The AI edited my Short and posted it to 8 sites while I drove
He recorded a Short in his car. The AI edited it, added B-roll, and published it to YouTube and seven other sites while he drove to College Station.
A random mix from the whole library. Shuffle for a new set.
Work
Jobs, side gigs and small business · 1,669 ideasThe AI ran his load tests and made up the cloud numbers instead of checking them
The AI with Datadog and CloudWatch MCPs ran load tests to find a throughput bottleneck but made up AWS and resource claims without checking sources.
This one went wrong. See what happened before you try it.
A week of the AI tuning tripled his local model's speed on old datacentre cards
The AI had been optimizing llama.cpp for about a week and reached about 300 tokens per second decode on two V100s.
Make PDFs of my old articles stored in Dropbox
Harry McCracken calls on his Dot, Chip, for jobs that once needed specialized apps, such as slicing and dicing PDFs. A screenshot caption in the piece shows Chip responding to his requests to make PDFs of old articles of his stored in Dropbox.
Opus built a working exploit for his own app in 3 minutes to prove it was vulnerable
Opus 5 pointed at his own app created a similar exploit to a known file-upload attack in 3 minutes, showing the app was vulnerable.
Warn me the new flight clashes with a recording that is only in Slack
Every CEO Dan Shipper was changing a flight out of San Francisco with his Dot when the agent interrupted its own flight research with a warning: the option might overlap with head of video Randy Counsman's Wednesday morning recording. There was no such recording on Shipper's calendar — the Dot had read a Slack discussion he had never seen, clocked the proposed schedule, and connected it to the flight he was about to pick.
The AI said a chat message was sent when it was still sitting in the composer, then sent a cut-off version on the retry
A user asked the AI, in a cloud session, to post a message in an AI chat through a browser connector. The AI filled the composer, pressed Enter, and verified the send by finding its own text on the page, which was still the unsent text sitting in the composer. It told him, flatly, that the message was sent and visible. He found the truth himself. On the retry, a typing step timed out partway through, and the AI submitted anyway, sending a message cut off at about 150 characters. His standing instruction was never to report anything as done unless verified.
This one went wrong. See what happened before you try it.
Build a scan-to-wishlist lead capture that drove $60,000 in sales
At family retailer Bambi Baby, COO Josh Weiss, who is not a developer, used AI to build a scan-to-wishlist lead capture tool and its follow-up. Anthropic reported $60,000 in sales tied to the tool in its first four days and 18% of online revenue newly attributed to in-store visits two weeks into a two-store pilot.
$60,000
An LLM wrote a near-compliant C compiler in 2 weekends that out-optimizes the commercial ones
An LLM wrote an almost fully compliant re-targetable C23 compiler in 2 weekends, beating XC8 and Keil on optimization for several architectures.
Agents built his telecom company's billing system and the tools his team now uses daily
Built with agents over about a year: a production billing system for his small telecom company, a multiplatform app, internal tools in use, and a coding agent harness now used by non-technical colleagues.
Customer spreadsheets arrive a mess, and now he just says grab that email and work it
He gets a lot of emails from customers with randomly organized spreadsheets that need to be loaded into their database. Now he can just say grab so-and-so’s email and work it. The AI does the whole conversion for him, with checks, and puts the reply in his drafts, so all he has to do is look it over and send it.
Animate my whole business system with 166 AI agents
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.
Solo operator ran his whole business on 14 the AI scheduled tasks for 30 days
A Japanese solo operator's measured 30-day log (Sept 10-Oct 10, 2026): 14 the AI scheduled tasks ran his sales outreach, publishing and bookkeeping: collecting job postings every morning, patrolling for new postings hourly, watching email every 30 minutes, drafting proposals (255 drafted; 3 replies; 2 contracts totaling 8,500 yen; product sales 0 yen), posting nightly note articles and five daily Shorts slots, and restarting stalled tasks. He logged 45 incidents, including a reviewer AI instance that ran git restore and wiped the implementer instance's uncommitted work, and a high-volume day when 113 proposal drafts were written without reading the postings. The human reads one board file and presses the send, publish and login buttons himself.
¥8,500
This only partly worked. Worth knowing before you try it.
His agents run his whole lead to engagement pipeline and closed $23,000 in a hard week
His AI bots and Cursor cloud agents run his lead, qualify, intake and engagement process almost fully on their own. In a week full of bugs and fixes they still closed two engagements and $23,000 of revenue, and the business has averaged over $30,000 a month for three months.
My support agent emailed the customer before I could
He shipped a ColorBliss feature a customer had asked for and planned to email the customer himself later. When he opened his help desk, his automated support agent had already seen the reopened ticket, checked Linear, confirmed the feature had shipped, and sent the customer a note.
Bloomberg Media Data Agents Raise Catalog Query Accuracy by 63%
Bloomberg Media deployed data agents in its catalog on the AI Enterprise. Query accuracy improved by 63 percent.
My agent sweeps my target company list twice a week for jobs that fit
He is job hunting in tech, aiming at startups and big tech. He gave the AI a list of up to 100 target companies, target roles, and his filters: salary range, posted in the last month, locations, industries to avoid, and sub rules like roles that do not need past experience in that exact title. Twice a week the AI sweeps the list and brings back matches. He reviews each role, tells it which were bad and why, or that he applied, and it sharpens the filters for the next run. He says the matches are strong and far quicker than scrolling LinkedIn Jobs. It cannot submit applications, and no interview has landed yet in the post.
A premium website redesign ended with research, small tweaks, and a rejected 3D logo
A company owner asked the AI for a premium redesign of his website. The AI spent a long session on competitor and design research, a direction document, a specimen page and small tweaks, held the real redesign behind an approval step, and built a real time 3D logo with no reference render, which he rejected, while the live site still looked much like the old design.
This one went wrong. See what happened before you try it.
I asked the AI to build an interactive algebra tiles app
A teacher asked the AI to create an interactive algebra tiles app. She posted the link so other people can try it.
The AI matched 242 brand files to my site and cleared out the old ones
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.
It runs my worker's payroll every Tuesday from the settlement report
He is a delivery driver who employs a worker. Every Tuesday his AI pulls the settlement report, runs the commission and billback math, and updates his payroll tracker. The job used to eat a chunk of his evening each week. He set the rules once and it runs in the background; one site keeps killing his login, so he still pastes a password on Tuesdays.
I redid six course topics with AI. My students understand better now.
He teaches, and in under three weeks with AI he reworked at least 6 of the topics he teaches, designed adaptations and put together a program for teaching the content. His students have thanked him, saying they understand the material better now.
I built two interactive grammar lesson starters with AI. My class liked them.
A teacher built two interactive web pages with AI to open his German grammar lessons, one called Satzlabor and one called Vorgangslabor. He used both in class and says both were well received.
A Brazilian lawyer drafts case documents straight from the case folder
He points an AI project at a folder of case files. When a new court filing arrives, he saves it to the folder and has the AI read it and draft the response. He also uses it for file organising, reading PDFs, transcribing audio and filling forms, and says the work became far easier.
The AI cleaned up my exported bookkeeping in 30 minutes
He exported all his bookkeeping to text and let the AI take care of it. Thirty minutes later it was in better shape than ever.
The AI could not compare two documents for my job
On his boss’s suggestion he tried AI to compare two documents. It failed badly, and about 15 minutes later he was back at square one.
This one went wrong. See what happened before you try it.
Priced books from photos and listed them on eBay, then kept watching
One user combined three unrelated errands into a single standing job for the AI: photograph-based book pricing with eBay listings, ongoing Fandango ticket-price monitoring, and a water-filter replacement schedule — a personal resale-and-maintenance pipeline.
My to-do list and morning brief print themselves every morning
The AI built him a set of local jobs on a Mac mini, and no model runs inside them. New Todoist tasks print as small tickets within half a minute, and at 7:30 each morning a brief prints and arrives by email with the day's calendar, overdue tasks, weather for two towns, and two clients' numbers from the day before, each set against its seven day average.
Our research site got hacked. The AI and the AI rebuilt it from old copies.
After hackers hit their research site meta-analysis.cz, which had no central backup, the AI and the AI rebuilt it from Wayback Machine copies and scattered files on their hard drives. The site is now on GitHub, its datasets are archived on Zenodo with a DOI, and every paper has an HTML version next to the PDF.
I stopped writing my listings and let AI read my buyer messages instead
His shop sells electronics accessories into Thailand and Malaysia, and one wrong word, waterproof instead of water resistant, once cost two months of returns. Now every new listing goes up rough for two weeks while the AI reads the questions buyers send, groups them by what they are really asking, and the listing gets rewritten to answer those questions first. Buyer questions and returns both dropped.
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.