OpenGov summary: Difference between revisions

1,026 bytes added ,  Wednesday at 22:37
Line 1: Line 1:
== OpenGov Encyclopedia - Executive Summary / Sales Pitch ==
== OpenGov Encyclopedia - Executive Summary / Sales Pitch ==
The Federal government and its inner workings are vast.  
The U.S. federal government manages one of the world's largest and most complex organizational landscapes: thousands of agencies, sub-agencies, programs, authorizing statutes, funding flows, and cross-cutting initiatives. Existing public assets like '''USA.gov''' (citizen front door), '''Search.gov''' (federated search), and '''USAspending.gov''' (spending transparency) provide essential services—but they don't deliver the unified, machine-readable semantic layer that modern agency AI systems desperately need.  


Agency LLMs and chatbots are currently "starving" for reliable ground truth. Most rely on scraping inconsistent .gov websites or parsing unstructured PDFs, leading to frequent hallucinations, fragmented answers, and reduced public trust in government digital services.


'''OpenGov Encyclopedia''' closes this critical gap as a '''supplemental, lightweight knowledge infrastructure''' — never a replacement or competitor to existing .gov platforms.


'''Core Dual Purpose'''


Resources such as USA.gov, Search.gov, and USAspending.gov already provide essential public-facing services, search, and spending transparency.
* '''Citizen-centric interface''': Wikipedia-style narrative pages (MediaWiki base + USWDS federal skin) organized around real tasks people want to accomplish (e.g., "Prepare for a Wildland Fire," "Access Housing Assistance," "Navigate Federal AI Opportunities & Regulations"). Each page provides clear context, relationships, and eligibility hints — then immediately directs users to the official agency or USA.gov destination to act.
 
* '''API-first knowledge graph''': Structured, queryable data (via Cargo extension) capturing precise typed relationships (e.g., "which agency sponsors this program?", "what legislation authorizes it?", "what funding connects them?"). This becomes high-quality "fuel" for agency RAG pipelines, reducing hallucinations and enabling parametric searches (e.g., "all active programs >$50M related to climate resilience").
In the age of AI, we propose a lightweight, dual-purpose knowledge infrastructure to supplement — never replace — these existing assets:
 
* Citizen-centric interface — clear, narrative pages in the familiar MediaWiki/Wikipedia format (with a USWDS-integrated skin that looks and feels like a standard federal site).  
* API-first knowledge graph — machine-readable, queryable structured data (via Cargo) that makes the entire federal organizational landscape — agencies, sub-organizations, programs, partnerships, authorizing legislation, funding relationships — understandable and reliable for AI systems.


== Knowledge graph ==
== Knowledge graph ==