Agazayt

Cash-heavy businesses (I'm involved with one: Thillens) reconcile deposits, invoices, and billing lines by hand every day, and the same fixes repeat for years while the knowledge dies in spreadsheets - teams want AI to automate it, but no CFO will let an agent rewrite financial controls unchecked. Ledger turns repeated human corrections into governed automation: variance cases and operator corrections live in MongoDB Atlas, an AI agent reads that history and proposes a deterministic rule in a strict closed JSON DSL, a demo operator evaluates it against ground truth for precision and recall, and only a separate human approver presenting the hashed evaluation report can activate it. The agent proposes, the operator evaluates, the human approves - capability gates enforce the separation and every transition is an auditable event, so operations teams get agent leverage without handing over the keys.