Your proposal is well-structured and interesting but has a fundamental flaw that needs to be addressed. Interest keyword-based filtering will primarily encourage politics-as-identity, which is actively harmful - it directs attention towards zero-sum thinking and performative identities, rather than creative problem solving. As Bryan Caplan demonstrates in The Myth of the Rational Voter, people already tend to vote to express identities and affiliations rather than to achieve better outcomes. We shouldn't build tools that further entrench this destructive pattern.

Instead, imagine a tool that:

1. Has users journal daily about their life - activities, hopes, problems, and worries
2. Uses AI to identify where their constraints are plausibly caused by or could be alleviated by government action, especially local government
3. Maps them to specific opportunities for formal recourse, with guidance on process, likely outcomes, and practical assistance (like drafting letters or legal documents)
4. For issues requiring collective action, connects users facing similar constraints and helps coordinate through mechanisms like dominant assurance contracts where appropriate

This approach would ground political participation in the solving of one's own problems rather than identity expression. While technically more challenging to implement than interest-based filtering, it would generate higher-quality engagement that expands our collective problem-solving capacity rather than just reallocating political power between existing interest groups.

The patterns emerging from aggregated user experiences would naturally reveal systemic issues and preventive opportunities, especially in how regulations and policies interact to shape people's choices and planning horizons. While building reliable AI judgment about political causation is challenging, it's better to attempt something hard that would be beneficial if feasible, than to facilitate the destructive forces of identity-based politics simply because they're easier to implement.

This would likely need to be a tool for local organizing that contains manuals. most of the information on the tool will be out of date and there needs to be a clear process for how to make it up to date, despite that people who potentially disagree with each other strongly would be updating it. AI could be included in the tool to help update it, but AI couldn't be the final authority at this time.

some references for content I'd suggest including, at least by reference - I make absolutely no attempt to be neutral in my recommendations:

1. best match I know of, after significant effort spent looking over several months: https://localwiki.org/ - but it isn't quite what you want, and also it's slow and underpopular
2. I don't know of a tool that filters by interests like that
3. https://www.congress.gov/state-legislature-websites maybe? each site varies and some are very very slow. utah was fast, georgia was fast, alabama never loaded for me.
4. ^
5. ^
6. https://ballotpedia.org/Main_Page maybe?
7. maybe https://activisthandbook.org/en/home?

some bonus resources I think are relevant to effective organizing - note that you don't have to completely agree with these resources to learn from them and produce worlds that are better in subsets of the ways the authors intend:

• https://c4ss.org/resources
• https://braverangels.org/
• https://www.ctctogether.org/
• https://www.youtube.com/results?search_query=community+network
• https://www.climatechangecommunication.org/debunking-handbook-2020/

some more non-electoral resources I've encountered recently but which I'm not sure are good-according-to-me yet, and I link anyway because they seem promising based on initial assessment and how I discovered them:

• http://foodnotbombs.net/new_site/ (specific resource for aiding the poorest in an area with food, as far as I know this is one of the very highest options for local impact altruism, which can have second-order impacts via network effects that I think are undervalued by EA messaging; not sure they're undervalued by EA funders though, idk about that part)
• https://netcentriccampaigns.org/7-elements/ (unsure I would feel comfy linking this site to someone without also linking c4ss, since their perspectives are compatible but may be too narrow without each other)
• https://www.mutualaidhub.org/ (looks extremely promising for direct aid, which is key for connecting with a local community for the long haul, not so helpful for making a difference with only the aid of electoralism)