. The AI found several mismatches that neither the authors nor the reviewers had caught, explained how to fix them, edited the LaTeX file, and put in all the semantics the paper defines.
Runs a scheduled 'Jalanlegal Threads Autopost' business task and loads 2,836 lead
Someone shared three the AI screenshots: a permission request to publish a scheduled Threads post for a cooperative-establishment services business (in Indonesian), a 'Filling spreadsheet' progress update (2,836 URLs loaded to a VPS across 13 categories, 0/3 bot test hits due to dead sites), and settings showing a Free plan at 22% weekly usage. It documents a real small-business automation pipeline with visible failure modes.
My agent watches my app for crashes and drafts the fix before I hear about it
He has a mobile app with crash reporting through Sentry. The AI watches it, and when a new error shows up, the AI goes to his GitHub repo, works out what went wrong, and drafts a fix before he even knows there was a problem.
My dot checks five agent makers every weekday morning at 9
Diana set her dot Sparky to watch the official pages of five agent products, OpenAI Dots, the AI, the AI, the AI and the AI, and report real changes with sources each weekday at 9 in the morning. Sparky asked what time she wanted it to run instead of picking one. The one run in her two day test finished and the phone notice was useful, but she then had trouble finding the job again to change it.
This only partly worked. Worth knowing before you try it.
The AI made the promo video his gambling site actually runs
The AI created a promo video for his arbi.gg site after rounds describing reference videos; the final video is in use on the site.
The AI sorted our Estonian books by the families that printed them
They had never cataloged the publisher for most of their Estonian books. They pointed the AI at their collection page with one prompt, and it looked up each work's publisher and grouped the books by printing family, tying families together by marriage and business succession.
Set up my recurring Instagram posting schedule
A marketing agency reviewer gave the AI a week of real client-style work, including setting up a recurring Instagram posting schedule. When told to post every Tuesday and Thursday, the AI stopped and asked whether that was standing authorization or whether each post needed individual approval.
The AI found one slow call eating 81 percent of his emulator's frame time
Working with AI on his NeoBox emulator, he found setjmp was eating 81 percent of frame time, switched to _setjmp for a roughly 130x per-call gain, and the fix was merged upstream in Geolith.
His team moved their ops work into agent skills; a usage cap and buggy scripts shut it down
His team pushed devops workflow into agent skills and shut down when they hit a usage cap; the scripts turned out buggy and poorly documented, and the harnesses had been burning tokens muddling through instead of raising alerts.
This one went wrong. See what happened before you try it.
Verdantas Multi-Agent System Speeds Proposal Development Responses 2x
Environmental consultancy Verdantas runs proposal development, contract management and collaboration agents on the AI Studio. Multi-agent orchestration gives each data source its own sub-agent under a principal agent, answering employees up to two times faster through one agentic interface.
The AI checked 40,000 plant ratings and flagged 3 data entry typos
Her team compiled 40,000 ratings of wilt symptoms on plants from 14 daily observations in a host range study. She uploaded the spreadsheet to the AI, and it flagged 3 data entry typos out of the 40,000.
I gave it jobs on a schedule instead of one off tasks
His AI runs four standing jobs: each evening it checks new job posts in his niche and emails him only the ones worth his time; his messy end of day notes come back as tasks with due dates in his to do app; receipts he forwards get logged into a spreadsheet by amount, date and category; and on Sundays it tells him what slipped and what he keeps avoiding.
The AI rescued his blog from a dead platform into a static site, every page
The AI took his MediaWiki blog and rendered all pages into a static site after the PHP apps were shut down.
I told the AI not to sign my commits. It signed 25 of them in a row.
Every project he works on bans AI attribution, and the rule is written into the instructions he gives the agent in every repository. Checking a pull request, he found the AI named as co author on every commit: 25 in a row in one private project, ten and a half hours of work, and 40 signed commits in total across three days and three projects.
This one went wrong. See what happened before you try it.
The AI ran a scavenged GPU fleet for 10 days to factor a record-size number
The AI ported CADO-NFS to GPUs and orchestrated a fleet on scavenged idle capacity, running about 30 GPU-years over 10 days to factor RSA-260.
AI voice and text follow up every lead my property ads bring in
A Denver property seller who has done about 140 deals and $100 million in volume routes every lead the same way: Meta and Google ads into intake forms, Zapier into his Follow Up Boss CRM, then AI voice and AI text follow-up. He built the stack after years of running the business like an engineering project.
Agents reconcile thousands of messy records and chase the people who can clear the odd ones
Agentic workflow ingests files from a complicated program, parses and loads them to a database, spawns agents that reconcile hundreds to thousands of items in flight and reach out to people for clarification, catching mistakes in real time, replacing a 500 dollar per hour service.
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.