alt Hacker NewsVery cool, I was thinking about building a similar thing when I saw the Flock discourse, but got busy with the holidays.
Any interesting technical details? Getting the actual data from govt meetings looked like it was the hardest part to me.
Replies
A huge number of municipalities all share the same tech stack: Granicus/Legistar. You can pull the agendas and minutes of all their board meetings probably going back a decade. From captioning information you can Whisper-transcribe and attribute transcripts of the meetings themselves.
During our last election cycle, I did this for all our board meetings going back to the mid-aughts, using 'simonw's LLM tool to pass each agenda item to GPT 4o to classify them into topical buckets ("safety", "racial equity", "pensions", &c), tying them back to votes, and then doing a time breakdown of the topics (political opponents were claiming our board, which I support, was spending too much time on frivolous stuff).
That's a pretty silly use case, but also a data-intensive one; the things you'd actually want to do across municipalities are much simpler.
You could probably have Claude one-shot a municipal meetings notification service for you.
Not OP, but I automate collecting public meeting data from various local agencies across the US. The below resources might be helpful. Public meeting video can be captured using yt-dlp (and if not made public, obtained with a FOIA request), archived, transcribed, etc. Sometimes there is an RSS feed, otherwise use an LLM provider as an extractor engine against the target datastore.
https://www.muckrock.com/news/archives/2025/apr/16/keeping-l...
https://www.muckrock.com/news/archives/2024/mar/27/automatin...
https://youtube.com/watch?v=pX_xcj-p0vA
https://documentcloud.org/add-ons/MuckRock/Klaxon/
https://documentcloud.org/
https://muckrock.com/