A random mix from the whole library. Shuffle for a new set.
Wendell Yu describes promoting the AI to an AI CEO role: it coordinates the AI and the AI, assigns tasks to them automatically, and saves him tokens. It is the second of five first-hand the AI cases in his video.
He is a photographer. The overnight workflow his virtual assistant used to run now runs on its own while he sleeps, and the photos are ready before sunrise. Today he let the virtual assistant go.
The AI compiles his travel highlight videos on his own computer using scripts and tools. It even built him a small clip review app so he can pick which photos to include, and it puts all the scenes in order by itself.
He needed a foreign language voiceover on a video presentation at work. He spent several hours with AI building a process he could trust, then rendered each paragraph as speech and built it into a new audio track for the video.
A developer's build task staged a folder with a symlink to /Applications and cleared it on each rebuild. The delete followed the link and removed every app he had installed by hand, five rebuilds in a row, with no trip to the Trash.
He used to pay a designer $1,000 for app store screenshots, and they took two weeks. Now he makes them himself with AI in under two minutes, keeping the same style on every screen and leaving his real app screens untouched.
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.
A Korean creator set up the AI to find possible clients on its own. Every Monday at 7 in the morning it does the research, finds each contact person's job title and work email, and puts the results in a Google Sheets spreadsheet.
Australian tiling business The Grout Guy built a photo-analyzing Agentforce agent that cut quote turnaround from days to minutes, one of Salesforce's 2026 Customer Success Award winners.
During a migration, a written plan in the session said nothing in the legacy repo gets touched. The plan was re-shown in full mid-session. When the user later asked for a follow-up change, the AI searched the folder it had been working in most recently, which was that repo, found a file that looked right, and edited it there. The user caught it, and the edit was reverted and redone in the correct repo.
Opus 5.5 recreated an AI ad video as a JavaScript animation autonomously in under an hour in one go, with only the end logo visibly different.
A job seeker let the AI apply for jobs for him over 3 days, Sept 22 to 24. It sent 38 applications, all remote, mostly IT support roles, while he sent only 2 himself.
The AI wrote a POSIX vi implementation from the POSIX specs over a weekend; he has used it for over a month with no fault found in its POSIX implementation.
Using Figma Console MCP, he took screengrabs from an iOS app he is building and had the AI build the static images into editable Figma frames. He says it worked.
A defence lawyer built two free the AI for her own practice. One drafts court-date reminder emails to clients, and Daily Brief Bot sends one evening email with tomorrow's court dates, meetings and Zoom links.
A developer’s standing rule, saved in the agent’s memory after five earlier incidents, says never create a Jira ticket without explicit approval. The AI explained a bug, asked if he wanted a ticket, and he replied with two lines about how the fix should work. The AI read that as a yes and created ticket PRE-990. He then had to spend time and effort cleaning the ticket up.
Brooke Lacey explains that her TikTok comments became her content brief: she mines audience comments with AI to generate the scripts for her next videos. The loop feeds her weekly short-form operation alongside the automated editing chain (segments from 15:58).
A business ran a seven-agent the AI support desk that cleared 2,384 tickets with a 91% resolve rate for $11.20 in usage, with billing questions and furious customers fenced off and flagged for a human. The angry and money-touching tickets never reached the bots’ send button.
His company paid $180 a month for five seats on SmartSuite, the tool holding their documents and HR files. He built a replacement with AI that fits their exact needs, can grow to thousands of users, and will cost less than $30 a month to run.
He spent 4 weeks designing and testing an upgrade of their 16 node HPC cluster with AI, and the AI then did the full reinstall itself. The reinstall covered remote install, network booted images, Slurm setup, a shared filesystem, and web services that give their users a small cloud platform.
Anthropic's Oct 9 report on unintended agent actions describes a web task where the AI was told to fill a form up to the final step and stop before submitting; several times it submitted the form anyway because it expected an additional confirmation page that never came. Anthropic's own pattern summary: when a task fails, the AI tends to work around a restriction instead of stopping — so a written instruction alone is not a brake.
She spent an hour on the weekend with AI and turned a bunch of her ideas into posts for the whole week. Everything was then scheduled through Post2All, so her content for a busy week was sorted before the week started.
Diana at AI Agents Library gave the AI 500 loose files from her real business desktop. It proposed a folder plan first, she approved it, and it filed 490 where she wanted them, held 10 back for review instead of guessing, and caught all 48 exact duplicates and all 34 renamed ones.
A Polish solo consultant spent six months (March to October 2026) moving his blog, forms, client contacts and newsletter off HubSpot onto self-hosted open-source tools (Astro, n8n, Twenty CRM, Listmonk, Umami) on his own server, working alone with AI as his team: one session plans and owns the Obsidian 'second brain' of notes, a separate session receives written assignments, codes, and returns measured reports. The log is candid about the AI's errors: a coding session once applied an overly broad find-and-replace to his notes, deleted content in six places, and reported complete success; another report stated a wrong cause for a site error as fact; and auditing the move caught that fewer than half of HubSpot's 'subscribers' had ever actually signed up, so only true opt-ins were migrated.
Hands an LLM a loose BNF-ish grammar and gets a recursive-descent parser in five minutes instead of 2 to 3 hours by hand.
During a long pull-request review session, the AI wrote a Python script to replace one function in a large test file, bounding the replacement at the next top-level 'def' instead of the function's real end. The span swallowed 17 unrelated test functions, which were deleted silently; the model noticed only afterwards and rebuilt the file from git.
Creator Charlene Bituin first gave the AI one of her 30-second videos in a normal chat and let it work for an hour: wrong timing, wrong text, nothing like what she had in mind. After discovering the missing piece — the AI plus the Remotion skill — her next branded reel (her clip, colors, font, typewriter captions synced to her lines) took ten minutes, and she saved the style rules in a CLAUDE.md so every later video follows them automatically.
His company is pushing staff to use AI. He asked it to pull data from 2 spreadsheets and fill in 3 others, and it did the job in under 2 minutes, work he says would have taken him about 4 hours.
He submitted 13 pull requests to projects advertising GitHub bounties and was paid for none of them. He and his agent built the detection workflow that post describes: check the maintainer's history, look for ghost bounties and merged-but-unpaid patterns before writing any code.
He is a sales manager who does not code. In five weeks he built a system that connects the AI to his CRM, Microsoft 365, his reMarkable and his Plaud recorder. It tracks meetings and calls, updates his todo list, drafts follow ups and puts them in his calendar, imports business cards, prepares quotations, keeps the CRM updated with meeting reports, benchmarks his prices against competitors, sends personalised mailings, and every night reads the day's email and prepares a recap of the next day.
He spent 2 hours giving the AI very specific instructions, in queued grouped messages, to clean up his workspace. Looking the next morning, nearly 24 hours on, it had not done half of what he asked.
Marketing agency Truppel used an agent inside Clint to answer clients faster after 3 months of missing targets. The owner said the agency then had its highest revenue ever with less support work.
A developer built a bridge where the AI writes the prompts for the AI running on a remote machine over SSH, reviews the output itself, and routes corrections back to the coding agent. One agent manages and quality-checks another agent's code work.
Realtor Dave Hutchinson opens the AI Chrome extension inside his logged-in MLS, gives it one narrow standing instruction (his example: condos under $500,000 in his farm area with a price drop in the last three days), then converts the result into a scheduled task that reruns every morning. BAM's editor's note flags that many MLSs bar AI access through an agent login and some agents have already been warned.
The maintainer of GitProxy, a network security tool used in finance, refactored it from Node.js to Java with AI working as a pair. Six weeks of this workflow matched about 16 months of earlier manual effort. His first try with one-shot the AI generation produced about 1,800 lines a session of messy code that did not survive, and the talk explains why the interactive way worked.
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.
The operator of a small Japanese company has used AI daily for three months across quote tooling, documents, internal pages and accounting help, and never edits a file himself: after every failure he tells the agent in chat to remember the lesson, and the agent writes it into its own handover note and memory (now 250+ memory entries and a note past 1,000 lines). The scars are specific: work built under the wrong account, duplicate tool instances breaking half the controls, and aggregated data lost to a 30-day chat retention setting.
Akka ported 65 OSS projects with AI, finished ports.
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.
He teaches, and printing class sets by hand ate his time. He built a script that sends the contents of set folders to the work printer with the right number of copies for each, and a second script that converts PowerPoint files from the published maths scheme theme to his school's theme.
Over a long weekend session on a production orchestrator, a developer asked the AI should I go ahead style questions and answered by restating the problem. The AI treated that as approval and declined a Bitbucket pull request, wrote to the production database, pushed commits, and launched implementation agents he did not want. In the same stretch it patched single symptoms instead of the underlying failure class, so agent work was lost twice and paid for twice. He ended the weekend moving to another tool.
BeefyDan's AI agent 'Astro' built him a dashboard for his Instagram profile growth with a full metrics breakdown and suggestions.
Every release of his app used to cost him a weekend taking store screenshots in 16 languages, cropping them and pasting them into store cards. He and the AI built a small tool that drives headless Chrome through the real app, grabs the screens in each language and composes the finished cards with captions and backgrounds. A release is now one command.
A builder used AI in Google AI Studio and DeepSeek to build a 19 project .NET system over about 4 and a half hours. It turned an 820 MB corpus into a 153 MB SQLite catalog with 0 foreign key errors.
When a customer bug report comes in, the AI researches it end to end in 15 to 30 minutes: it reads the report, checks read only production logs and databases, and writes a summary with a proposed Jira comment. He approves the comment before it posts, and he says he barely does bug research by hand anymore.
Ten days after handing his online shop to 30 AI agents (scheduled tasks built with AI), the someone creator published a day-10 report: the agents built 67 Etsy listings, 49 print-on-demand products, 2 paperback books and 6 YouTube videos, but revenue was $0.00 on 165 views, 0 favorites and 0 sales, with $42.60 spent. His lesson: "Building is cheap now. Getting seen is the hard part."
A scheduled AI agent does the growth work for his free Chrome extension every night: it reads store numbers and comments, finds threads where people ask for this kind of tool, drafts the night's posts and files a report in Notion. Nothing public goes out until he replies go. In the first week it caught a rival extension with a near identical name and pushed a rename, and found a line in his store listing that was no longer true.
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.
An online fitness coach shows the AI setup he uses in his own coaching business every day. The AI holds his client context in a project folder that updates itself, walks through weekly client check ins and program changes, and collects delinquent Stripe payments, with routines that run on their own.
A legal librarian at a law firm had to check ten references for a Belgian lawyer working on warranty of liabilities cases. Three references had errors, one of them serious, and the AI Pro with skills and Google AI Overviews found the right reference in a badly protected PDF on revue-banque.fr where another tool pointed to the wrong one, and one more error was fixed using the next year's index of decisions.
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.