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.
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.
As the only financially literate owner, he ended up president of a condo association with negative money in the bank. He fired the management company, then built an owner portal with AI that handles accounting going back years, dues tracking, bills, payments, compliance and vendor records. The association is out of debt, and the whole thing runs on free tier services plus a domain.
A couple keep a shared spreadsheet of shows coming soon, being watched, finished and dropped, plus their thoughts on each one. The AI reads and writes the sheet, adds picks from a list of autumn shows with reasons why they would like them, and will tell them when a show is out.
ESPM professor Wilson Silva had his AI agent research ten auto repair shops, send them photos and videos of his car, request quotes and rank the options while he worked. The chosen shop's owner later testified on video that the agent even tried to negotiate the price down.
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 bought a cheap Bluetooth receipt printer and pointed the AI at it. Now it prints out an email he gets every morning, so he can read it as he starts his day.
A man let an agent live on his home network and finally get his hundred or so sensors and smart devices configured and talking to each other. This year he set up garden sensors with its help, tied soil, rain and sunlight readings into automated watering, and had by far the largest hot pepper harvest he has ever had.
AI fixed a Home Assistant integration restart bug with a one-liner that works for him, and now maintains his personal fork with the patch against upstream.
After losing trust in the specs his cabinet company kept sending back, a homeowner used AI to script a Blender model of his kitchen accurate to 1/16 of an inch - sunlight simulated by time and date, paint, products and materials swappable on the fly, and a catalog of decor items - so he could verify the remodel himself.
A machine-learning user built a bridge ('wand') letting his AI act on his Mac remotely from his phone. The AI reads his Terminal, reports training-run stats like epoch, loss, and accuracy, and can lock the machine on request.
A hobbyist says the AI assembled the firmware running his living-room lights and fans: an ESP32 web server driving a radio transmitter. It also built him a Streamlit app to explore the signals, and the code is public on GitHub.
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.
His 2019 LG TV has a great screen, but the official Plex app took about 30 seconds just to show the profile picker, because it is really a web page. There is no public native toolkit for the TV, so he rooted a spare set, read the TVs own software with analysis tools and the AI, and built a native Plex client of his own. On the same TV it shows the profile picker in about 3 seconds.
He runs the AI on his PC with ha-mcp on the same machine, so the AI can reach into Home Assistant and make the changes he asks for. He keeps it on his own PC only, and says a new dashboard is done as soon as he describes it.
His cat feeder camera charged $5 a month to store motion clips. He had the AI reverse engineer the feed login so his home server could pull the video, spot the cats, cut clips, save them to R2, and play them in an iOS app, all for $0 a month.
LLM helped develop in about 10 minutes a tray app that watches for a USB device and switches the TV input via the LG API; he no longer touches the remote.
The family's move required buying a property abroad: a buying engine found the place, and an agent then saw the purchase through to completion, handing the owner a step-by-step list of the only parts a human could do - mostly moving the money across the Atlantic.