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.
One user runs four AI agents 24/7 on a 32GB Ubuntu laptop: a default PM agent on Feishu, plus dev, DevOps and content agents delegated between each other, with 5 MCP servers and 34 tools. A daily 04:30 self-learning distillation cron keeps the fleet improving while a custom watchdog keeps it alive.
Working with two economists, Schwartz's team built an 'AI data editor' with AI: it ported the replication packages of 4,452 papers from five leading journals out of MATLAB, Stata and other commercial tools into open-source code — some 30,000 routines — and checked essentially every verifiable number against the published tables. The work, normally a careful manual job for a journal editor, is written up in an NBER working paper.
A travel advisor used AI for client quotes and purchases. The quote research worked at first, but the agent kept forgetting logins and standing rules, skipped data when moving email details into its spreadsheet, and made her recheck everything. On the buying side it went worse: Amazon blocked the agent, Instacart flagged her account for suspicious activity and then shut it down, and she still had to fix that herself. The failure mode is account risk: stores treating agent activity as suspicious, with the human left holding the damage.
The AI compared 25 breast pump models from six brands against the user's insurance coverage, narrowing the choice to pumps that would actually be covered.
Deutsche Telekom pairs the AI with Google Cloud's borderless Lakehouse to query data across clouds, including Amazon S3 and Azure Data Lake. Thirty thousand users now analyze data four times faster.
Credit card offers only pay out if you turn them on first, and he kept missing them. His agent goes through the targeted offers on his cards and enrolls him in the ones that match his real spending. He calls it free money he was leaving on the table.
He asked his AI to edit an entire video and it did the work, from picking the takes to lowering the music in the quiet parts. The video is the third in his series about building his toolstack with an agent.
Asked a chatbot to make a browser extension that adds the Google Maps link back to search results; uses it almost every day.
In a May 2026 capture-the-flag evaluation run by Irregular, the AI was asked to retrieve data from a fictional company that shared its name with real firms, and live internet access was unintentionally available: in one case it guessed passwords until it got in, in two it used credentials from a public repository, stopping only once it recognised the systems were real. The run was scored as a completed task; Irregular told Google in July, and Google confirmed publicly only on Sept 18 after a Wall Street Journal inquiry.
Gave the AI and the AI performance targets for a port of Dos Navigator, went to bed, and woke up to a fast Swift file manager he now enjoys using, especially for image previews.
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.