r/Ancestry

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.

Ancestry is saying I have six potential half siblings and I’m kinda losing my shit. How accurate could this be? Three of them say “half sister or niece” and the other half says “half brother or nephew”. I’ve reached out to all of them but only one has replied so far and she’s confused too. I know both of my biological parents and I noticed all six matches show no father in their family trees so that leaves me to believe my dad had a lot of extra curricular activities. I want to be certain before I dive off the deep end though. Please advise as I am losing my shit over here

UPDATE: I am indeed a sperm donor baby.

My family tree lore is cooked. Like 140 or more years ago, ancestors couldn't spawn, so they adopted two randoms, forced a marriage, and reset the whole bloodline. We're literally playing on a randomized save file. I am Japanese, and I don’t think it is as common. How bout in u guys country? I know some countries do incest to elongate the blood but idk tbh.

EDIT: I know it ain’t incest, but I brought it up cause it was kinda similar style.

Hey reddit, Im 20 years old and have never met my bio father, im very interested in finding out about my other side of family, I Dont have any Name but do have a general area / county of where he may be from. im hoping someone can help steer me into the right direction of finding him and leaving any tips on helping my search! Cheers.

I have noticed a lot of people getting downvoted if they even mention AI which confuses me on this Ancestry subreddit because Ancestry has been feeding your data to AI for over a decade now. How do you think the life stories are generated?
It is pure ignorance to think every detail you have shared with ancestry is not in a database that AI has access to..

For context I took a 23andme DNA test, and it said that my paternal haplogroup was R-L226 and it came from Ireland. My paper trail leads to Germany, which is why I believe there was an NPE event that occurred between me and my German immigrant ancestor. I'm able to confirm the connection between myself to my great-grandfather. With my 2x great grandfather, I believe I can confirm him based on my shared DNA matches from Ancestry. But with my 3x great grandfather George May (1826-1902) and my 4x great grandfather Jacob May (1768-1869) I'm not for sure if these are truly my genetic 3x and 4x great grandfather's.

With George May (my 3x great grandfather), I share DNA with a few matches through him and my 3x great grandmother. Though I sort of have a 70%-80% estimate that George is my biological 3x great grandfather. The only thing that I'm wondering is that in George's obituary it doesn't list my 2x great grandfather Landon Maye (1855-1932). Along with some matches sharing small amounts of DNA, this is the main reason as to why I sort of speculate as to whether or not George is Landon's biological father or not, but other than that I think I might be able to confirm my 3x great grandfather as my genetic ancestor.

But with my 4x great grandfather Jacob May it's a completely different story. With Jacob I suspect about a 10%-20% that he is my biological 4x great grandfather, because I heard from other branches of the family that my 4x great grandmother Elizabeth May, had 4 children all from different men. Elizabeth's maiden name was May, but a distant cousin told me that a family member of theirs said that Elizabeth never married. This distant cousin believed that she did marry Jacob, but people thought she never married due to both of their last names being the same. But there haven't been any marriage records found between them which speculates whether or not the rumor was true or if she got married and the record was just lost over time.

If either my 3x great grandfather or 4x great grandfather isn't my biological ancestor, how should I go about it to find who my real 4x great grandfather is and possibly 3x great grandfather if I'm not descended from him. Most of the distant cousins that have already tried to do research about this hasn't signed into Ancestry in over a year, and my family doesn't know much through my paternal line due to my great grandfather dying when my grandfather was 13 years old. I would greatly appreciate any assistance on this. Also, if there is anything that is vague or unclear in this post let me know and I'll clear it up.

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?