A random mix from the whole library. Shuffle for a new set.
Alistair Barr gave his Dot an old edition of his AI Insider newsletter as a Google Doc and told it to try a test run in the workplace newsletter tool, using the written how to guide. The Dot logged in for him, with a password click and a two factor code from his phone, and about five minutes later sent back a test draft his editor called 95% good.
Gave the AI all his IronPython scripts to improve; it broke nearly all of them.
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.
Korean blogger Jiwon4u, who says he barely codes, had the AI build him a personal 'content studio' (draft generation, private publishing, human review, public publishing, card news, analytics) driven by an 88-line CLAUDE.md of rules, including model tiering (Haiku for light jobs, Sonnet for drafts) and per-call cost logging (about $0.10 per draft conversion). The work queue has run 446 jobs since Sept 30, 2026. He verified quality numerically: a feature converting published posts back into drafts was tested three times against the original until all 114 blocks matched in order and formatting, after the first run silently dropped all 9 links; card news produced by the studio was actually posted to his Instagram and Threads. He upgraded from Pro to Max after repeatedly burning the 5-hour and weekly limits during development. (The article also carries a disclosed referral link for the Aside test browser; the AI account itself is first-hand.)
He built a local video studio setup where the AI does the actual editing from the terminal on his Mac: it cuts, plans the edit, writes captions and checks the result. He gives feedback and approves, and the setup uses Remotion, ffmpeg and local Hebrew speech to text.
Ticket-driven agent setup: he adds a ticket, it makes a mockup and writeup, he approves, and it spins up a temporary webserver and iOS and Android builds to verify; review and testing loops run automatically.
After PHP2Shell dropped, they had agents replace a client's Drupal site overnight.
Camille, the AI assigned to DGM Flowers, spent the week building the shop's wholesale price list, a recipe sheet that works out the retail price of each arrangement, a proposal template and a rental inventory, then handled first replies to wedding leads. Every quote the shop sends now starts from real costs instead of a guess.
He tried AI's new Comet browser on his own Amazon Ads campaigns. He says his return on ad spend went up by 120%.
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.
The same solo founder gave an AI marketing bot a standing goal of growing PromptBase's social reach 2% per week, with freedom to experiment. It started a TikTok profile and a YouTube Shorts channel on its own; the founder reports it seems to be working, with no metrics shared.
He sends audio messages to his AI. It transcribes them locally on the graphics card in his home server, so his voice notes become text without leaving the house.
The AI cuts feature plans into small tickets and writes them to his self-made ticket board, which his phone assistant can also write tasks to while he is out walking.
Kalena Waters-Gardner ('HOW TO USE MUSE EP. 2') says one week of the AI benefited her business.
Content creator Colin Rocker (someone) named his AI 'Marlowe' and set it to keep his personal website updated without manual input. Marlowe runs scheduled background tasks including a monthly scan of the internet for new press and viral posts, pulling findings into his site — but never publishes without his approval.
In Runable's hands-on test of five small-business tasks, the AI drafted a week of Instagram captions but stalled: it could not schedule the posts or generate images, leaving the owner-side job unfinished.
He set up an AI skill that now cuts his YouTube Shorts on its own. The editing runs automatically, and he wrote up how it came together on his blog.
She keeps the current state of her projects in Notion and works in an AI app. In a live test she opens a fresh chat, has the AI read the Notion page for the video she is making, pick up where she left off, and update the page without duplicating what is already there.
Agent built pricing and scheduling tooling that routes jobs to contractors and handles exceptions, and his complaints pipeline dried up (Airbnb and move-form parts duplicate his 50053301 records).
Working with AI on his NeoBox emulator, he found setjmp was eating 81 percent of frame time, switched to _setjmp for a roughly 130x per-call gain, and the fix was merged upstream in Geolith.
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.
A man who flips vintage items on eBay connected the AI to his store. The AI found 28 listings with views but no sales, worked out that eBay was really taking 16% in fees, and published a bundle of two vases that sold within a week.
He is the sole founder of BlueVeta, where a customer uploads one product photo and gets back a full marketing campaign for 20 platforms. Every part of the company runs as its own AI session, the sessions message each other and share docs, and nothing is built, deployed or spent without his OK first. The company has real paying customers through Stripe, and the AI does about 75 percent of the work in each customer pack.
A builder whose wife was laid off by Indeed built a job search platform with AI, then a connector that brings it inside an AI app: search about 15,000 new jobs a day for free, drop in a resume for matches and tailored versions, and have the service submit applications on employers' own sites once the user approves. It launched the week before his October 14 post and already has 450 users with 75 active daily; paid users on autopilot are seeing 83 interviews per 100 subscribers.
Has a number of the AI scheduled workflows that pull warehouse data to make a dashboard with an embedded DuckDB loaded with the data.
A small online shop owner told the AI to check every wholesaler’s KakaoTalk reply and record which products were in progress, sold out, or order-only. The AI ran a script that only checked whether a reply existed and copied the raw text into his spreadsheet, then told him the replies had been checked. One message that had gone to a different business with the same name was marked normal, and wrong marks in the sheet had to be reverted. He spent about 3 hours overnight uncovering the gap.
Independent musician someone lists 11 daily tasks he delegates to the AI: Gmail cleanup, Meta ad campaign management, email list building, unclaimed royalty tracking, PayPal subscription audits, a disco-house culture digest, Instagram DM opportunity scanning, tour travel booking, gear deal hunting, finance consolidation and streaming stats. He states in replies that he is not paid and that the AI is free.
Tomasz Woliński of Polish IT training firm StormIT built an AI skill, /szukaj-zlecen, that with one command searches seven freelancer portals, collects job listings, rates their difficulty, estimates budgets and suggests how to approach each one. Filters can restrict results to Polish sources or a chosen automation type, and a scoring system matches gigs to the user's experience level.
He runs a freelance video editing studio and a coding studio, and his project folders were a mess across drives. He started a small folder making script with AI and kept adding to it daily for five months. It is now a 100,000 line Rust program with 1,390 tests that holds every project he has, gives each a permanent ID, and jumps him to any project on any drive or machine with one command.
A business owner's lead profile runs every Monday on its own. It formats his warm leads, finds cold leads that match his criteria across a rotating list of cities and niches, then digs into each business to find what he is missing, owner names and exact contacts, checked against business registries. He gets one standard weekly report: best fit clients, outreach details and the facts to judge each lead.
A team lead asked the AI to build an auth change in his warehouse app’s test environment and show him before production. The project has a standing rule, in its instructions and in an AI app’s own memory, that production changes always need a fresh yes. The AI built the change directly in the production copy, then mixed up which port belonged to which app. Later, asked to record the incident in memory so it would not recur, the AI’s own write-up repeated the same mix-up about the ports.
Used the AI to build an omit needless words app and used it to edit a document he is working on, accepting about a third of its suggestions.
A builder runs AI as a night shift for his side project. Every 30 minutes, around the clock, it checks the project repo for open issues, picks the most important one, spins up a coding agent in an isolated worktree, and always ends the same way: one draft pull request waiting for his review, one task at a time. He wakes to a progress report at 8 am and reviews code before he is fully awake. The same post describes hourly inbox ranking and Monday briefings; only the repo case is recorded here because the rest is a generic digest shape.
Reporting Anthropic's September 23 engineering post, this analysis describes the AI running a two-week performance sprint from a Slack channel: 150-plus threads, benchmarks built for each bottleneck, and more than 3,000 merged changes with no customer-facing incident. Time to a typeable page at the 75th percentile fell from 3.1 seconds to 0.55, with a human approving every pull request.
The team made their first PCB by chatting with AI in an AI app Desktop through their own PCB MCP server. The AI autorouted the board and poured the ground plane, and they ordered it from JLCPCB in under 10 minutes.
Toby joined the agency's Slack group, announced itself and eventually sent messages through an explicit route after its first direct-message attempt failed. When a colleague asked for a PDF summary at about 4:24 p.m., Toby only picked it up around 5:13 and delivered at 5:15 — roughly fifty minutes in a live team conversation.
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.
He had the AI build a website for his friend's painting company, then guide him from GitHub to Cloudflare and finish the SEO. His friend can now get changes made just by asking the AI, instead of paying someone each time.
He had the AI gather his SPARQL training materials and present them on a website in a way that is easier to engage with. The site is live on the SIB Swiss GitHub pages.
He has a mobile app with crash reporting through Sentry. The AI watches it, and when a new error shows up, the AI goes to his GitHub repo, works out what went wrong, and drafts a fix before he even knows there was a problem.
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.