The Platform

A discovery pipeline engineered for the public record.

Seven interlocking capabilities, all designed to deploy end-to-end inside your controlled infrastructure.

No. 01 · Available

ADA Liability Detection

Find the documents that put you at legal risk.

Title II of the ADA requires state and local governments to make digital content accessible. Metadata Minder analyzes structural accessibility — heading hierarchy, alt text, reading order, scanned-image PDFs, color contrast in embedded media — and ranks documents by likely remediation priority.

  • Untagged structure detection
  • Missing alt text and image-only PDFs
  • Reading-order and language tagging gaps
  • Prioritized remediation queue
WCAG 2.1 AA alignedPDF/UA awareTitle II focus

No. 02 · Available

Security Risk Detection

Strip away what was never meant to be public.

Public documents often contain metadata such as author names, creation tool fingerprints, machine identifiers, and reviewer comments. Metadata Minder surfaces these exposure indicators across your entire archive — at scale, without sampling.

  • Author and username extraction
  • Cross-document re-identification signals
pdftotextexiftoolOOXML parsers

No. 03 · Available

Three Witness TrueDate™

Catch records whose dates don't match their content.

Three Witness TrueDate™ compares document content against historical context to detect inaccurate digitization dates, unexpected changes, and post-hoc edits. Useful for audit trails, FOIA defensibility, and detecting silent record tampering.

  • Content-vs-timestamp consistency checks
  • Tooling-fingerprint dating
  • Silent-edit detection across re-uploads
Heuristic + LLM-assistedAudit-trail ready

No. 04 · Available

Automated Document Normalization

Every format, into one analyzable substrate.

Built on a production-tested pipeline using industry-standard tools — LibreOffice, pdftotext, and Tesseract — to convert Microsoft Office, WordPerfect, and Open Document formats into structured text for downstream analysis and accessible alternate-content rendering.

  • Microsoft Office (.docx, .xlsx, .pptx, legacy .doc)
  • WordPerfect (.wpd) including legacy archives
  • OpenDocument Format and PDF
  • OCR fallback via Tesseract for image-only content
LibreOfficepdftotextTesseract

No. 05 · Available

Automated Retention Logic

Classification that respects statute.

Intelligent classification supports archival and retention workflows based on statutory requirements — so records of permanent value are preserved and records past their disposition window can be defensibly culled.

  • Statute-aware classification scaffolding
  • Retention-window flagging
  • Defensible-disposition reporting
Configurable per jurisdiction

No. 07 · Pilot Phase 2

Searchable Dashboard

One pane for compliance leadership.

A unified dashboard for search and analysis is in Pilot Phase 2, supporting leadership briefings and compliance reviews — so the records officer, ADA coordinator, and general counsel are looking at the same evidence.

  • Cross-archive search and faceting
  • Saved findings and exportable reports
  • Role-based access for legal and records teams
Full-text + metadataExportable findings

Next step

Want a working walkthrough on your archive?

We work with state, county, and local agencies to scope engagements against real archives.