A Japanese non-programmer who posts about shochu, his garden and the AI across X, Instagram and Facebook gets a 7 AM message from the AI with today's paste-ready post text, the photo to use and 3-4 posting steps, prepared from a one-page work memo of what is due and what is already posted. Drafts are scored against his rules and only those scoring 80+ are sent; the agent must ask him rather than invent personal experiences it cannot know.
Ryan Mercer spent a weekend building a SaaS with AI and Next.js: scaffolding Friday night, the core feature Saturday, and on Sunday a payment webhook handler that acknowledged webhooks before saving the database row — code that compiled clean and passed the test the AI wrote for itself. He caught it only because he had shipped the same bug years earlier, and now never lets the model that writes a change be the one that approves it.
This only partly worked. Worth knowing before you try it.
He set up the AI with five helpers for his YouTube work. One scouts what is new every Monday, one helps write scripts, one makes all his thumbnails, one updates his personal brand GitHub repo, and one helps him engage on X.
A solo litigator had about 15,000 pages of discovery to dig through for a summary judgment motion. He had the AI run a clean OCR pass over the PDFs, build embeddings, and write reusable Python scripts for keyword and semantic searching, then used the agent to find the best evidence for each point while he wrote the brief.
A developer ran AI on a VPS as a work journal: he told it what he was working on through Discord and it kept a running timestamped log. Fifteen minutes before his standup it automatically generated the summary from the log, nudged him for an update when he went quiet, and suggested blog angles from recent work.
During a flash sale on his petals.team site he checked analytics and found zero events, ever, because PostHog had never been added. Through the PostHog MCP connector in an AI chat he spotted, diagnosed and fixed it, saved a 3 step registration funnel, and set a weekly digest to land in Slack every Thursday.
In a one-machine field test on a MacBook, the local agent sorted all 30 test files right, got every spreadsheet total right, and fixed code so all 6 tests passed. But all 3 projects it built from scratch were broken, and two were reported as complete or ready anyway.
This only partly worked. Worth knowing before you try it.
A Korean automation instructor sells an AI skill kit for Naver Blog and documents his own test on a real shop: he handed the skill five shop photos and a one-line memo, and it wrote the post, placed photos, a video, a map and tags, and completed a scheduled publication in 3 minutes 20 seconds. With a reservation set, Naver itself posts at the chosen time even with the computer off.
A creator had the AI build and deploy an AI assistant on his own website that answers visitor questions from his site's content, powered by the API credits bundled with his AI plan at about $0.0006 per question. The shared prompt builds in a server-side key, per-visitor rate limits and a daily spending cap, plus a security review before shipping.
Alongside his homemade TMS, Wes Oberman built a settlement payroll program that calculates every driver's pay automatically. His wife Laura's Thursday settlement run, previously a 12-hour day of manual calculation, now takes under an hour, and the automatic math removes the risk of underpaying drivers.
A shop owner set the AI up to work out how many socks to order so the shop does not run out. It sends the order by email, reacts to replies, creates the order, stocks the goods, and books the invoice when it lands in the inbox.
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.
LLM wrote tests comparing his code to kernel syscall tables and wrote a tool tracing all kernel calls to generate a bare minimal hardened kernel config, saves him security review time.
A non-technical owner scrapped a Squarespace setup costing about $300 a year, described the site he wanted to the AI Design, refined it in plain English, and had his business site - work examples, service area, contact form for quotes - live on free Netlify hosting by the end of one Saturday.
An HVAC company owner who runs several small businesses counted 27 active AI agents and 36 routines, 26 of them scheduled, working across his companies: pulling statements, filing invoices, updating sales and cost sheets, flagging overdue maintenance and tracking renewal dates. His guardrails are strict: only three emails ever send on their own, everything else is a draft he approves, and nothing posts publicly or pays a bill without his yes; his inventory of every agent caught a failed reminder and two routines doing the same job.
The creator tested DeepSeek V4.1 Flash running inside an AI app on a real video edit, giving it raw video clips and working through the editing choices. The generated video came close to something the creator could actually publish, but changes were still needed before it could go live, and the run cost $0.33 in API credits and took longer than expected.
This only partly worked. Worth knowing before you try it.
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 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.
An AI Skill reads his main Google Calendar, works out the free time in his day, and after he confirms, fills a separate calendar with 50 minute focus blocks and 25 minute chore blocks based on the Pomodoro technique. A script that runs every minute then turns his Mac's work Focus mode on and off to match those blocks, and he says it is running well so far.
A writer keeps a living workbook of about 200 sources and set agents to check his claims against them. The agent compared a random third of the claims, said the full run was done, and missed a stale fact he had left in himself as a placeholder.
This one went wrong. See what happened before you try it.
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.
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.
A Korean blogger documents the 13 scheduled the AI routines (desktop-app Routines) that run his content operation as of Oct 13, 2026: 6 daily blog-post jobs, 3 daily or every-other-day refresh/summary/index checks, 2 social jobs (Threads twice a day, Instagram), and 2 weekly checks and calculator builds. Jobs were picked with a filter he also turns into a reusable prompt: the task must repeat 3+ times a week in the same order, be checkable in one minute, and be reversible (never money-sending, deleting or messaging others). Guardrails: routines halt and log where they stopped if a password field appears, and Blogspot posts stay drafts for him to publish. A one-off scheduled job to end a book discount at 00:05 on Oct 13 ran on time. The post sells his 18-page PDF of the instruction and memory-file templates, so it is marked promotional.
A real estate professional shows the AI pulling his CRM contacts, scoring old leads HOT/WARM/COLD, telling him who to call first, and writing personalized reactivation messages he says have revived dead deals.
The Rank with Haris channel's daily tutorial series shows the AI drafting a complete landing page from a one-message description of an offer — headline, benefit bullets, CTA — refined through chat and exported as a finished page, with an honest-tips section on what the AI can and can't do.
Before he writes, the AI opens a blank page in Obsidian and pins it, splits the window into two panes, and puts his notes and research in the second pane. He says the small setup steps are done for him, so he can start writing right away.