---
name: "triage-scanned-family-documents-method"
description: "Use when you need to Triage scanned family documents for genealogy research. Sort scanned papers by type, pick an OCR method for each, work through the most valuable records first, then review quality and log each source"
---

# Sort scanned papers by type, pick an OCR method for each, work through the most valuable records first, then review quality and log each source

Job: [Triage scanned family documents for genealogy research](https://aiagents.org/canai/triage-scanned-family-documents)

## Need

- ai agent

## Steps

1. Sort each scanned document into a category: vital records, military records, church records, legal documents, newspapers, personal correspondence, photographs, family records or genealogical documents, and note which template each one routes to.
2. Pick an OCR method for each kind of document: Tesseract for clearly printed or typewritten text, Claude multimodal for handwriting or old printing, a layered Tesseract plus Claude pass for mixed pages, preprocessing with ImageMagick for faded or damaged pages, and no OCR for photographs.
3. Process in priority order: vital and military records first, then church and legal records, then newspapers and correspondence, then family records, and photographs last.
4. After each document, grade the OCR quality as Good, Partial, Bad or Photo-Only, check the extracted facts against what you already have, flag discrepancies and update your data inventory with the new source.
5. Use it when you have a box of scanned family papers to turn into searchable, sourced records. Some routes point at templates in the same repository.
6. Note: Steps from Matt Prusak's autoresearch-genealogy document-triage workflow (MIT).

## Credit

Method author autoresearch-genealogy (Matt Prusak; MIT)
Source: https://github.com/mattprusak/autoresearch-genealogy/blob/main/workflows/document-triage.md
