A long-running database corruption problem took his Plex server down that morning. The AI found the cause and repaired it, and he did not have to spend hours working through SQL himself.
The AI with FreeCAD and MCP designed three useful parts, a printed OLED and ESP32 case, a milled hotend mount and a pen mount, all of which worked on the first hardware revision.
Fable built him a tiny, fast text editor in about 2 days that he uses as his primary editor, plus a key-bound note-taking interface in his Notes folder.
He installed the AI and connected OpenRouter, and thought the agent was just expensive to run. Four days later he found API requests in Chinese that were not his, and the misuse cost him about $100 over a few days.
$100at stake
This one went wrong. See what happened before you try it.
A user built optimAIzr with AI, a local-only CLI that analyses his own LLM usage habits, flags costly or repeated patterns and estimates where he can cut tokens or spending. All data stays on his machine, and the tool adds live tips while he works.
A builder created a skill that converts a user's Instagram saved collection into a private, searchable personal library. Every saved post is deep-read by vision AI, and everything runs on the user's own machine.
Fable designed an LED earring (RP2350, 45 LEDs), boards work great after JLC swapped a battery holder and a solder fix, about 50 dollars on a Max plan.
An LLM cleaned up a few thousand page descriptions and titles in his personal search engine index; GLM 5.3 Flash chosen after a shootout between models.
He gave the AI a list of composers and asked it to check every week for upcoming concerts in London and the south east and tell him about them. It showed him something else instead.
This one went wrong. See what happened before you try it.
He set up an auto-sync of his Goodreads updates to BookHive with help from the AI and val.town, so both places now hold the same content, including his new review of Slaughterhouse-Five.