A random mix from the whole library. Shuffle for a new set.
A developer new to making videos drops raw files into a folder and the AI, connected to DaVinci Resolve through an MCP server, builds complete edited YouTube videos: transcribing, picking cuts, graphics and music, using a setup it built up over his last three videos. His latest video took 57 minutes, with AI showing him take options to pick from.
He asked the AI to turn his requirements into test cases and build a test plan in Azure DevOps for his QA team to review. He says the job is done.
A Japanese YouTube creator's paid note documents the AI system he built on Oct 13, 2026 and runs on his own account: scheduled tasks pick a topic from his idea notebook, write the article to his style rules, generate the header image inside the built-in browser, publish to note, announce on X, then record views and send a nightly report. In its first three days it published three articles at noon daily. Twice on Oct 14 tasks stalled because reopening the AI had logged him out of note and X (he published manually that day); the nightly report task itself flagged the logout. He states plainly there are no view or revenue results yet.
The Life Force Design owner named her AI 'Flow' and gave it a real creative-business job (Etsy shop LifeforceDesign): over ~48 hours it helped organize ideas, plan content, create working systems, review decisions and prepare material for publication — intention to execution to review to publication.
He is not a developer; he is a management trainee at a company made up of five entities. Every quarter, full financials go out to the management team: a batch of at least 25 PDFs from their SAGE accounting software, several of them over 20 pages long. He spent weeks reviewing test files and batches and debugging formatting mistakes to build his own converter, after finding that the AI models themselves could not do the job faithfully on larger documents: they would combine rows and categories or produce totals that added up but were not identical. The AI itself told him the task would need a hard coded deterministic app. His converter can now batch format the whole set at once, with the bolding, blank rows, sum lines and column sizing he is picky about.
The AI goes through his sent emails to learn which sorts he typically responds to, pings him when it thinks he left something unanswered he'd want to answer, and repeats the exercise monthly to stay current.
Andy Bennett built Helm, a Mac, iPhone and iPad job tracker with CV tailoring, with AI writing all of the code and most of the design across 641 commits and 21 plans. The first working Mac version landed in about eight hours of commits on September 11; both apps are now in TestFlight beta.
Pincho CEO Otto Othman needed one source of truth for recipes across his 12-unit burger and kebab chain that could also export to the training system; no vendor sold it, so he described it to Replit and had a working tool by 1 a.m., about five hours of work. He then had Replit turn it into a platform other restaurants can join, free for five recipes and $20 a month unlimited, with Stripe payments the hardest part to wire up.
The user's agent, nicknamed for its savings habit, cancelled Squarespace, migrated the site to Shopify, and discovered his Apple TV subscription was already free through his Chase Sapphire Reserve, activating that instead of paying.
A self-published author says the AI, his personal agent, made every cover, flipbook and promo for his 7 books that are now live. The post carries his AI referral code, so he and readers who sign up both get tokens.
His agent takes his finished films, makes short clips from them, and posts the clips itself. He reports the results have been great.
In Tye Gordon's Lauderhill businesses, the agent roster includes Hope, whose whole lane is the gap after the AI receptionist takes a call: Hope follows up on those calls and sends the customer update texts and thank-you emails, each one approved by Tye first. The design point is that an answered call is not a finished job — somebody still has to close the loop with the customer, and that somebody is an agent working from the call record.
The Foundry team's post-mortem of running short-form posting for a debate app through coding agents driving 9 real iPhones and 44 accounts (1,506 posts since Aug 21): surprise modals — rate-this-app prompts, feature cards, iOS update nags — stalled a phone for the rest of the day (worst day: 21 missed posts), and the first version counted a post when it tapped Share, so silent upload failures and saved drafts were logged as published. Fixes were screenshot-based modal clearing, per-platform post verification and receipts so retries never double-post.
Prompted an agent to build a custom LLM coding harness with session resume, done in an hour and working nearly flawlessly, plus a WebFetch tool added in 5 minutes.
He runs Nostr relays for clients. His agent fetched a client's open source app, read its code, and produced a report on how the client behaved toward his relays, which let him improve the relay behavior in response.
Got the AI to build a focus app for his Mac; he uses it daily and says he does more good work with it.
A solo founder runs his game key store with about a dozen AI sessions, one each for code, pricing, copy, bookkeeping and suppliers. They stay in sync through a shared record where facts are only ever added, each fact says whether a session confirmed it or just read it somewhere, and his decisions go into a numbered ledger the sessions look up instead of asking him again.
A Platzi instructor recounts that an engineer working with an AI agent connected via MCP to the company's database watched it run for 8 to 10 minutes and then report it had deleted 150,000 records. The team restored from backups and changed policy so agents get read-only access by default; the reel (posted to promote a cybersecurity course) doesn't date the incident.
Had the AI build an open-source source control system, benchmarked on a 100k-file monorepo as 12x faster sparse checkout and 82x higher concurrent land throughput than git.
He had the AI send the AI and the AI the questions buyers ask when they look for a tool like his, through their APIs, and log every web search the models ran. Then the AI wrote SEO pages for those exact questions.
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.