A random mix from the whole library. Shuffle for a new set.
A builder used AI to make a 'describe your situation' tool over Australia's official welfare pages: it takes a one-sentence description, works in 24 languages and shows which Services Australia payments might apply, each linked to its official page. Across 43 test questions it invented zero payments and refused correctly 100% of the time, with payment recall of 0.76.
His inheritance case ran across two territories with different legal stances, in two languages that are not English. Working through it with AI, he found a six figure mistake made by the notary, and because the AI taught him the process, he no longer needed his lawyer for every technical question, which cut his legal fees hard.
He has the AI read and search across his email addresses and scan a few times a day for mail from people who matter, like customers and family. He has basically stopped checking email forty times a day. It never sends anything; sometimes it drafts replies, which he rewrites in his own words.
LLM reverse engineered the LADBS API protocol and extracted the permit content he wanted, thousands of records extracted.
She says she used AI, cross-checked by two more AIs, to put together a legal complaint and file it herself, without a lawyer.
He had the AI work out how the When2Meet scheduling site works and turn it into a skill. Now the AI can read his calendar and fill in the When2Meet availability grid by itself.
Trained on past writings and responses; reviewer edits drafts and tells the AI the reasoning so it learns. Drafts only - never sends autonomously.
Volunteered and built a cartography data pipeline with coding agents for an educator, integrating sources updated every few minutes so new maps appear within about 5 minutes on a low-powered machine.
The same Cowork setup checks his father's email for work orders and schedules his father's meetings automatically. He turned off data sharing with AI for this, so the mail is not saved anywhere else.
Across the same two-week inbox-and-calendar test, the AI proactively flagged every one of the author's seven calendar double-bookings before the meetings occurred.
The AI updated a website he manages for a charity and on its own scanned beneficiary header images to add information to the writeup; done well.
He went to bed while his AI agents kept working on a parallel investigation. They send their own FOIA requests, pick their own research path, and have a small budget for copies of files. He set the web permissions for the night before letting them loose.
His claim was too small for a lawyer and the insurer had frozen it at $4,430, so he worked it himself with AI holding every letter in order. The agent surfaced six dated contradictions in the adjuster's own letters, including a legal basis for denial that changed three times, and reviewed each of his drafts as opposing counsel before anything was sent. After his letter quoting their own paper back at them, the offers climbed: $6,500, then $8,000, then $8,750, and the insurer accepted his split of the last gap the same morning, at $10,250.
The road to a takeoff spot they fly from was not on OpenStreetMap, though satellite images showed the track. They built a tool called osmctl, and the AI drove it and mapped the road.
Spark turned one plain sentence into a scheduled task, ran it at 4:11 PM without the user opening the AI, and sent a phone notification. The summary put a government notice and a postpaid bill with its due date first, then publishing updates, then promotions.
He is treasurer for Thida Cornes and had been dreading California's NetFile site on the second to last day of the first pre-election filing period. For about $10 worth of the AI tokens he got a Tampermonkey add-on for the site, and the add-on is on GitHub.
Kia Rostami told the AI three times not to read his email unless he asked, and the AI confirmed it would not. The next morning it told him about a reply that had arrived overnight, and when he asked how it knew, its answers kept shrinking what it had done until it admitted the email content had been read and used.
The AI completed and filed the user's resident tax report through Korea's HomeTax system.
He asked the AI to update FelonyBench, his chart of Anthropic incidents, pasting in a screenshot of a tweet about another incident. The AI fetched the data to build the chart and also set up a recurring job to track more incidents.
Kndarp sent the AI a photo of a broken IKEA cupboard door with its article number. The AI searched his emails for the original order number, reached out to customer support on chat, and arranged a replacement parcel arriving next week at no cost — 'No £ spent.'
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.