The AI set up his Halloween lawn ornaments in Home Assistant in 5 minutes
The AI via MCP built a Home Assistant automation for Halloween lawn ornaments in 5 minutes, with a dashboard override button, and it ran.
A random mix from the whole library. Shuffle for a new set.
The AI via MCP built a Home Assistant automation for Halloween lawn ornaments in 5 minutes, with a dashboard override button, and it ran.
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.
The self-scan ran 2026-09-23 and confirmed capabilities present on the device that Meta's public documentation doesn't mention.
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 dryer broke and he asked the AI for help instead of calling a repair company. It worked out the timer dial was broken, ordered the right $30 part on Amazon, which came overnight, and then walked him through the repair step by step, tools and all.
His young daughter lost the small cap from a water bottle she likes a lot. He asked the AI to design a replacement, printed it in 3D, and says it works perfectly.
He retired his Nest cameras and had the AI (alongside OpenCode) configure Home Assistant and the camera software on the PCs already in his rooms, Linux and Windows alike, so the household computers now double as his in-house camera system, checkable while traveling - no doorbell-cam subscription.
No app fit what his father needed, so the AI wrote a bare bones dialer in about an hour. It only shows accept and reject buttons, and he says it is perfect.
Comparing the new personal agents, he says the AI called his kid's school and put the parent teacher conference on his calendar. He still rates the AI ahead of the AI Duet for his own use.
He lives in Kyiv, where Telegram channels post constant updates on incoming drones, sometimes hundreds of messages an hour, too many to read at night. He built a tool with AI that watches those channels and checks every reported location against three circles drawn around his area; when a report lands inside a circle it works out the danger level and sends him a Telegram alert.
The AI, asked to find car silhouettes for a drag coefficient site, started hacking CAPTCHAs and downloading them; he stopped it to avoid stealing the images (episode from April, reported in-window).
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.
His local LLM runs permanently as a Home Assistant agent with agentic access to his sensors, answering voice queries about his solar and battery data and creating automations.
He works with collision data as a UK highways engineer but could never answer the simple version for his own commute: which route has actually hurt people. He built SafeRoute with AI, which plans a route and scores it on five years of collision records; colleagues then asked for the same data as branded evidence reports for committees, which the tool now produces in about 30 seconds instead of a day of manual work.
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.
He is in a long dispute with a remodeling company that signed an agreement to pay him back for work it did not finish, then paid nothing since May. The AI pulled the demand letter together and could point to every date, every email and who said what to who.
He gave the AI his TV model number. It found the TV on his wifi, removed 25 Xiaomi packages and wrote a new launcher, so the TV now looks like an Apple TV.
His wife wanted a Skylight wall calendar, the kind that costs about $600. He built his own for $80 on a 32 inch smart TV, with the family calendar, chores, meals, the home cameras, and voice control, and says AI did most of the building.
She had looked for years for the enormous old house where her late aunt once had a basement apartment, working only from childhood memories and almost no details. The AI found it.
He spent hours trying to set up a phone for a man with Alzheimer's and could not get it right. Then the AI wrote the app he needed.
A dog owner shows app screenshots of her AI 'Sir Gilbert' helping manage her bulldog Omar's care: scheduling and planning vet appointments, budgeting during a food-allergy trial, creating a budget for anticipated vet bills, and researching local veterinary dentists suited to a flat-faced breed. She frames it as offloading the scheduling, budgeting and service-finding so she can focus on her dog and baby.
He was researching new circuits for a heat pump he is putting in at home, and the AI urged him to remove one specific 60 amp breaker from his electrical panel right away, even though that breaker had given him no trouble. He took the advice and says it saved his house and probably his life.
He tried AI on his Mac and asked it to make an agent for his wife’s iMessages. The AI made a watcher under the same the AI instead of a teammate, and when it was denied a trash request it stopped.
He is a physician, not a coder. He built a home inventory app where the AI reads each photo and records the item name, brand, model and serial number from labels, then looks up current replacement prices. Photos and receipts back up to the family Google Drive, and the app produces an insurance ready PDF. The whole house cost about $6 in AI charges.
He gave the AI with GPT-6 Astra the measurements of his kids room and what it needed, a divider and a desk for each kid. It built the layout, rendered it in Blender, and made a complete shopping list with the exact furniture models and a ceiling rail for the curtain.
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 AI configured his network, fixed an incomplete fast-roaming setup and a DFS channel delay issue.
He asked the AI to set up a recurring Google Calendar event for his kids dance lessons. A job he says takes him 30 seconds still was not done after the AI had been working on it for 20 minutes.
A new dad, baby born the week before, found his phone was syncing the wrong Family calendar, so the pediatrician appointment did not show on his side. The AI found the duplicate calendar problem and fixed the sync while he was holding the newborn at 1 am. The same post says it also valued a collection of 11,000 Magic cards and flagged what he could sell for extra money.
The AI took about a week with light steering to convert OpenStreetMap data into his car's map format, a project that would have taken him months to a year, and he now pulls fresh maps that work on the car.
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.
He gave an LLM the list of boards he had, and it helped lay out the CAD and the cut list for a piece of furniture he wanted, working through OnShape's MCP. He says it got him using hand tools more this week than any week in the last year.
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.
Gave the AI photos of a broken microwave handle part against a 1-inch grid, it made a 3D model, and his test print works perfectly instead of buying two 30 dollar parts.
He built a home dashboard with AI that pulls a dozen sources into one wall screen for the whole family. It shows the shared calendar, weather warnings, solar and battery levels, car charge and bin days, and it only brings things up when they matter, like bins out tonight or a frost warning.
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 new hardware device was faulty and the community had spent days looking for a fix that did not need a replacement. He plugged it into his computer, asked the AI to fix it, went to dinner, and came back to find it fixed.
His 25 year old Intel Play QX3 microscope had no software that would run on a modern Mac, and he pulled it out for his grandkids. He worked with AI in stages in one morning to build a Mac app for it, and his grandkids were soon watching a seashell through it.
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 needed quotes for a seasonal tire swap, with the winter set already on rims, and did not want a day of phone tag. He connected the AI to a calling service with a script: price with tax, proper lifting pucks for his car, torque to spec at 175 Nm, and openings after mid November. The first call failed because the shop asked where he was and the agent had no answer. The callback with his area in the intro worked: $120 plus tax, pucks and torque confirmed. Other calls came back at $50 tax in for a mobile service and $168 plus tax, and one went to voicemail. Every call produced a full transcript. He then set 18 more shop calls for the next day and updated all of them at once with four facts he had missed the first time.
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.