{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Civic Tech Chat","title":"Six Weeks to Launch: How Nava built Document AI in response to H.R. 1","html":"","width":"100%","height":180,"duration":4038,"description":"Summary\nWhen H.R. 1 put new pressure on states to cut SNAP payment error rates, Nava PBC had six weeks to help Pennsylvania stand up a way to catch bad document uploads before they reached a caseworker. That rapid-response build became Document AI, an open-source service that checks whether an uploaded document is legible and the right type, then extracts key fields for review.\nProduct manager Sophia Philip and senior software engineer Laurence Goolsby of Nava Labs join Ryan to talk about the project, which has since been adapted for a Maryland pilot that's set to scale statewide by December. They cover:\n- Why the tool is deliberately kept out of eligibility decisions, with no policy coded into it\n- How applicants can opt in, opt out, or proceed anyway when a document is flagged\n- How it handles gig-work and handwritten invoices, plus Spanish-language documents\n- Why a confidence score is not the same as accuracy\n- How they're approaching AWS dependence and data security\n- How other agencies can fork the repo and adapt it to their own needs\nThis episode is sponsored by Nava PBC.\nKeywords\nDocument AI, intelligent document processing, Nava PBC, Nava Labs, open source, SNAP, H.R. 1, payment error rates, Maryland, Pennsylvania, benefits delivery, administrative burden, human-in-the-loop, consent, Amazon Bedrock, government technology, civic tech\nKey Topics\n- How AI-assisted prototyping (\"demos over memos\") is changing collaboration between product and engineering\n- Document processing as a shared problem across benefits, licensing, permits, and more\n- Building a six-week rapid response to H.R. 1 in Pennsylvania, then adapting it for Maryland\n- Why open source: avoiding vendor lock-in while keeping PII inside each agency's environment\n- The three users: applicants, caseworkers, and the people who administer the service\n- Consent that is plain-language, just-in-time, and reversible\n- Supporting nonstandard documents like handwritten invoices from gig and informal work...","thumbnail_url":"https://img.transistorcdn.com/wf_lJPgK0tAZyd_v9MM4M5qxoeBjMpgnK_rf7CJfEqI/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9kZTVi/NDY3OWQ2NTk4NzVl/ZjI3OTY3ZTExODRi/NzE3MC5qcGc.webp","thumbnail_width":300,"thumbnail_height":300}