Luna finished the doorbell panel software that answers calls and shows the video
Luna finished an ESP32 SIP client for an in-wall touch panel that rings when someone is at his doorbell and lets him answer calls and see video.
A random mix from the whole library. Shuffle for a new set.
Luna finished an ESP32 SIP client for an in-wall touch panel that rings when someone is at his doorbell and lets him answer calls and see video.
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.
He remembered some smart plugs more than ten years old that use Bluetooth, and found Home Assistant could talk to them by pretending to be Apple HomeKit, but some functions were missing. He asked the AI to reverse engineer the plugs, and five minutes later they were fully revived with fully local control, with even more controls than HomeKit offered back then.
He built a household app with AI that holds the family calendar, shopping list, chore rotas, house documents, and push notifications. The family uses it daily, an update in the thread says it survived a move to a new host with its 147 releases intact, and he calls it probably the best thing he has made with AI.
He finally connected the AI to his Home Assistant setup and spent the day changing all of his automations. The AI also made an overview of how many cups of coffee they brew, which he called totally useless but fun.
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.
His LLM agent reviews his robot vacuum's images and either sends the vacuum out or suggests moving things that would foul it up; works great.
Mentioned in passing in a thread about an unlisted offer: the sellers' friends bought their house as-is on a contract the buyer had the AI write up - no agents, no lawyers - and the title company told them it was the smoothest deal she had ever handled.
He gave the AI 10MB of architectural plans. 35 minutes later it gave back a good interactive 3D walkthrough of the house, while the AI did the same job with several layout mistakes.
A man doing a home renovation uses a discount monitor alongside shopping list alerts and 3D models of the project. He says the monitor on its own saved him about $2,000 on the renovation.
He gave an agent his favorite meals, his dietary limits and the food he has on hand. It makes a weekly food plan and a full grocery list, and he tells it over the week which meals he liked.
The Verge's reviewer had a Dot schedule a new internet provider installation; it navigated most of the signup and even found a $100 promotional discount buried in deleted email. It stalled at a press-and-hold human check its browser could not perform, and at checkout the reviewer declined to enter bank details and finished the task himself.
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.
He built an app with AI that reads his solar inverter and batteries, forecasts tomorrow's solar generation and household use, and emails him a report. It sets the battery charge level for the overnight cheap tariff based on the forecast.
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.
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.
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 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.
A parent of three was copying school, cram school and nursery dates from paper prints, LINE and email into Google Calendar by hand, and nearly missed a field trip lunch. He built Hanamaru: the family posts a photo of a print in Slack, the AI pulls out the dates, and it registers them on the right child's calendar, asking in the thread first when it is not sure.
A father set the AI up to read 7 school WhatsApp groups twice a day on school days and post only the items about his daughter into a private chat he shares with his wife. It reads PDFs and images too, and caught his name on a volunteer roster he would have missed.
Spent an hour with AI migrating a Home Assistant setup to Tailscale, updating sensors and Pi-hole, and putting it all in one documented git compose file.
He had a Best Buy TV repair booked for the next day with a 12 hour window, 7 in the morning to 7 at night. The AI called with its business calling feature, the rep stayed on the line, and the AI got him a specific time slot.
The AI configured his network, fixed an incomplete fast-roaming setup and a DFS channel delay issue.
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.
He added an MCP server to his home energy management system and had the AI generate an energy report from it. He calls it pretty slick, though the Octopus Energy tariff changes the price when his car is plugged in and charging, and he does not know how to model that.
AI coding agents implemented six ways to update a Matter device on real hardware.
He had a PDF of scanned letters from his dad's Navy years, the paper letters long misplaced, and had put the project off for decades. He asked the AI to turn the PDF into an interactive timeline, and after about 10 minutes of prompting it was live online.
His corals died but the tank lights still ran a coral schedule. The AI drove a Raspberry Pi over Bluetooth, changed the light and pump schedules, and found the lights had been dimmed to about 35 percent and their clock was 6 and a half hours late, then fixed the time.
Niraj Rajgor's unused 10th generation Kindle is now a photo frame. Working through AI over Wi-Fi, GPT-6 Astra built tools to run custom software on the Kindle and installed a slideshow app that cycles ten photos, four minutes each, and picks up where it left off after sleep.
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.
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.