Resolve conflicting dates, names or places between family history records with AI
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 agent.
Use cases
Show all 6Show fewer
Methods
Record the conflict, rank the sources, apply the hierarchy, resolve or leave it open, then update every affected file
Steps
- Document the discrepancy in the person's file: for each conflicting pair, note Source A and Source B (name and type), the field (such as birth date, name or place) and each value.
- Classify each source: its tier (primary, secondary or tertiary), how close to the event it was created, who gave the information and how likely they were to know, and whether accuracy mattered for the record's purpose.
- Apply the hierarchy: a higher-tier source is presumed correct. For sources of the same tier, prefer the one made closer to the event, the better-informed informant, a third source that breaks the tie, or the source that is otherwise consistent.
- Resolve or defer: if the answer is clear, update the person file, note the resolution and mark it RESOLVED with your reasoning. If not, keep both values, add the question and a search plan to your open questions, mark it UNRESOLVED and flag the claim as speculative.
- Propagate the resolution: if the correct value differs from your family tree or other files, update the tree, the timeline and any affected person files, and log the correction in your research log.
- Use it whenever two records disagree, with an AI assistant such as Claude that works on a research vault of person files, a family tree and a timeline.
- Note: Steps from the discrepancy resolution workflow in Matt Prusak's autoresearch-genealogy project (MIT).
Run this method with your agent
Download .mdCopied 0
--- name: "resolve-conflicting-genealogy-records-method" description: "Use when you need to Resolve conflicting dates, names or places between family history records with AI. Record the conflict, rank the sources, apply the hierarchy, resolve or leave it open, then update every affected file" --- # Record the conflict, rank the sources, apply the hierarchy, resolve or leave it open, then update every affected file Job: [Resolve conflicting dates, names or places between family history records with AI](https://aiagents.org/canai/resolve-conflicting-genealogy-records) ## Need - AI agent ## Steps 1. Document the discrepancy in the person's file: for each conflicting pair, note Source A and Source B (name and type), the field (such as birth date, name or place) and each value. 2. Classify each source: its tier (primary, secondary or tertiary), how close to the event it was created, who gave the information and how likely they were to know, and whether accuracy mattered for the record's purpose. 3. Apply the hierarchy: a higher-tier source is presumed correct. For sources of the same tier, prefer the one made closer to the event, the better-informed informant, a third source that breaks the tie, or the source that is otherwise consistent. 4. Resolve or defer: if the answer is clear, update the person file, note the resolution and mark it RESOLVED with your reasoning. If not, keep both values, add the question and a search plan to your open questions, mark it UNRESOLVED and flag the claim as speculative. 5. Propagate the resolution: if the correct value differs from your family tree or other files, update the tree, the timeline and any affected person files, and log the correction in your research log. 6. Use it whenever two records disagree, with an AI assistant such as Claude that works on a research vault of person files, a family tree and a timeline. 7. Note: Steps from the discrepancy resolution workflow in Matt Prusak's autoresearch-genealogy project (MIT). ## Credit Method author Matt Prusak — mattprusak/autoresearch-genealogy (MIT) Source: https://github.com/mattprusak/autoresearch-genealogy/blob/main/workflows/discrepancy-resolution.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/resolve-conflicting-genealogy-records - 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": "resolve-conflicting-genealogy-records",
"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"
}