A random mix from the whole library. Shuffle for a new set.
Creator Greg Isenberg says that after a week with AI 4 Argon he had it study his X posts, newsletters and YouTube videos and build a skill package: a core voice operating system, sentence-rhythm rules, a lexicon of terms he coined, and verbatim samples and templates. A post it then wrote on marketing engineers was self-scored 9.2/10 by him.
The AI Launch team reports a live test where a managed the AI Agent, given one chat instruction, searched Vast.ai for an RTX 4060 Ti under a $0.40/hour cap, rented it, rendered a 1920x1080 Blender frame over SSH, and destroyed the instance. The whole cycle took 194 seconds and cost $0.007.
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 added a weekly ops review to his AI chief of staff bot. Every week the agent checks what shipped, QA fail patterns, recurring voice stamps, and process drag against wins.
Used GPT-6 to develop a new barcode scanner library, built a labelled real-world test suite, and published it for JS, Python and Rust.
In Tye Gordon's Lauderhill businesses, the agent roster includes Hope, whose whole lane is the gap after the AI receptionist takes a call: Hope follows up on those calls and sends the customer update texts and thank-you emails, each one approved by Tye first. The design point is that an answered call is not a finished job — somebody still has to close the loop with the customer, and that somebody is an agent working from the call record.
Mailing thousands of people brought hundreds of auto replies that nobody read. The AI scanned them read only, flagged who had left or changed roles, and updated Mailchimp, leaving a cleaner list and better deliverability.
The AI ported CADO-NFS to GPUs and orchestrated a fleet on scavenged idle capacity, running about 30 GPU-years over 10 days to factor RSA-260.
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.
A Business Insider Japan writer set up six AI bots besides his main one and has run them for about a week. One checks his to-do list and pushes him to reschedule, one picks out mail that needs a reply and drafts it, one pulls expense items from mail into a spreadsheet, and one looks up missed call numbers in his mail and contacts and sums up who called.
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.
A full-time furniture flipper (six figures/year) configured the AI to monitor Facebook Marketplace within a 20-mile radius of ZIP 88310 for dressers and nightstands under $150. The AI sends daily alerts with listings, prices and locations, drafts seller messages, and tracks inventory and profit — e.g.
He runs a print shop full time and is not a designer. The AI designed about 35 formal disinvitation cards with him, drove the browser to set the products up on Fourthwall with prices and descriptions, built the website, and synced the catalog to Etsy with new main photos.
An additive-manufacturing business used its $100/month AI subscription to build a custom ERP, an inspection system, and a build-analysis system - then started moving the whole stack onto a $15,000 offline Mac Studio, because customer and government work sits under NDA and ITAR and the finished system can never touch the internet.
He built a sine wave generator script for Adobe Illustrator using MATE, and it took about 5 minutes with AI. The script is now free for everyone in Astute Manager Pro.
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.
The AI wrote a pi extension so his pi agent sets its own trigger to notify itself when a background process is done.
Team Data Platform Agent, evolved over 2 years, is widely used for SQL questions, on-call alert triage, lag monitoring, and scheduled workflows fixing bad data.
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.
A solo founder runs his game key store with about a dozen AI sessions, one each for code, pricing, copy, bookkeeping and suppliers. They stay in sync through a shared record where facts are only ever added, each fact says whether a session confirmed it or just read it somewhere, and his decisions go into a numbered ledger the sessions look up instead of asking him again.
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.