Triage scanned family documents for genealogy research
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 agent.
Use cases
Show all 6Show fewer
Methods
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
Steps
- 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.
- 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.
- Process in priority order: vital and military records first, then church and legal records, then newspapers and correspondence, then family records, and photographs last.
- 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.
- 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.
- Note: Steps from Matt Prusak's autoresearch-genealogy document-triage workflow (MIT).
Run this method with your agent
Download .mdCopied 0
--- 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
No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/triage-scanned-family-documents - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "triage-scanned-family-documents",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}