I've been working on building hyper-local services, sort of as a love letter to my community in Denver, Colorado. Before decent LLM harnesses, these would've been prohibitively expensive in time and resources to build out and would never break even. Now I think I might be able to at least cover hosting costs and tokens; that's enough to keep these sustainable for my neighbors.

Broomsday: https://broomsday.com sends folks emails and SMS the night before street sweeping parking restrictions for their block(s). Email notifications are free, SMS on a paid season pass. The schedule here is block-by-block and easy to forget, so people get ticketed _a lot_ at $50 a pop. The city has an email-only notification service that's free, but it's poorly supported and the interface sucks. This is ready; I'm testing with friends and family currently before attempting real marketing.

HailPass: https://hailpass.com similarly is a notify-before-pain service that integrates a bunch of open weather services (NWS/NOAA mostly, plus a handful of impact reporters and working on a small hail-specific ML model) to give folks on the Front Range 5-10m heads-up before damaging hail arrives at their location. Weather prediction is (not shocking) hard so I'm still tuning to get as much signal out of the noise as possible; some false alarms will be unavoidable but I want to cut them down before even a F&F release. This year's season is pretty much over with, so aiming for an April '27 release.

There's a lot of ski/snowboard/winter sport culture here, but there's also existing services for those, and I'm mostly trying to offer new coverage where there isn't a good option for my neighbors. Might do an ash borer treatment/prevention service navigator yet.

None of this is going to make me wealthy or famous, but building things that help the people that I actually interact with every day and that are a part of a community that supports my family feels _really_ good.