Got the AI to implement TPAP compatibility in Swift purely by interacting with his local plugs and response shapes plus RFC 9383, figuring out it was SPAKE2+ and the password hashing steps.
His new Kasa bulbs would not talk to Home Assistant, and the problem had sat open for eight months. With the AI talking directly to the devices, they now work, a fix he says he could never have written or fixed on his own.
His home network had eight VLANs and no firewall rules between them, scoring 70 out of 100 on an audit with segmentation at 0 of 25. The AI, working through a UniFi MCP server, designed a default deny zone setup, previewed each rule, and wrote it only after he confirmed. Three audit runs took the score to 93, though one change briefly broke DNS on a live VLAN before it was rolled back.
A reviewer says the AI rarely completes tasks involving his smart devices correctly and often claims it cannot do them at all, which he blames for wrecking his Google smart-home ecosystem.
This one went wrong. See what happened before you try it.
He needed his address history for a co-op application and had struggled to dig out leases from a decade or more back. The AI searched more than 20 years of his Gmail and built a spreadsheet listing his addresses back to 2006, with links to the emails behind each date and a flag on the dates that were only a guess.
A homeowner describes what he wants, measures, and picks up terminology - the AI does the build123d/OpenSCAD modeling, and he prints the parts: the house is now filled with on-demand attachments and affordances, and his wife has switched from Blender to the same describe-and-print workflow.
Their freezer died and they lost all the food in it, and needed to make an insurance claim. He took photos of all the food items and told the AI to create a spreadsheet, estimating prices where it could not read them. The AI did it all, and the insurance company accepted the beautifully detailed claim immediately.
The open-source 'burner' project gives the AI a real spare Android phone (Android 11+). The agent uses the phone's apps exactly like a human would — opening them, tapping, typing, scrolling — and sends the user screenshots, extending its reach to marketplaces and shopping apps with no website or API.
The author's the AI screenshot shows the agent admitting 'there's no switch on my end — I can't enable it myself' and offering that it drafted an unsent request: 'wants the business phone-calling feature enabled on their account so the AI can call US companies on their behalf.'
This one went wrong. See what happened before you try it.