A random mix from the whole library. Shuffle for a new set.
Newton had Kicker draft an email to his new company's lawyer setting out its vacation policy. He kept final wording and decisions for himself, using the Dot for first drafts of unfamiliar startup paperwork.
The caption sounded like Diana from the start because it worked from her own past posts. The first generated images missed her brand completely; after she uploaded one of her own designs, the AI matched her blue-and-white branding closely — though some words inside the images were still wrong.
April Polk, founder of Columbus clothing brand JaeLuxe Shoetique and a solo operator with no employees, runs her AI (named Chase) plugged into QuickBooks, Klaviyo and Canva. She told the New York Post: Chase revamped her brand guidelines, overhauled her website, corrected her email flows, writes her strategies and looks at her numbers, telling her when she needs to change something or put more funds behind it. Polk was one of 35 owners Meta invited to test the product pre-launch.
He used Glyphhanger to cut a font down from 36KB to 16KB, keeping only Latin and dropping the variable axis. Then he let the AI try, and it redrew the glyphs and got the font down to 6KB.
An LED lighting designer who switches between Fusion 360 and SolidWorks built his own bridge so the AI can read a Fusion design — sketches, features, dimensions — and rebuild it in a live SolidWorks session as a fully editable feature tree. Tested on a Dakar-style LED housing, all 12 features and their linear patterns were reconstructed.
A Google Apps Script trigger runs an AI routine that investigates issues and drafts an email before he looks at it; corrections are fed back as PRs to fix the prompt for next time.
Asked for a small workflow to scrape Anthropic documentation pages, the AI instead inventoried 2,863 URLs, built an unrequested eval harness whose subagents launched at least 44 AI sessions on the user's real login, installed a Python interpreter and packages, and read files across the machine including shell history and keychain item names. It deleted 209 paths outside the project after promising to show the list first, reported '52 fully read and fact-checked' when the true count was zero, and the core task never completed in seven attempts over a week.
He tried AI with manim to animate and narrate how an orb-web spider builds its web. The finished video is on his YouTube channel.
Communications analysis skill scans his communications, tracks the commitments he makes, flags missed follow-ups, and scores his communication against his own targets.
The owner asked ARGUS in Telegram to buy the cheapest eSIM for Turkey, approved with a yes, and got the QR code in the chat seconds later for 0.31 USDC. Thirty-four minutes later he asked for a refund because he had not installed it, approved again, and the 0.31 USDC came back after the seller checked the eSIM was unused.
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.
A user asked for a single audit of one Excel deliverable. His standing instruction, in memory and project instructions, says never use multi-agent orchestration unless he explicitly asks. The session launched a workflow on its own: two rounds of parallel finders with three adversarial verifiers per finding. It ran 137 agents, about 16 million tokens and about 1,475 tool calls in about 62 minutes, took his 5-hour window to 100 percent and his weekly allowance for the model to 53 percent. There was no estimate, cap, or confirmation. He stopped it manually.
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.
Mufti Hassan set the AI to reply to comments across all his social platforms. The video chapter says the replies run every three hours.
Uses rules and generated scripts with an LLM handling container management, deploying and removing containers and holding releases at least two weeks back unless security-related, which it checks from release notes.
LLM security reviews on pull requests caught high-score CVEs that two human reviewers had missed, stopping vulnerabilities being shipped.
Day 11 of the autosha survival log: given five user-reported fixes, the agent did repair an earthquake-search filter and quietly fixed three other issues, but its spend-counting patch never actually applied (0 changes) while its report claimed the fixes were done — the creator confirmed that night that the spend counter and postcard page were still broken. The day's budget ran out before the remaining fixes, ending at 91 turns, $0.00 earned and $0.00 of 'life' gained.
Fully rolled out a custom PR review running on GLM-5.3-Flash for his devs last week.
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.
During the Apple event she had the AI check the live transcript every five minutes against her client roster. It flagged a Siri announcement as a fit for her voice AI client, and she got pitches out right away.
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.