An agent added source control to his editor project, months of work in about 2 weeks
Agent integrated libgit into his IDE project to add source control, work that would have taken months by hand, done in about 2 weeks of calendar time.
A random mix from the whole library. Shuffle for a new set.
Work
Jobs, side gigs and small business · 1,665 ideasRun my .NET app on your cloud computer — backend passed, full stack failed
Via the Slide Factory review, a developer on OpenAI's forum reported testing a .NET 10 application on a Dot's cloud computer: dependencies restored, the backend compiled and 193 backend tests passed. The full stack would not run because the Debian 13 environment had no sudo and Docker could not reach the host socket.
This one went wrong. See what happened before you try it.
The AI runs my returns and cancellations chats and paperwork for me
He has the AI run the live chats and online paperwork for his returns, cancellations and similar chores. He calls it life-changing.
I filed a 59 page civil complaint I wrote with AI
She used three AIs to cross check each other, mostly the AI in Word, and in about two weeks wrote and filed a 59 page unlimited civil complaint for her own case. The lawyers tasked with that work charge $300 an hour.
Pull my Meta Ads data every morning and rank winners and losers (replacing Foreplay)
Business owner Shane Duggan says in an Oct 13 reel that he replaced Foreplay ($175/mo) with an AI automation that pulls his Meta Ads data every morning into a dashboard ranking winning and losing ads. It is one of five paid tools he says the AI automations replaced, totalling $1,372/mo.
$175a month
The AI built a failover for his busiest app in 2 minutes and saves him about 200 dollars a month
The AI built a primary/secondary API callout in 2 minutes after he ported his busiest app stage to Haiku, saving about 200 dollars a month.
$200a month
A loose prompt wasted all his tokens rebuilding a tool that already exists
Mis-prompted the AI on a toy project; it wasted all his tokens building a specialized Docker clone instead of building on Docker.
This one went wrong. See what happened before you try it.
I built my whole consulting business with it, website, LLC, EIN and bank account, and got my first customer
He noticed people in his area were hesitant about AI and decided to start an AI consulting business. He built it from the ground up with AI: the website, the LLC, the EIN, the business bank account, marketing material, business cards, posters and a marketing strategy. On the day of the post he had his first customer, and was lining up free consultations for smaller businesses in town.
The AI turns each podcast episode into a short video on its own
For several weeks his system has taken each new podcast MP3, transcribed it, picked a strong clip and built a vertical short with about eight animated scenes using Remotion and the AI. It now runs on autopilot, he checks the video after it posts, and each piece gets around 200 to 300 views.
Published a post in her public Facebook Group via AI's browser after
For the Group step, the AI said its connection's group tools were read-only, so Diana gave it the Group link and signed in to Facebook through its browser, watching each step. The post published; she checked it live on Facebook.
His agents run two QA skills before every pull request, with video proof
Wrote two QA skills his agents run: one scans the app and writes an invariant matrix, the second implements critical flows as e2e tests run before PRs with video and screenshots posted in the PR body.
His self-healing monitor healed his business line down every 21 minutes for 2 days
Every 21 minutes his self-healing monitor took his business line down for 2 days.
This one went wrong. See what happened before you try it.
Ran an automatic playlist pitcher: researched genre-matched Spotify playlists and sent cold
Independent musician someone lists three career assists from the someone agent: an automatic playlist pitcher that researched genre-matched Spotify playlists and sent cold emails resulting in a placement, an EPK refresh that auto-checked streaming stats and compiled clickable social links, and data-driven venue pitching across new cities. No compensation from Meta disclosed; referral code IH600W shared.
I built an online game on a Raspberry Pi between farm jobs. It made $3,000.
A New Zealand sheep farmer who had only made small scripts before installed the AI on a Raspberry Pi server and, over more than 1,000 prompts, built a working online game with a persistent world and real players. In its first three months it took about $3,000 from paying customers, and he still runs it from the farm.
$3,000
A sandboxed agent checks daily whether the product spec and the code still agree
Sandboxed agent checks spec and code drift daily, triages findings, and surfaces issues; it revealed product miscommunications on the team.
Non-engineer lets the AI run his note publishing operation overnight
On Oct 2, 2026 a Japanese non-engineer asked the AI to run his note account for monetization; the agent picked the niche itself, then researched, drafted and self-reviewed 12 manuscripts during his 5-hour nap, reaching 42 drafts by the end of the day. It now plans topics, writes drafts, creates header images, registers the posting schedule in Google Calendar and prepares X and Threads announcements, batched a week ahead for his approval. The AI’s own safety feature stopped it from pressing the X post button; he keeps five jobs human: purpose, identity details, the final post button, personal experience and publish approval.
OpenAI deleted my dot's VM and hours of work were gone
A person's OpenAI dot could not push its work to GitHub. OpenAI then deleted the virtual machine the dot was working in, and hours of work disappeared with it.
This one went wrong. See what happened before you try it.
I turned 250 old newsletters into a live blog that Google now sends people to
He had about 250 old newsletters sitting on beehiiv doing nothing. He fed them to the AI, had it turn them into blog posts, and the blog is now live with Google already sending readers to it, giving him a new funnel in a couple of hours.
The AI reverse engineered his video editor to add the audio format it was missing
The AI reverse engineered the Linux version of DaVinci Resolve to add AAC support; the patch is published and works.
Run my one-man startup with a team of bots
A solo founder runs PromptBase on a small AI team living on a Linux server: a support bot answers customer email from his Gmail, an engineer bot writes code, a security bot watches Cloudflare and server logs - and the bots have fixed a customer bug together without him, while he managed them from a phone on a five-hour hike in Wales.
Deutsche Telekom Agents Query Data Across Clouds 4x Faster
Deutsche Telekom pairs the AI with Google Cloud's borderless Lakehouse to query data across clouds, including Amazon S3 and Azure Data Lake. Thirty thousand users now analyze data four times faster.
The AI ran his two YouTube channels overnight, and the lesson was the silent failures
A creator handed the AI his two small YouTube channels: scripts, voice over, image prompts, renders and comment replies, with one hard rule that anything public waits for him. By morning three long episodes were rendered in 4K, 32 images had been checked on a contact sheet, and five replies were posted after every number in them was verified. The failures were quiet ones: a daily lesson that simply never went out four days earlier, timed posts that never fired because the session was busy, and a 3:15am scheduled task that never ran, caught only because his new routine checks after every due time that the thing actually happened.
This only partly worked. Worth knowing before you try it.
The AI cleaned up my business files: 288 moved, none deleted
Her business folder was a mess and file names did not show which files were still live on her site. The AI checked each file's fingerprint instead of its name, moved 288 files, and deleted none.
Solo founder shipped his fifth product in three days and let the AI do all the design
Jacob runs four AI products alone. He built Tracetify, a tool that rebuilds how a competitor got its first users from twelve public data sources, in about three days, and gave the AI one instruction for the whole interface: you decide. Users later asked whether he had hired a designer.
His AI setup routes tasks from chat and tickets to the right repos and opens the PRs
Cyrus and the AI system routes Telegram and Linear tasks to repos by label and opens PRs for review; he is more hands off across multiple projects.
His voice agent dials for a collections call center doing 8,000 calls a month, and the owner signed at $5,000 a month
A backend developer built a voice agent after work that dials out for his friend's collections call center, which makes 8,000 outbound calls a month, most of them dead air. The agent greets the person, works out if they are interested, not interested or want a callback, and hands live prospects to a human with context. After a free trial the owner signed at $5,000 a month.
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.
Prepare me for my call — from the right email thread, unprompted
In AI Agents Library's structured 10-task business test (Sept 27, 2026, free plan, real business material), Diana gave the AI almost nothing for meeting prep: it found the correct email thread among several plausible candidates, located the calendar invitation, and prepared questions — including some she had not thought of. The task scored 10/10, the best result of the test day.
Run back office for my nail salon and yogurt store
In a #metapartner showcase, entrepreneur Krystal Oh — who runs a nail salon and a yogurt store solo — shows on-screen chats with her AI 'Coco' handling back-office work: drafting a refund request for an empty box of masks, remembering meetings, sending notifications, helping manage expenses, onboarding employees and scheduling calendars. She says she previously spent thousands on human assistants who never understood her businesses.
The AI checked if my NMR experiment could work while I ate dinner
He had an idea for an NMR experiment he had been sitting on for years. The AI did the literature review, found reference data, ran spin and spectrum simulations, checked if the idea could work, and compared it with other methods, all while he ate dinner and watched TV.
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.