u/astroproff

▲ 0 r/AIGenealogy+1 crossposts

Using Claude to write fuller, narrative event descriptions in Ancestry.

I have a largely completed family tree. For my closest ancestors' pages - which have lots of documentation and attached sources, including multiple newspaper articles - I know their lives are largely mapped, and that all their siblings and children are known.

In this context - I've found Claude does a pretty good job at writing narrative descriptions for each event on an ancestor's timeline. I already have fairly complete notes with short facts - an address here, a "Living with all 3 children" there - but I wanted pages which, if read by more distant family, would paint a fuller narrative picture of their lives.

I call this a "Profile Cleanup". To do it, I did something like this:

  1. Download Claude app on my desktop/laptop.
  2. Use it in "Co-Work" mode - you'll need it to save and read files locally.
  3. Set up a "Genealogy" project (which creates a walled workspace for files and research memory for Claude).
  4. Download your GEDCOM file from Ancestry and put it in the project directory.

Now you're ready to start. I asked claude to write the prompt (below), based on the many accumulated commands I've given it. If you enter the below once, you can thereafter just call it "Profile Cleanup" as in "Perform a profile cleanup for my maternal grandmother."

After executing this on an ancestor's page, the Descriptions read narratively, and a layperson can get a very full description of that person's life, without it reading like it's a police file.

===================================================

Ancestry Profile Cleanup — Brief Prompt

Clean up [PERSON FULL NAME]'s page in my Ancestry family tree and add biographical Description text to each event.

Setup. Read the GEDCOM file. Use my Ancestry.com account, and my family tree [FAMILY TREE NAME]. Use the Claude-in-Chrome MCP — I'm already logged in.

Phase 1 — Study the family first. Before writing anything, (a) read the GEDCOM records for parents, every sibling, spouse, and children; (b) load each of their Ancestry facts pages and note dates that bear on the subject's events; (c) fetch the actual content of every newspaper clipping attached to the subject and the major obits of immediate family via the newspapers.com/clip/... URLs. If you find yourself writing "likely" or "probably," stop and go verify.

Phase 2 — Inventory. List every timeline event. Skip ones with substantive Descriptions already (unless missing context). The Marriage event is shared with the spouse — don't overwrite a cleaned spouse page.

Phase 3 — Edit rules.

  • Biographical, not source-citing. Don't write "per the Tribune obit" — the source is already attached. Add facts the auto-LifeStory doesn't say.
  • Append-only. Preserve existing text exactly, including sensitive notes (cause of death, etc.).
  • One concise paragraph per event (~15–50 words; vitals can run longer).
  • Always include: church names for vitals, street addresses for Residences, funeral home + cemetery for Burial, family members by full name in obituaries.
  • No bullets, no fabricated details, no edits to auto-generated rows ("Death of mother…"). Don't click "Explore" — it navigates away.

Phase 4 — UI. Click card body → Edit pencil → edit Description → Save → wait for green banner → Close. Work chronologically. Fix wrong dates, inconsistent place formats, and obvious typos against sources as you go.

Phase 5 — Summary. Post a table of every event edited with a one-line note, and flag anything ambiguous for review.

Person this run: [PERSON FULL NAME].

reddit.com
u/astroproff — 3 days ago

A NYTimes OpEd by graduating Stanford CS student depicts his class as largely without integrity, due to AI

Gift Link to the OpEd. This is a pretty grim depiction.

"In junior year, 49 percent of the 849 computer science majors who responded to an annual campus survey said they would rather cheat on an exam than fail. A friend of mine captured the school’s ethos while we were discussing the tech hardware and other items our student club neglected to return to corporate sponsors. It was all, I recall her saying, 'just a little bit of fraud.' "

u/astroproff — 4 days ago
▲ 0 r/Ancestry+1 crossposts

New Community! /r/AIGenealogy has been created!

I've created a new community - r/AIGenealogy - to support and promote the use of AI in genealogical and family history applications, in a positive way.

If you have ideas on how AI can improve people's study of their family history, "How To"s on how to do so, or just want to benefit from others' experiences - come join us!

reddit.com
u/astroproff — 6 days ago

👋 Welcome to r/AIGenealogy - Introduce Yourself and Read First!

Hey everyone! I'm u/astroproff, a founding moderator of r/AIGenealogy.

This is a community for the discussion of how to use AI to support family history and genealogical research, in a positive and supportive way. We're excited to have you join us!

What to Post
Post anything that you think the community would find interesting, helpful, or inspiring. Feel free to share your thoughts and questions about using AI in a way which improves and increases your knowledge of your family history.

Community Vibe
We're all about being friendly, constructive, and inclusive. Let's build a space where everyone feels comfortable sharing and connecting.

How to Get Started

  1. Introduce yourself in the comments below.
  2. Post something today! Even a simple question can spark a great conversation.
  3. If you know someone who would love this community, invite them to join.
  4. Interested in helping out? We're always looking for new moderators, so feel free to reach out to me to apply.

Thanks for being part of the very first wave. Together, let's make r/AIGenealogy amazing.

reddit.com
u/astroproff — 6 days ago

Welcome! Let's discover how to improve genealogy and family history using AI, in a positive way which supports its use.

Other communities on reddit given to genealogy are generally negative about the use of AI in genealogy and family history.

This community is established for people to discuss how AI can improve personal genealogy work, and work in family history, in a positive way which supports its use.

If you share this goal - welcome!

reddit.com
u/astroproff — 6 days ago
▲ 1 r/AIGenealogy+2 crossposts

How To: Transcribing and Translating documents with Claude AI

Claude AI has excellent transcription and translation capabilities, and works with results from my Ancestry account. When combined with my GEDCOM file from Ancestry, it can hit discoveries out of the park.

Here's how I get the most out of it.

  1. I use a Claude Desktop app on MacOS. I operate it in "Co-Work" mode.
  2. I ask Claude to set up a project for Genealogy. Claude will create a dedicated directory "Genealogy" (within its "Projects" directory - the only directory it's permitted to read/write from).
  3. I'll put my GEDCOM file in the project directory - downloaded from Ancestry, and direct Claude to read it "Read the GEDCOM file and extract all information from it. This is my family. I am astroproff born 1978." This gives Claude context to interpret the document.
  4. Then, I take jpg historical document and tell Claude "Read this. My relative is Lars Hansen. Find my relative in it and extract all the information from the entry. Point out information which is new."

For example, here is a handwritten page from a Danish church record. It contained a possible relative of mine. I hand it to Claude, give it the above command. It churns for about 5 minutes:

This is Claude's response, in full - which, because I can't read Danish, and the handwriting is nearly inscrutible to me anyhow, is an enormous help:

=========================================================

Got it — entry 22. Here is the complete reading of his record, plus what it adds to what you already have.

Lars Hansen — birth/baptism record, Lindelse 1846 (entry No. 22)

  • Born: 28 August 1846
  • Baptized in church (i Kirken): 11 October 1846
  • Parish: Lindelse Sogn, Langelands Sønder Herred, Svendborg Amt — entered into the main parish register on 1 July 1847 by Pastor Toft
  • Parents' residence: Hersløv Mark (the outlying fields of Hersløv, a hamlet in Lindelse parish)
  • Father: Hans Jørgen Hejne Larsen — written with the prefix "Ungkarl" (literally "bachelor / young man"; usually marital status, but here paired with "hd." it most likely just signals he was a young husband)
  • Mother: Maren Pedersdatter — listed as "hd." (hustru = his wife)
  • Godparents / witnesses (Faddere):
    • Hmd. (husmand — cottager) Hans Pedersen of Kjædeby
    • Ungkarl Jørgen Madsen of Kjædeby
    • Pigen (unmarried young woman) Caroline Madsdatter of Kjædeby
    • Godmother: wife of Hmd. Morten Christiansen of Hennetved
  • Jævnførelses-Register cross-reference: 880 / 369 (this is where his entry is indexed in the parish's running comparison register — useful if you want to pull confirmation/marriage/death entries for him out of the same Lindelse books)

What's new vs. your GEDCOM

None of these people — Lars himself, his parents Hans Jørgen Hejne Larsen and Maren Pedersdatter, or any of the four witnesses — currently appear in your family tree. The two "Lars Hansen" individuals already in your file are different men (one b. 1836 in Kerte, Odense; one b. ~1816 in Mesinge, Odense). So everything in this record is net-new information.

A connection worth checking

This is the part to look at carefully. Your tree already includes Ane Marie Hejne Hansen (b. 5 Aug 1848, Helsned, Humble parish — the parish next door to Lindelse on Langeland), who married Mads Frederiksen and is the mother of Rasmus Madsen (the Sacramento immigrant). Her father is recorded in your GEDCOM only as "Hans," born ~1818 in Fyn, married to Dorthe Madsdatter.

The middle name "Hejne" is unusual and is the same one carried by Lars Hansen's father here. That raises a real possibility that Lars's father Hans Jørgen Hejne Larsen is the same "Hans" who later (after Maren Pedersdatter died) remarried Dorthe Madsdatter in Humble — which would make Lars Hansen a half-brother of Ane Marie Hejne Hansen, and therefore an uncle to Rasmus Madsen. That fits the chronology (Maren's child in 1846, Ane Marie born to Dorthe in 1848) and the geography (Lindelse → Humble, neighboring parishes). It would also explain why your "Hans" has no surname recorded — it had never been pinned down.

This is a hypothesis, not a confirmation. The thing that would prove it is the marriage record of Hans Jørgen Hejne Larsen to Dorthe Madsdatter in Humble or Lindelse, somewhere between 1846 and 1848, and/or a death/burial record for Maren Pedersdatter in Lindelse in that same window. Both would be in the same Rigsarkivet kirkebog series you already have references to (Reference 8008907761 / 8008908021 / 8009029901 for Humble and Lindelse).

Suggested next steps

  • Pull the Lindelse 1846–1848 deaths to look for Maren Pedersdatter
  • Pull the Lindelse + Humble marriages 1846–1849 for a Hans Jørgen Hejne Larsen → Dorthe Madsdatter
  • Look for Lars Hansen in the 1850 Lindelse folketælling — that will tell you if he was still alive, who he was living with, and whether the household has reorganized after a parental death/remarriage
  • Pull the Lindelse confirmation registers c. 1860–1861 (boys confirmed around age 14) — that's where you'd find Lars Hansen confirmed if he lived

Want me to draft a research log entry for this and save the hypothesis (and the new individuals) so you can pick it up next time?

==================================================

u/astroproff — 6 days ago
▲ 1 r/AIGenealogy+2 crossposts

How to break down a wall using Claude AI and Ancestry records

Since I've done this a few times now, I thought I'd write a quick "How to" for other genealogists.

This is the basic prescription.

  1. You're going to need to download and have a *paid* account on Claude. Why paid? Because the free account just doesn't offer enough computation time.

  2. Get used to using the Claue App on your desktop/laptop. Specifically, put it in Co-Work mode - which enables it to read files on your computer and set up a "Project" space for your genealogical work, like a directory called "Genealogy".

  3. Download your GEDCOM file from Ancestry, and put it in your Genealogy project directory for Claude.

  4. In Co-Work mode, instruct Claude to read your GEDCOM file, and look for the ancestor of interest by name, where the wall goes up. Let's call him "Edward Forgotten".

  5. Tell Claude to search for Edward Forgotten on your family tree on Ancestry. com. Claude will probably need to access it through your browser, so grant permission to do so.

  6. Finally, tell Claude to search for the documentation which will break down the wall. For example "Find Edward Forgotten's documentation near where he died, such as his marriage record, baptism record or birth record."

The response to this, if it is like mine, will be a description of that documentation, pulling out the key information - like exact date, location, parents, etc.

  1. Really finally - READ all the discovered documentation. You want to be at least as familiar with this, as you are other documentation on the tree, and this is to confirm that claude did an accurate job of reading the documentation.

That's gotten me two generations of parents beyond my brick wall for my maternal grandmother's maternal grandmother in Denmark. So now, I have all the way back to her paternal grandfather.

The accounts cost money - so I won't say it's worth it. But I've found it extremely helpful in getting information that many hours of dilligent searching had not uncovered.

reddit.com
u/astroproff — 6 days ago
▲ 0 r/Ancestry+1 crossposts

How I used Claude AI to examine my work on one Danish family in the mid 1800s.

tl;dr I asked Anthropic's Claude to read 20 jpg files of handwritten church documents in Danish that I had placed on my computer in a subdirectory. He did, translated them to English, found the entries relevant to my family (which he learned from my GEDCOM file), and confirmed my previous work of extractions; found a few inconsistencies; found the place names for all the births, baptisms, confirmations and marriages and compared them with entries in GEDCOM.

This was extremely useful. Claude was able to do reading/translation/consistency check work/report writing which would have taken an experienced Genealogist (who could read Danish) over 100 hours of work, in less than an hour's work for me.

----------------------------------------------

My mother's maternal grandparents were Danish (her father was Italian); and my father's side is 100% Irish.

The Danes were immigrants to the US circa 1890-1910. Understanding and documenting the Danish branch of my family has been one of my greatest challenges.

Much of the most useful Danish sources from this period are the church documents (available and Indexed on Ancestry) of births and baptisms, confirmations, and marriages; these often contain full names of parents, with repetetive birthdates and townland names where they live.

These church documents are handwritten, in Danish, and I (who don't speak Danish) struggled for months pouring over the documents. The Indexes for these documents on Ancestry are already useful - but they are sometimes incomplete.

Furthermore, my Danish family has been challenging to me because the patronym changes every generation (e.g. Lars Penderson's son's last name is 'Larsen'); and I don't know Danish geography well, which made intercomparing place names challenging at times.

I wanted to see what I could do with Claude to double check my work, find any information I may have missed, find inconsistencies, and make suggestions for additions to my family tree.

For this test, I focussed on one Danish family - my 2nd great grandparents Mads Frederickson and Anna Hansen. Mads and Anna had 10 children.

Thus, attached to Anna's page are about 20 sources of church documents, in jpg format, handwritten in Danish. These documents are full pages which contain a lot of extraneous information from other families, which I have to read to find the information related to my own family.

From my Ancestry .com family tree, I downloaded to my local computer 20 jpg document copies of Danish, handwritten church records. I also downloaded my full GEDCOM file. I put these into what's called a "Project Directory", which Claude can read while in "Cowork" mode - a mode which allows it to interact with local files, manipulate the files, and create and populate new files.

This is what I prompted Claude with:

I would like to check the consistency of Danish church documents and census documents for the children of my 2nd great grandmother Anna Marie Hejne Hansen and my 2nd great grandfather Mads Frederickson.

Can you see the directory marked Anna Marie Hejne Hansen and Mads Frederickson?

Claude responded:

Yes, I can see the directory "Anna Marie Hejne Hansen and Mads Frederickson" inside your Genealogy folder. It contains 20 image files — the filename prefixes (48551 and 48623) suggest a mix of Danish parish register pages and census images from Ancestry/Rigsarkivet.

Before I dive in, a few quick questions to make sure I check the right things:

  1. Children list source — should I treat the GEDCOM file (XXXX Family Tree.ged) as the authoritative list of children to verify, or do you have a separate list of children in mind?
  2. Scope of "consistency" — are you primarily looking for:
    • Matching birth dates / names / parents' names between church baptism records and census entries
    • Children listed in one source but missing from another
    • Spelling variations or transcription discrepancies
    • All of the above
  3. Output format — would you like a Word document summarizing findings (a table per child with church record vs. census entries side-by-side, plus any inconsistencies flagged), or a more informal chat summary?

Also, the images are in Danish gothic/Gothic script — I'll do my best to read them, but church records from this era can be difficult. I may need to flag entries where I'm uncertain rather than guess.

After I answered these questions, in brief, what Claude then:
* Read all 20 jpg documents in handwritten Danish, translated them to English, and found the entries relevant to my family, ignoring the other entries.

* Compared the information found in the church documents to what was in my GEDCOM file, and found a few inconsistencies between the two, and some places where I had not inserted useful information.
* Claude found a few inconsistencies in the church documents which warrant a closer look by me.
* Wrote up a 12 page document, with tables, directly compared the gleaned information with the GEDCOM file contents, highlighting recommended changes (to the GEDCOM file, based on the gleaned information).

Just one example of new information this exercise provided, is this. Claude found an inconsistency between the documents and my GEDCOM file - specifically, one of the documents documented a child's re-marriage, and the written document contained the death date for that child's first husband, and where he died. That information was not indexed by Ancestry attached to the document (unsurprisingly). I previously had a wrong date/location - decades later, in the wrong country even - since I hadn't found any other documented death information. This corrected the record - my relative had been widowed, not divorced, prior to her second marriage.

reddit.com
u/astroproff — 9 days ago

Using AI with your GEDCOM File

I downloaded my GEDCOM file and handed it to Claude. I asked, what can you do with this?

One thing Claude did, is spotted all my relatives who died of what is definitely heart disease, and made up a summary of these in a nice clean document, with recommendations on how to have a conversation with my doctor about it. Claude also recommended non-standard tests I should consider asking for to detect hereditary heart disease.

I also asked Claude to write up short biographies for various relatives.

What are you using AI for, and how, in your genealogical work?

reddit.com
u/astroproff — 12 days ago

SOLVED!

I found the scotlandspeople.gov.uk website - and found their marriage document, and it has his parents name on it and age! Completely solved!

===================================================================================

I'm researching this John B. M'Culloch (possible alt spelling: McCulloch) of Edinburgh, Scotland, and am in a bit of a brick wall situation.

This is what I know about him:

* Married a Violet (Ward) Drummond about 1939-1945.
* I've found all their electoral registrations at the same address, (1945-1960; 17 Craigmilllar Castle).
* Probably born about 1895 (bc Violet was born 1897), probably in Northern Ireland but possibly Scotland.
* He likely died in 1961 (I don't have an official confirmed death record; but he disappeared between 1960 and 1963; I found a cremation record for John M'Culloch, who died 2 Dec 1961, and it's probably him - because Violet's first husband was also cremated).
* Probably lived in Edinburgh as early as 1934, and possibly even earlier, possibly even born there.

What I really want to know about him:
* His parents' names/identities, where and when he was born (so I can track backwards).

What I also don't know about him (but isn't critical):
* No marriage record between him and Violet (this could help identify his parents, birth year, birth place, and other information).
* Any addresses, or any documentation prior to 1945.

Challenges:
* There are multiple John M'Cullochs living in Edinburgh between 1910-1940 (from Election records), and it seems he could be almost any of them (most do not have an initial).

Already exhausted:
* Ancestry.com, Familysearch.com , and Newspapers.com. By which I mean - I did my best to search these resources for relevant information. But, I haven't (for example) made information tables for every separate John M'Culloch I've identified in Edinburgh 1934-1945.

Probably would be very useful to find:
* The marriage document
* A Draft or military document from WWI, or WWII.

Thank you in advance for any direction you're able to give, or information you find!

reddit.com
u/astroproff — 19 days ago