video1.0<iframe src="https://www.loom.com/embed/df34820d5c5447f197341a447c7b03b4" frameborder="0" width="1728" height="1296" webkitallowfullscreen mozallowfullscreen allowfullscreen></iframe>12961728Loomhttps://www.loom.com12961728https://cdn.loom.com/sessions/thumbnails/df34820d5c5447f197341a447c7b03b4-4ca9cdf01cbad59f.gif185.782I created Civic Ledgers, an audit-ready intake and reconciliation layer for local government financial teams. I noticed teams spend a lot of time manually matching invoices and payments during audit season, and current tools store data but do not connect it well. Civic Ledgers pulls information from invoices and files, matches documents to the right transactions, and lets analysts review items as matched, pending, or review. I demonstrated starting with 30 transactions from a sample CSV, running a match, and then confirming or rejecting uncertain matches with AI plain English explanations. No action was explicitly requested from viewers.