Ancestors and Algorithms: AI for Genealogy

Two men named Giovanni Farruggia registered for the World War I draft in Tampa on the same day in 1917. An online family tree fused them into one ancestor. Identity separation for genealogists: how to tell two same-name ancestors apart with ChatGPT, Claude and Gemini Notebook, using a Sicilian case from Ybor City, Tampa. This episode is for you if: You attached a record because the name matched an...

No record names her parents, and you can still prove them. This episode shows how, step by step, with 5 ordinary records and 3 free AI tools. Every family tree has a woman like Nancy Brockway: a first name, a married surname, and nothing before that. Our case is a composite family built from real 1850s New York record types. Nancy lived in New Berlin, Chenango County, and was born about 1816 in Ot...

Texas did not register deaths statewide until 1903, so if your ancestor died there in the 1890s, no death certificate was ever created. This week, a county tax roll dated one anyway. Cyril Sebesta came to Fayette County, Texas from Moravia in 1873 and bought eighty acres in 1881. His headstone carries a birth year and nothing else. Three generations left a question mark in the death column. The re...

Most genealogists audit a family tree by hunting for blanks. The dangerous conclusions are the ones that already have a source attached. In this episode, Brian builds a fifteen-person test GEDCOM with five deliberately planted errors, then turns AI loose on it to see how many it catches. Four found. One missed. And the one it missed was the most dangerous error in the file. This is the opposite of...

A Marine killed at Tarawa in 1943 was declared non-recoverable in 1949, but DNA proved eighty-one years later he had actually been buried within days. It was the paperwork that failed him, not the men who buried him. This episode is for you if you've hit a record whose final-sounding language you never verified, if your family tree has a WWII, Korean, or Vietnam War service member whose fate...

A family told the same story about a 1948 move for nearly eighty years. One recorded interview and three AI tools changed that. Effie Napier is eighty-eight, and by her family's account, the last person alive who actually remembers why they left the West Virginia coal fields for Dayton, Ohio. The story everyone told was simple: better money, a fresh start. It's the version repeated at ev...

In 1836, a Yorkshire parish legally removed a laborer to a village he'd probably never lived in, over his father's old apprenticeship. This episode uses Claude, Gemini, and ChatGPT to trace an English settlement dispute through parish chest records most genealogists never open. This episode is for you if: - You have English ancestors and don't know where to start before 1837 - You&a...

A Jewish ancestor's hometown was spelled three different ways across three documents. A 1985 algorithm and three AI tools narrowed it down. This episode shows exactly how, and exactly where the method stops working. This episode is for you if you are researching Eastern European Jewish ancestors, if a hometown name on an old document does not match any map you can find, or if you want to see...

Episode 50, The AI Lab: Brian tests four AI features built directly into FamilySearch and Ancestry, using a five-question trust rubric built live with Claude, to find out which ones you can actually trust with your family tree. One of the four had not even shipped yet when this episode was first outlined, which becomes part of the story you'll hear. THIS EPISODE IS FOR YOU IF YOU HAVE SEARCHE...

Ancestors and Algorithms Episode 49, "The Research Assistant That Remembers," teaches genealogists how to build a persistent AI research assistant across three free tools: Claude Projects, Gemini Gems, and ChatGPT Custom Instructions, so you stop re-explaining your family history case to a brand new chat every single session. Host Brian walks through the exact custom instructions he wrot...

A Quebec family's baptismal records begin abruptly in 1850, though family memory said they were French Canadian for generations before that. The answer is a dit name: Quebec's centuries-old tradition of alternate family surnames, in which a family could be baptized under one name and married under another, and it is hiding more genealogy brick walls than most researchers realize. This ep...

A family believed their ancestor arrived in Australia a free man in the 1830s. A 190-year-old government pardon said otherwise, and nobody had ever read past the word "Pardon" printed across the top of it. In this episode of Ancestors and Algorithms, host Brian uses AI genealogy tools to work a full case study built around Australian convict records, a first for this show. More than 76,0...

During the Chinese Exclusion Act, one immigrant's 200-page federal case file was built to hide his real name, and nearly succeeded. For sixty-one years, the Chinese Exclusion Act barred an entire ethnicity from immigrating to the United States, with one narrow exception: the children of Chinese American citizens. That loophole created the "paper son" system, families with no blood r...

A single 1917 WWI draft card, plus a naturalization petition filed seven years later, reveal an Italian immigrant's real birth name. This is a real, start-to-finish example of using AI for genealogy research, ChatGPT, Claude, and NotebookLM working together to solve it. If you've searched "AI genealogy tools," "ChatGPT for family history," or "how to use AI to re...

Use ChatGPT, Perplexity, and Claude to email any archive in the world, including drafting a formal German-language request, in under 15 minutes. Most genealogists stop when online records run out. But the records you need are often one professional email away, whether it is a US county courthouse or a German Catholic archive that has been keeping baptism registers since the 1500s. Brian demonstrat...

Three AI tools, one 1866 Mexican parish register, and the family  that a U.S. census reduced to a single word: México. Brian traces composite ancestor Esteban Vasquez through two Arizona  census records where birthplace reads only "México" and no  naturalization record exists. The research pivots to FamilySearch's  Mexico-Sonora Catholic Church records, a collection covering roughly...

You can write a genealogical proof argument using 3 AI tools in one afternoon: NotebookLM organizes your evidence, Claude drafts and stress-tests the argument, and ChatGPT reviews it for plain-language clarity. This is the GPS Mini-Series capstone on Element 5. What you'll learn: The three-part proof argument structure: Statement to be Proved, Evidence Presentation, Analysis and Reasoning How...

Brian uses 4 AI tools to trace a formerly enslaved Mississippi ancestor across 6 record collections and through the 1870 Wall. This is what African American genealogy research looks like when AI and the Genealogical Proof Standard work together. If your ancestor was enslaved, the census did not record their name before 1870. Every year before that belongs to a completely different research strateg...

You've found the estate settlement. You've counted the heirs in the distribution sheet. And the math doesn't add up. Nine children appear in the 1860 census. Seven names appear in the 1874 settlement. Two heirs are gone with no explanation, no death notation, and no trace in the legal record. That is where this episode begins. Probate records are among the most underused sources in...

If you can't find your Norwegian ancestor in genealogy records, the problem is almost certainly the name. Norway used a patronymic naming system until 1923, meaning most Norwegian-Americans carried completely different surnames in their homeland than the names their families kept in America. A woman who appears in Minnesota records as Astrid Solberg was never called Astrid Solberg in Norway....

Most genealogists search 4-6 databases and miss 70% of the records that exist for their ancestor. In this episode, we fix that. If you have ever searched Ancestry, FamilySearch, and a couple of other databases and still hit a wall, this episode is for you. The problem is not that the records do not exist. The problem is that you do not know what records exist or where to find them before you start...

Every family has a story that got quietly handed down across the generations. A birthplace. A number of children. One marriage, one life, neatly summarized. But what happens when you sit down with the actual records and the story doesn't match? In this episode of Ancestors and Algorithms, Brian walks through one of the most universal genealogy research scenarios there is: testing a family ora...

If you have Scottish Highland ancestry and your family tree hits a wall before 1855, this episode was made for you. In Episode 36 of Ancestors and Algorithms, Brian traces a MacLeod family from the Isle of Skye using three AI tools and a research workflow that works for any Scottish Highland, Hebridean, or Inverness-shire ancestry. Whether your ancestors were MacLeods, MacDonalds, Morrisons, Campb...

Three records. Three completely different birthplace answers. A German Lutheran church register from Schuylkill County, Pennsylvania says New York. The 1880 US Federal Census says Germany. A Pennsylvania death certificate says Pennsylvania. All three claim to document the same German immigrant ancestor. Not one of them agrees. In this episode of Ancestors and Algorithms, Brian walks through a step...

Your ancestor went to California in 1849 as a forty-niner. The family says he struck it rich. But when you search the mining records for his name? Nothing. No claim. No miner's registration. No county tax list. He's a ghost. That is exactly where Episode 34 begins, and where four AI tools working in sequence completely rewrite everything the family thought they knew. Host Brian traces a...