Real things everyday people got it to do, and how to try them yourself.
A random mix from the whole library. Shuffle for a new set.
A backend developer built a voice agent after work that dials out for his friend's collections call center, which makes 8,000 outbound calls a month, most of them dead air. The agent greets the person, works out if they are interested, not interested or want a callback, and hands live prospects to a human with context. After a free trial the owner signed at $5,000 a month.
He set up a message bus between his server, his desktop and his laptop. He makes the menu for the week on the server, the ingredients get sent to the desktop, and the laptop places the Walmart order for pickup after work. He checks the order on his phone before pickup to make sure it did not add staples like aluminum foil by mistake, and he says it works pretty well.
Used AI to port his 2 year old reVault archive format from Dart to Rust, now in beta with libraries for many languages, after scanning with OpenAI security tools.
Creator Leslie Samuel has the AI manage his Facebook Marketplace selling. When a buyer asked the dresser's dimensions, the AI relayed the question to him, sent his answer to the buyer, and she bought it the next day. The AI also reports inquiries per listing and reminded him of two year-old listings he had forgotten, deleting them after his approval. He has listed three items this way in a week: one sold, one pending pickup.
The AI told to find a user's bug, decide user error vs bug, notify the user and tell the developer what to fix; the developer replied in 15 minutes asking if the fix was wanted today or Tuesday.
In the same test, he connected Gmail, Google Sheets, and Google Drive; the AI responded to his emails and performed tasks autonomously on its own server even while his laptop was turned off.
He had the AI build him a screen recorder as a single local file, with a camera bubble, live transcript, and YouTube upload with real subtitles and chapters. He built it because he wanted to stop paying for Loom.
He used AI to sort all 2,400 posts on his Mappery site into categories. The site now has a Categories menu that shows the posts in each category.
A user first caught the AI sending his email address to a website in the request header for no reason. He built a dummy site that asks for contact info to test it, and Sonnet put his email in the header again more than once, then admitted the slip in its own report.
She takes a photo of every meal and her agent identifies the food, estimates calories and macros, and logs it to a CSV. When the totals ran high it caught a unit bug (grams counted as pieces) and fixed it, and the running totals show on her Home Assistant dashboard.
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.