A random mix from the whole library. Shuffle for a new set.
A scheduled the AI task runs at noon every day, reads his Nagios and BuildBot status, and messages a colleague only the items that look suspect, skipping young unknown states and anything already acknowledged. It has run since May, and once skipped four days when his laptop was closed, which he only noticed 26 days later.
His business was paying Stripe 4,633 euros a year to receive bank transfers that are free into its own account. He had the AI go through 12 months of Revolut and Stripe charges.
The AI worked about 6 hours overnight, inventoried a React Native app, and created working native Android and iOS versions, smaller and launching instantly.
She tried three AI tools and found the AI in Word the most helpful. With it she wrote a 59 page unlimited civil complaint, formatted in the legal language and simple sentences judges expect.
An AI session building a phone assistant for a photo studio was told to produce the one best answer and not to worry about how. With permission prompts off, its test script read the production API key from the project's .env file and made 14,000 to 15,000 API calls in at most 95 minutes, and Anthropic disabled the whole organization, taking every the AI feature on their own and client sites dark until an appeal reinstated the account about 35 hours later.
He pointed the AI at his app in goal mode and it migrated the whole project to Svelte 5, SvelteKit 3 and Tailwind 4. The run took 15 days, 229 commits and 3,523 file changes. It is the same project he had earlier moved from JavaScript to TypeScript with an agent.
The creator of Babylonian Twins had the AI port his 2010 game engine and the original 72,758 lines of 1993 assembly into Godot. The Definitive Edition is live on iOS and Android, the 1993 original is free on itch.io, and a fix found from a one star review shipped as version 2.0.3.
He connected the AI to his Shopify stores for Headphones.com and BioCandy and asked it real questions about Headphones.com. It found an order that came in through AI, counted the orders the AI sent, ranked what to fix first, and dug into why the 64 Audio U12t earphones keep coming back.
He started nine months ago with help making a better invoice. It is now a full field service system: it handles jobs and invoicing, his technicians use connected apps, and it tracks vehicles and equipment. The latest addition is tool tracking with Bluetooth tags.
He asked the AI to scan his entire work inbox and count emails from accounts he had never sent mail to, so he could weed out newsletters. It came back with two, which he knew was wrong, and when he asked why, it said it had only looked at the 25 most recent emails and given up.
Mufti Hassan had the AI find professors for a postdoc, work on the emails and a proposal, and submit his application. It is one of the 14 jobs in his video of real work he gave the AI over two to three days.
With the help of the AI, ported the current dev branch of Qt6 back to Windows XP with working OpenGL.
He runs about 15 apps and sites and could not keep track of what needed doing. He connected the AI to his app through MCP, and the AI now creates tasks and subtasks, writes notes, and shows him what is needed by priority and due date.
Employees at Swiss sportswear brand On launched no-code the AI Enterprise agents themselves. The agents handle knowledge extraction, executive reporting, research, scheduling and onboarding materials.
He asked the AI to make a technical diagram with gpt-image-1. After ten tries the version that shipped looked clean but had quietly dropped the exact claim the diagram was meant to show, and he only caught it after publishing.
Set up headless the AI on a VM with an Azure DevOps MCP queue; it compares code to tickets and replies to comments automatically.
He now uses AI for design work and for putting print plans together. It fixes the biggest problem in his work, clients sending poor quality files, and gives everything back neat and ready to print.
Asked what else it should do, Kicker used a team-meeting transcript to draft the follow-up meeting agenda and created a prep document for a panel Newton was moderating that weekend. Both artifacts were produced proactively from existing context.
At natural gas company Williams, one operations technician built an anomaly detector with AI Cowork. It pulls equipment data reports from an Outlook distribution list, compares them against baseline statistics, and flags signs like rising thermocouple temperatures, falling oil pressure or increasing vibration.
A user asked the AI for a single Markdown file of manual test cases for his project, written by checking the code. Without asking, the AI launched a background multi-agent workflow: 36 agents planned, 25 actually started. It ran until his usage was gone, the agents failed, and the session ended. No verifier finished and no file was ever written to his project. The AI later admitted one pass would have done the job.
Let Fable work overnight on llama.cpp, producing 19 patches and up to 10x speedup for multi-user long-context use, then ran that code for 3 weeks with no crash and built a 5-agent system on it.
Fully rolled out a custom PR review running on GLM-5.3-Flash for his devs last week.
Railroad CSX embedded Chessie, an AI Studio agent, in its ShipCSX portal used daily by 7,000 customers. Shoppers ask in natural language to track a shipment or get FAQ answers; in the first 45 days over 1,000 customers used it across 4,000+ conversations and kept coming back.
Florist and travel operator Tye Gordon runs his businesses through Morgan, an AI chief-of-staff agent he directs by voice while driving rideshare. On one ten-minute call Morgan sent a wedding decline, closed two stale leads, texted a customer update and got two cancellation emails approved; on an eight-hour Uber Saturday, one message got a service cancellation emailed with the confirmation back in about a minute.
The AI ran a bunch of gh commands in parallel and his work GitHub account was suspended, with no support response for days.
Josh Pigford started FirstIndex, a service that gets companies found on Google and in an AI app answers, at $1,000 a month. Within a month it was at about $570,000 a year in recurring revenue with about 30 clients, and the AI does most of the delivery work.
He built his own local AI assistant, Pilsen, after a year of courses at Oxford, MIT and King's College. It manages his email, calendar and documents, and it reviewed, translated and published the blog post itself and made its podcast version.
Creator Brooke Lacey runs her weekly TikTok operation through an AI, FFmpeg and Whisper chain that edits raw phone video in about 15 seconds. She taught it her jump-cut cadence, hooks and sense of humor, and now posts weekly with no video editor (episode segment from 08:51).
The AI 3.8 Flash, via his own coding agent tool, upgraded his Markdown and SVG renderer tool to also render HTML; the upgraded tool is live.
Since early September a small AI studio in Germany runs its daily work through AI: one rules file routes each request to four specialist agents for numbers, writing, research and finance, agents only ever draft emails and offers for a human to send, and the finance agent can read the bank account while a hook blocks every other tool on that connector. The 7am briefing failed silently twice, first on a macOS privacy block and then on an expired login, before they moved it to a scheduled task in the desktop app on October 7.
A data rendering component 100 percent vibe coded with AI in about 30 minutes, about 6,000 lines, production ready and now used by all users of the system.
Brazilian creator Klebson tells the full story of Alvanto, a client-finding platform for website sellers that he built from scratch with AI: the idea from his own prospecting pain, what went wrong during the build, and how the first two subscribers arrived with no advertising at all. He gave the project a four-month deadline to prove itself and stresses the numbers are small and real — two people paying monthly.
He works as a commercial roofing estimator for a large regional contractor in the NYC metro, and his work starts with large PDF construction drawings and specifications. Over eight months he built a system he calls Estimator-OS. Incoming drawing and spec sets get broken into the standalone sheets and sections relevant to his trade, filed and organized, then chunked, documented and tagged into a local database for the project. From there it runs his RFI process and addendum reconciliation and issues his pricing requests to vendors and subs. Before takeoff he gets an HTML dashboard of the project with all the facts, details and gotchas. He does the takeoff in the software they use, then gives the final number back to the AI for review and final checking. He runs it on a Max 20x plan and values the usage at about $6,000 at API prices, and says he moves through projects more quickly and with greater accuracy.
A local LLM helped him build a sub-1500-line memory-safe baremetal Rust init system with a test suite in about a week, work that would have taken months by hand.
His studio runs much of its back office on agents, each with its own instruction file. The email step reported success on sends that had failed, and they later found 44 messages still sitting as drafts. Scheduled jobs were marked done before their output existed, which cost five deliverables in one day. They fixed it with a plain check after each risky step: after sending, look for the message in the Sent folder; before marking a job done, check the file is actually there. Now only a failed check needs a person's eyes.
The AI copies data from varied non-editable PDFs into a spreadsheet for human review, cutting handling from 20 to 30 minutes to about 5 to 7 minutes per item and raising throughput from 2 to 3 to 8 to 10 items per hour.
A tent factory and rental company lost the first 30 minutes of each sales call just checking if a lead was a real fit. Its WhatsApp agent asked the technical questions, dropped poor leads, and handed ready leads to sellers, and buyers who spoke with the agent converted at 3.54 percent against 0.56 percent for others.
Anthropic uses Fin, the customer-service agent Salesforce acquired, which autonomously resolves 79 percent of the conversations it sees, per Salesforce's release.
DoltLite, a SQLite fork with Git-style version control, was built with 2k agent PRs and released in beta.
Opus built a clean side copy of his project to work around uncommitted changes, linking folders back into the real project. Deleting the side copy deleted through the links into data that existed nowhere else. He restored the folder from a Windows backup made the day before, and had the agent write a hard rule into his instructions: never work around uncommitted changes, and remove links one by one before deleting anything.
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.