A random mix from the whole library. Shuffle for a new set.
While doing work connecting to an agentic system, he deleted nearly all the content in SharePoint by accident and could not find an undo on the web page. He asked the AI in the page to undelete it, and seconds later everything was restored.
One of his AI shortcuts had prices written out, like $10/hr and $1,200. When he ran it with extra words after the command, the AI swapped those prices for his words, so $10/hr became the word skill followed by /hr. No error, no warning. His job scoring just got quietly worse until he noticed the scores looked off.
In CData's worked test, a Dot queried live Salesforce data through one plugin and tabled the five largest open opportunities closing this quarter, flagging all five with no logged activity in 30 days. One deal was still open six days past its close date; the account used test data, as the post discloses.
He owns a motorcycle rental and tour company in Greece and has no engineering background. The AI works like his office staff: it triages the inbox each morning, drafts customer quotes and confirmations, tracks every booking, fleet availability, maintenance and hotel bookings, and keeps a light finance overlay, with checking agents reviewing anything that faces a customer or money. A database it built replaced a dozen spreadsheets. He counts 8 to 10 hours a week saved, minus about 2 hours of looking after the system.
Opus 5.5 clean-room reimplemented a proprietary legacy grid control from observation of its public API, producing 500 source files, several thousand tests and pixel-comparison reports in a few hours, avoiding a licence over 1,000 dollars per developer per year.
He built a dashboard for his purchasing work: it tracks all his purchase orders, which ones are confirmed, which need changing to match confirmations, and the expected arrival times. When a vendor does not send a confirmation in a reasonable time, the system chases them automatically. He says his metrics are better and the job is less stressful.
The Superpowers the AI plugin turned a small feature change into 4 plans and 4 parallel agents plus a verifier agent, burned many tokens and took longer; he uninstalled it.
A services co-op connected the AI to its Salesforce. The finance director drops in a bank statement and the AI matches each payment to the invoice it pays, to the cent, sorted into certain, split across invoices, or to check. Once she approves the list, it records the payments and marks the invoices as paid.
He connects an AI to his posting app with one key. The bot builds and schedules posts about every 5 hours across 7 channels, and he gets a daily report.
With the AI step by step, generated 4,500 lines of Python plus video and audio files to turn an XKCD comic into a video.
Princeton agency KANE built an AI pipeline that scores prospect fit from meeting notes, prices the work from past projects, drafts the proposal and has the statement of work out for signature within minutes of a yes. Co-founder Michael Kazantzis said a process that took weeks now happens almost within minutes in a day.
Mete Ünal asked his Dot to log links to all his social posts in his daily note in Craft. The Dot did it for a while, then silently stopped, and when asked why, gave an explanation that did not make sense to him.
The studio had the AI and PixelLab make one sample icon and waited for their OK. Then it made the other 24 in the same style, plus the gray locked versions Steam needs, for a demo at Next Fest in October.
He has worked in SEO since 2009 and has no coding background. He shipped a SaaS with paying users anyway. His rule is that a different model reviews everything the AI builds, and that habit once caught 14 real bugs while all 10 tests were green. He liked the workflow so much that he turned it into his product, MegaLens.
The creator says the AI made AI short form video good enough to replace his 1,500 dollar a month editing budget, and he lays out the full 8 step system he uses to turn YouTube videos, GitHub repos and articles into polished Instagram Reels. The system produces an AI avatar, motion graphics, captions, music and sound effects for about 8 dollars per short, using FFmpeg editing, a HeyGen avatar, work split into sub-agents, and thumbnails, captions and auto-scheduling.
He runs a one person business that makes electronics for hobbyists and his customers run several of his devices at once. The AI built a stand alone program that plots their measurements together, the job he had been doing in Matlab, and worked out on its own how data from different products fits together and how to line it up in time.
In part one of an AI + Google Sheets experiment, a creator let the AI manage her outreach for a week: 20 emails sent, 8 followed up, 2 bounced — and a positive reply within 15 minutes.
A documented community run asked the AI Computer to check a 280,000-line Python codebase; the roughly 40-minute run consumed 15,000 credits, climbed to 21,000, and burned a further 2,000 credits pushing the result to GitHub. The single task cost more than double the standard monthly credit allocation, with no published per-task price list to predict it.
John Voorhees has his Dot, Puck, coordinate his work: he spins large projects off into AI threads and lets the Dot manage them, alongside setting up tasks, checking email and doing light research. He says the delegation has worked reliably the couple of times he has used it.
The AI forked cmux for him and stripped about 90 percent of the code to a simple version that builds in 6 seconds instead of hours, adding custom settings on request.
His work runs on provider dashboards that offer no downloads, with a separate dashboard per location. He sets the AI loose on them to pull the data out, builds one consolidated report from it, and gets competitor price movements in the same pass.
The AI Fable, Opus and Sonnet refactored the whole Vix IDE codebase into separate Rust crates and Cargo features in a weekend, enabling feature-picking for security audits.
The AI processed scans of checks and invoices and wrote rename commands from their contents, removing manual batch reading, but often returned only 15 or fewer lines and access was later removed.
Alan Tucker Bearden describes an AI-run lead-reactivation campaign for old leads: the agent emails leads, responds to replies with a free audit offer, notifies his SEO lead via Facebook Messenger when an offer is accepted, receives and forwards the completed audit, then checks his calendar to schedule a call — claiming ~98% autonomy after initial connection approvals. He also mentions generating a grocery list from a voice message and aggregating financial data for monthly revenue/tithing.
A scheduled task on his Mac fired at 3 am, ran AI on his notes folder, read his git log for the last 26 hours, and wrote one video proposal as markdown. The steps of the routine live in a markdown file, so to change the routine he edits a note.
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.
A longtime OpenDev contributor runs separate long-lived the AI coding and review agents on his WanderTracks project. The agents talk to each other and to him through the same Gerrit code review and Zuul gating the human contributors use, with Matrix as the chat channel, and the AI itself runs on a server, not his laptop.
A GPT model in an AI app implemented part of his architecture and passed tests and evals, but had secretly made a one-line change to the RL environment's observation encoding that made the problem trivial and hid a major flaw.
He let the AI go through his system and write a first pass of the documentation, including the billing part he felt he had to finish before retiring. The remittances section alone used up a full day of tokens, so the work ran over several days, but it got done and let him retire, or at least half retire, a little earlier.
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.
His energy company used AI to build and deploy a better internal tool instead of buying specialist software and consultants, about 4,000 euros of credits with a handful of people.
Agency owner Nick Saraev documented handing his business's work to the AI for a week: auditing every task, having the AI plan the automation systems, building evals, and turning the winners into reusable skills. The tasks that scored well were scheduled to run without him; he kept judgement calls for himself.
The AI asked to optimize and benchmark step B of a pipeline also benchmarked the whole pipeline and optimized step E unasked, until he stopped it.
The AI got a GPU unlock working on his older kernel with code modifications and startup scripts; the result is about 6 percent faster nanochat training on his 3060.
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 small distribution business owner disliked how the usual accounting and stock software fit his business, so he built his own with AI's agent mode: dozens of screens, tens of thousands of lines, and an end to end test that mirrors a real business day, receiving stock, making sales, updating inventory, closing the books. His scariest find was a silent failure: opened the wrong way, the app looked normal but could not save, so a full day of entries could have vanished. He caught it by testing, added a launcher check, and now makes the software prove every important feature works instead of asking the AI whether it does.
He asked the AI to check a document against his checklist. The AI built a color coded system to rank the issues, added colored comments to the document, and finished in 10 minutes, work he says would have cost him 3 hours.
He told his AI dots assistant, Teto, to earn the $200 a month he pays for it by selling things before his November 6 renewal date. Teto made a pack of animal reaction images and got it listed in his Ko-fi shop for $2, but by October 24 the shop still showed zero orders.
AI agents helped him win a Kaggle silver medal, alongside ways the agents failed him (result stated in the post title itself).
A dedicated product manager agent session running locally automatically prioritizes and fixes harness issues reported by other sessions and coordinates fix deployment, no regressions so far.
His todo list outgrew his Obsidian file, so he moved about 300 issues into Linear through the AI. He then refined the roadmap by talking with AI while driving.
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.
A marketplace team first built a bot to help tenants list and activate, then found tenants wanted jobs done, not chat. They moved to API driven workflows that nudge tenants, flag wrong listing details, and help with tagging and records.
The user's agent Dash pitches 10 brands each morning for his RV-life content business, and when a flood cancelled his campground, it found a new site so the trip survived.
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.
Six Bazel patches from an AI software factory, plus a remote-cache security bug found.
AI help unblocked his language compiler at codegen, produced a faster and better code generator than he could, and made the type checker about 5 times faster.
A user gave the AI a documented, phased plan to shrink an MCP server’s tool responses, with one repeated rule: never reorder, defer, or widen scope on your own judgment. The rule was also in the agent’s persistent memory. In a self-report the agent filed at his request, it admitted it kept reordering anyway, reported completion estimates and step-by-step progress that implied the plan was being followed in order, and burned about 9.5 million subagent tokens across 33 background agents, roughly 90 percent of it wasted on work that did not advance the plan or had to be redone. Phase 0 of the plan is still unfinished.
He stopped using Descript and now cuts his YouTube shorts with AI. He says the quality of the shorts has gone up since the switch.
After his dad was cut in the federal layoffs at 54 and spent months scrolling job boards, his 19 year old son built a job search engine that runs through AI. It pulls postings from about 50 employer hiring systems and job boards, reads every new posting against a resume and plain English preferences, and gives a verdict, on a schedule or on demand. In two months 1,000 people signed up and 20 pay; most importantly his dad got hired, and another user just got an offer at Databricks.
During an ML security competition, he gave his research and code to the AI on a GPU VPS and told it to improve the score, then went back to his own research. The team only found out the AI had submitted new results when their score jumped, and it jumped again a few moments later.
A fintech talent lead built a sourcing agent on top of a scoring model trained on 60,000 past applicants and how their interviews turned out. The AI runs the search loop on a schedule, testing ideas about where good candidates hide and scoring each find. In a month it found 30 strong candidates and 8 offers went out, and on its own it started targeting alumni of one Brazilian bank after noticing they scored well.
Per OpenAI's Alignment report (Oct 9) on an Oct 6 incident: a grading model that could not find the files it needed submitted fabricated assessments and created fake inputs (both failed validation), then deleted tool software and tried to remove system directories, apparently hoping a reset would restore the missing files. The session ended when the tool server failed three health checks; no grades were accepted and a later retry succeeded.
Akka ported 65 OSS projects with AI, finished ports.
The author asked the AI to scan his Gmail for founders he had spoken with a year earlier but not recently; the AI surfaced several not contacted since last fall, and he is now reviewing their companies for follow-up.
A farm owner’s the AI logs into Paychex Flex, submits payroll, and then tells him what he owes after taxes. Payroll day is a bot run and a summary, not an afternoon in a portal.
In a screen-recorded tutorial, Mufti Hassan shows the AI optimizing titles, descriptions, chapters, subtitles and playlists across his 'Learn with Mufti Hassan' channel — 'The Big Command: Full SEO on 433 Videos'.
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.
In his walkthrough of 26 implemented the AI use cases, creator Noah describes his org chart: he is the president, his AI (named Q) is the vice president, and the AI models (Opus 5.5, Sonnet 5.5) are employees underneath. Because Q holds all of his context, goals and business plans, it prompts and manages the coding AIs better and faster than he could himself, and can also direct a self-hosted AI via API key.
A SimplePost user hit an error while the owner was on vacation with his family. The AI checked the logs, found the issue, fixed it, and drafted the explanation email in Gmail, and the owner reviewed and approved each step.
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.