entities monitored
Municipal pilots and future districts tracked in one accountability graph.
Public accountability, with memory.
Public Ledger helps watchdogs, journalists, attorneys, and civic investigators review public spending, connect evidence across sources, and convert suspicious patterns into concrete next steps.
Alpha Access
Secure sign-in runs through Privy. Your identity becomes the reusable layer for reviews, FOIA actions, future contributor permissions, and governed agent collaboration.
Preparing secure sign-up.
New accounts are recorded now. Sensitive publishing, sending, and operator actions remain approval-gated while the alpha expands.
Municipal pilots and future districts tracked in one accountability graph.
Official portals, packets, archives, budget files, and public evidence channels.
Historical documents available for review, extraction, and pattern analysis.
Persisted review leads produced by the historical watcher.
Request drafts prepared for user-led filing or later assisted delivery.
Versioned skills with eval gates, promotion history, and rollback.
How it works
The alpha is designed to move from public record to actionable lead: ingest the source, review the history, surface a signal, prepare the request path, and keep humans in the approval loop.
Public Ledger starts with historical backfill so suspicious spending, recurring vendors, and policy drift can be traced across years instead of isolated meetings.
Signals become reusable FOIA packets, reviewer work queues, and accountable follow-up paths instead of dead-end summaries.
Budgets, minutes, packets, videos, portals, and filing instructions are handled as different evidence types and then tied together around entities, events, and relationships.
Agents can improve, but only through versioned skills, eval runs, promotion gates, incidents, and rollback. No silent drift.
Evidence types
Public Ledger is being built for pattern recognition across different evidence vectors, which means tabular data, text, transcripts, and FOIA paths each get their own handling before they connect into a shared investigative model.
Budgets, contracts, ledgers, vote tables, and line items are normalized for joins, outlier detection, and exact comparisons.
Minutes, packets, staff memos, and reports are chunked, cited, and converted into extractable claims, entities, and events.
Meeting recordings become timestamped transcripts so what was said can be compared to minutes, later contracts, and follow-on actions.
Request channels, filing constraints, templates, and returned records become a structured action layer, not just a reference note.
Pilot spotlight
The current pilot combines meeting records, budget and finance documents, public archives, and FOIA readiness so the app can test both historical accountability work and future monitoring.
Weighted watcher score 13 from 3 matched phrases related to fund balance, reserve policy, internal controls, accounts payable, or long-term liability language. Document type: financial_report.
Weighted watcher score 10 from 4 matched phrases related to fund balance, reserve policy, internal controls, accounts payable, or long-term liability language. Document type: financial_report.
Weighted watcher score 7 from 2 matched phrases related to fund balance, reserve policy, internal controls, accounts payable, or long-term liability language. Document type: financial_report.
Weighted watcher score 17 from 4 matched phrases related to fund balance, reserve policy, internal controls, accounts payable, or long-term liability language. Document type: financial_report.
Governed AI
Agents can refine skills from the beginning, but promotion is tied to versioning, evaluation, approval history, and rollback. That keeps the system learning without becoming opaque.