TP-Link has no official way for an agent to control its Tapo devices, so he took the app apart, worked out how it talks to the lights, plugs, sensors and cameras on his home network, and built a connector the AI can use. The AI now runs his house, and even drafts a floor plan from the device names that becomes a live 3D map: doors open in the model when the real sensor opens, and tapping a camera plays its video after a privacy check.
Her AI Tay produced an 8-page printable birthday party plan ('Shine Like a Star') with a $700 budget breakdown; she approved it and Tay set three calendar reminders.
A Tesla owner’s the AI took a Sentry-mode scratch incident end to end: it cut the relevant clip, identified the other car, wrote the incident report and sent the insurance claim. The whole claim package was assembled from the car’s own footage without the owner editing video or forms.
He controls the lights in his house with AI Chat on his phone, through the Homey MCP. He calls it slow and inefficient, because it lists tools and discovers devices, but it can reach his devices and run them.
This only partly worked. Worth knowing before you try it.
A smart home user had the AI create a vector floorplan of his house, then write a small tool where he could drag icons for his lights and fans into place. He set it up in Home Assistant so he can click a device on the floorplan to turn it on or off.
The AI diagnosed the user's failing waterfall pump, selected an efficient replacement, designed a 3D-printable adapter for it, and separately saved $1,100 a year moving car insurance from AAA to Progressive.
A user built a custom the AI skill that remote-starts their car, reports EV battery level and monitors charging status from any chat. They published the skill because nobody else had made one for it.
In the same week as his treadmill buy, a SpaceX launch engineer says his AI got several quotes for new car tires, paid for them, and scheduled the install. No prices or shop names were shown.
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 case-study carousel describes buyer Advaith Sridhar having an AI agent negotiate a car purchase over email, pitting dealers against each other. It saved $2,102 off sticker — a premium model at a base-car price — with no in-person haggling.