A Hubitat owner built a free app that connects his home hub to the AI. He asks the AI if the garage door is closed, tells it to set the house to Night mode, and has it write spoken alert rules, like warning him when a window stays open while the heat is on.
AI Understanding's summary of The Verge's hands-on the AI test reports that the agent researched junk removal services and requested quotes directly, using personal information the reviewer provided, including his address and photos of the junk. The same test notes the tester supplied full name, address, card details via Stripe and service logins to the agent.
He had the AI add all the special days from the Pittsburgh Public Schools calendar into the family calendar. It was a win, but the school calendar itself had errors, and he spent 30 minutes working out which day was wrong.
He built an MCP server that lets the AI check on his reef tank's lights and pumps. It is read only, because he does not trust the AI or himself with the fish.
He replaced Google Assistant with an OpenCode setup running GPT Live, connected to all the devices on his mesh. Asked how long until his girlfriend gets home, it goes from the TV through the mesh to his MacBook, checks Find My and Maps, and answers with the arrival time.
After the AI started managing his home systems, he gave it control of Home Assistant too. It proved good at writing automations and doing the setup, and he later moved Home Assistant into a Docker image.
AI built his renovation material list and looked for discounts, saving about 2,000 dollars (watch for fuller sibling telling 50013796, dedupe by case facts at merge).
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.