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 man spent a few weeks building a work AI agent for compliance checks. Today it worked through a 200 question information security audit bank and completed the 119 items that match answers to the correct standard procedures in 15 minutes. That section normally takes him a whole day.
His scheduled search looks 8 days to 12 weeks out for same day return flights from Stansted under £30, and checks Eurostar promo fares too. The point is the tobacco run: 200 cigarettes cost him about £150 at home and about £50 abroad, and he gets a day in a city he would not normally visit out of it.
Connecting the agency's own MCP-based SEO service to Toby took an afternoon of wrong turns between desktop and web plugin setups, but once authenticated it created both monitored sites and completed full crawls: 44 pages for the law firm and 111 for the medical practice. Google data imports were still skipped because the service had no Google connection configured.
When every Oura MCP server turned out unmaintained, the AI suggested a simpler design - a SQLite database with a cron sync - and built it. Now he's experimenting with injecting his sleep score into his agents' startup, so they give simpler, less demanding responses on days he's not all there, down to gentler perfume samples.
In February he told the AI what road he was taking and when he was setting off. The AI picked lunch places within a 20 minute detour that he would reach at lunchtime, 10 of them spread over 50 miles, with an import into Google Maps.
AI through tscircuit and OpenAI models designed and autorouted about 15 ordered RP2040 and ESP32 PCB designs; known mistakes include improperly rotated connectors and routing loops.
A digital-health CEO reports his businesses have no full-time developers, DevOps, designers, analysts or product manager: scheduled AI agent shifts handle deploys, an agent-built CRM, per-business-line email sorting, meeting scheduling, technical support and publishing news four times a day. The work runs on three $200 AI subscriptions — $600 a month against roughly $38,500 a month at US median pay for the replaced roles.
Migrated a fairly complex setup to NixOS 1 to 1 with an LLM agent and gained declarative services, backups and redeploy tooling.
At the same accounting firm, staff batch upload client bills and the agent reads each one, decides whether it belongs in payables, receivables, or the cash book, and posts it into AutoCount after a person reviews and amends the lines. The firm has run the setup in production for three months.
The AI built him a file manager app for the Amiga's Workbench system. He says it is genuinely useful and powerful, with the best parts of Windows Explorer and OSX Finder.
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.