Ancestors and Algorithms: AI for Genealogy

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 American genealogy. When an ancestor died without a will, the intestate settlement process required the court to document every legal heir by law. When someone is missing from that list, there is always a reason. This episode shows you how to find it.

In Episode 40 of Ancestors and Algorithms, host Brian works through an 1870s Tennessee intestate estate using four AI tools: Claude, Perplexity, ChatGPT, and NotebookLM. Step by step, prompt by prompt, you watch AI transform a dense 19th-century legal document into a focused research roadmap for tracing missing heirs.

WHAT YOU'LL LEARN:

How to use Claude to analyze a probate distribution sheet and surface the anomalies that are easy to read past, including a buried legal clause that completely changed the research direction.

How to use Perplexity to research historical intestate succession law so you understand exactly why a legal heir might be absent from an estate settlement with no death record to explain it.

How to use ChatGPT to generate every plausible reason a family member might be missing from a probate document, including scenarios most researchers never consider: daughters recorded only under married surnames, guardianship proceedings filed separately from the estate, and creditor debt attachment.

How to use NotebookLM to cross-reference census records, tax lists, and estate documents together and identify what the evidence actually establishes versus what you are inferring.

THIS EPISODE IS FOR YOU IF:

• Your ancestor's probate distribution lists fewer heirs than the census records suggest there should be. 
• You are facing a 19th-century estate settlement full of archaic legal terms you cannot parse. 
• You research Tennessee ancestry from the Civil War era through the early 1900s. 
• An ancestor disappeared from the records after a death in the family and you have no idea where to look next. 
• You want to see exact, copy-paste AI prompts designed for genealogy research before trying them yourself.

The outcome is honest: this mystery is not fully solved. The research produced two legally grounded theories and identified a precise next record set in a physical archive that has not yet been digitized. Sometimes the win is knowing exactly where to look. That is real genealogy.

TOOLS: Claude, Perplexity, ChatGPT, NotebookLM RECORDS: Intestate estate settlements, distribution sheets, probate inventories, Tennessee county tax records, FamilySearch Tennessee Probate Court Files 1795-1955 GPS: All five elements of the Genealogical Proof Standard

Companion Guide and free resources at ancestorsandai.com.

Connect with Ancestors and Algorithms:

📧 Email: [email protected]
🌐 Website: https://ancestorsandai.com/
📘 Facebook Group: Ancestors and Algorithms: AI for Genealogy - www.facebook.com/groups/ancestorsandalgorithms/

Golden Rule Reminder: AI is your research assistant, not your researcher.

Join our Facebook group to share your AI genealogy breakthroughs, ask questions, and connect with fellow family historians who are embracing the future of genealogy research!

New episodes every Tuesday. Subscribe so you never miss the latest AI tools and techniques for family history research.

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. Not once.

In this episode of Ancestors and Algorithms, host Brian works through a complete AI-powered research workflow that starts with a blank Digitalarkivet search result and ends with a specific farm in Kviteseid parish, Telemark, demonstrating exactly how four free AI tools can crack open a Norwegian line that seemed impossible to trace.

What you will learn:

Why Norwegian-American surnames like Halverson, Solberg, and Olson look nothing like the matching Norwegian record, and the exact naming logic that makes every transformation predictable once you understand it.

How to search Digitalarkivet, Norway's free national digital archive, using correct Norwegian naming conventions instead of the American surname that returns zero results.

How to use Perplexity to build a research map of a specific Norwegian parish before opening a single record, so you know exactly what exists, what is missing, and where to look next.

How to use Gemini 3 Pro in Google AI Studio to transcribe handwritten 19th-century Norwegian census pages and emigration departure lists in old Norwegian script.

How to use Claude to compare documents from two countries and build a structured evidence table that shows exactly what has been proven and what is still missing.

How to use NotebookLM to construct a GPS-compliant evidence argument and determine honestly whether your identification is proven, probable, or still open.

This episode covers Norway's 1865 and 1875 census records, kirkebøker (parish registers), and afgangslister (emigration departure lists), all free on Digitalarkivet. The workflow applies to Norwegian ancestors from any region: Telemark, Hordaland, Rogaland, Trøndelag, Vestlandet, or Østlandet.

The outcome of this research is a partial answer. A strong, evidence-based case pointing to the right family, with one link in the chain still unconfirmed. That is what honest genealogy research looks like, and this episode shows you exactly how to get there and what to do next.

If your Norwegian line has gone cold because the name does not match, this is exactly where to start.

Companion Guide and advanced prompts available for members at ancestorsandai.com. Free for all listeners to begin today.

Connect with Ancestors and Algorithms:

📧 Email: [email protected]
🌐 Website: https://ancestorsandai.com/
📘 Facebook Group: Ancestors and Algorithms: AI for Genealogy - www.facebook.com/groups/ancestorsandalgorithms/

Golden Rule Reminder: AI is your research assistant, not your researcher.

Join our Facebook group to share your AI genealogy breakthroughs, ask questions, and connect with fellow family historians who are embracing the future of genealogy research!

New episodes every Tuesday. Subscribe so you never miss the latest AI tools and techniques for family history research.

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 searching. That is the gap this episode closes.

In Episode 38, Brian introduces the Research Map: a structured, AI-powered framework you build before you search a single database. Using Claude, ChatGPT, and NotebookLM, you will learn how to map every record type, every repository, and every access pathway relevant to your specific ancestor, including the ones that never appear on Ancestry or FamilySearch.

In this episode, you will learn:

• Why most genealogists are only searching 20-30% of the records that actually exist for their ancestor, including the three mental habits that keep them there
• The Research Matrix Prompt: how to use Claude to generate a comprehensive, prioritized list of every record type relevant to your ancestor's time, place, and background. Results are organized by repository, digitization status, and research priority
• The "What Am I Missing" Prompt: how to use ChatGPT to surface specialty repositories, local archives, ethnic community records, and record types that no major platform indexes. Includes how to flag which suggestions need verification before you act on them
• How to use NotebookLM to cross-reference and synthesize your research map into a source-backed, conflict-resolved action plan
• Why a 1880 Special Schedule of Agriculture for Iowa was sitting on FamilySearch the entire time, searchable for free, and why it never showed up in a standard census search
• How Iowa state censuses going back to the 1840s represent years of uncollected evidence that most researchers have completely skipped
• The difference between a failed search and a genuine absence of records, and why confusing the two stops research in its tracks
• How GPS Element 1 (Reasonably Exhaustive Research) defines the standard professional genealogists use, and how AI helps you meet it

The AI Tools Featured:

• Claude (claude.ai): Research Matrix Prompt, record type mapping, repository identification
• ChatGPT (chatgpt.com): Specialty repository brainstorming, ethnic and local archive surfacing
• NotebookLM (notebooklm.google.com): Source-grounded synthesis and cross-referencing

All workflows use free tiers. No paid subscription required to follow along.

The Genealogical Proof Standard Connection: This episode is Part 3 of the GPS Mini-Series within Ancestors and Algorithms. Episode 38 focuses on GPS Element 1: Reasonably Exhaustive Research, which is the standard that says you must search every source that could reasonably be expected to hold information about your ancestor before drawing a conclusion. AI does not replace that standard. It helps you finally know what that standard requires.

The Teaching Scenario: This episode uses a composite ancestor named Silas Renner, a post-Civil War German-American farmer in Buchanan County, Iowa, with a documented two-year gap in his record between 1865 and 1867. The research map built in this episode surfaces record types most researchers have never searched, and which found three records that had been sitting in free databases the entire time.

For Australian and UK Genealogists: The Research Map framework applies directly to your research. For Australian researchers, the same framework surfaces resources including Trove (trove.nla.gov.au), the National Archives of Australia (naa.gov.au), Public Record Office Victoria, and State Records NSW, covering record categories that sit outside the major platform indexes just as they do for American research. For UK researchers, the framework applies equally to county record offices, the British Newspaper Archive, ScotlandsPeople (scotlandspeople.gov.uk), and specialist collections at The National Archives (nationalarchives.gov.uk). The method is identical. Different archives.

Resources Mentioned:

• FamilySearch Iowa Non-Population Census Schedules (familysearch.org)
• FamilySearch Iowa Grand Army of the Republic Membership Records (familysearch.org)
• Chronicling America (Iowa newspapers) at loc.gov/chroniclingamerica
• HathiTrust Digital Library (county histories) at hathitrust.org
• State Historical Society of Iowa (iowaculture.gov)
• GPS Mini-Series: Episode 30 (Overview), Episode 35 (Element 4), Episode 38 (Element 1), Episode 42 (Element 5, coming)

Companion Guide: The Companion Guide for this episode includes 12 advanced prompts built on the Research Map framework, including specialized versions for African American pre-1870 research, international non-English archives, and DNA-integrated research planning. Available for Patreon members at ancestorsandai.com.

Join the Community: "Ancestors and Algorithms: AI for Genealogy" is our private Facebook group for genealogists learning to use AI tools in their research.

For everything, including every episode, the community, Companion Guides, and The Research Lab: visit ancestorsandai.com.

Connect with Ancestors and Algorithms:

📧 Email: [email protected]
🌐 Website: https://ancestorsandai.com/
📘 Facebook Group: Ancestors and Algorithms: AI for Genealogy - www.facebook.com/groups/ancestorsandalgorithms/

Golden Rule Reminder: AI is your research assistant, not your researcher.

Join our Facebook group to share your AI genealogy breakthroughs, ask questions, and connect with fellow family historians who are embracing the future of genealogy research!

New episodes every Tuesday. Subscribe so you never miss the latest AI tools and techniques for family history research.

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 oral history against primary documents using four free AI tools. What starts as a simple census comparison becomes the discovery of a hidden first marriage, a child no one in the family ever mentioned, and a woman who rebuilt her life in silence after tragedy.

If you have ever accepted a piece of your family story at face value, this episode is for you.

In this episode, you will learn:

• How to use Claude AI to build a cross-census comparison table that surfaces inconsistencies your eyes might miss
• How to use ChatGPT to generate a targeted research checklist for finding a missing marriage or undocumented children
• How to use Perplexity to verify which genealogy records actually exist for your ancestor's state and time period before you waste hours searching in the wrong place
• How to use NotebookLM to organize all your gathered evidence, build a timeline from your uploaded documents, and identify the specific gaps that still need to be filled
• What the "children born" and "children living" columns in the 1910 federal census actually reveal, and why most researchers walk right past them
• How to recognize a second marriage in a census record and what records to search next

The AI tools featured in this episode (all free tiers):

• Claude by Anthropic (claude.ai)
• ChatGPT by OpenAI (chatgpt.com)
• Perplexity (perplexity.ai)
• NotebookLM by Google (notebooklm.google.com)

Records and resources mentioned:

• FamilySearch Indiana Marriages 1811-2019 (free at familysearch.org)
• Indiana State Archives vital records guidance (in.gov/iara)
• 1900, 1910, 1920, and 1930 US Federal Census (free at familysearch.org and ancestry.com)
• Hoosier State Chronicles Indiana newspapers (free at newspapers.library.in.gov)
• Chronicling America historic newspapers (free at chroniclingamerica.loc.gov)

For Australian and New Zealand researchers: The techniques in this episode translate directly to your family history research. Use electoral rolls on the National Archives of Australia website (naa.gov.au) as a census substitute for early 20th century ancestors. State Births, Deaths, and Marriages registries hold marriage records that can surface a first marriage the family never mentioned.

For UK and Irish researchers: England and Wales civil registration indexes marriages from 1837. FreeBMD at freebmd.org.uk gives you free access to birth, marriage, and death indexes going back to that date. Scotland's records are searchable at ScotlandsPeople (scotlandspeople.gov.uk). The family story that nobody told exists in British and Irish families exactly as it does in American ones.

Connect with Ancestors and Algorithms:

📧 Email: [email protected]
🌐 Website: https://ancestorsandai.com/
📘 Facebook Group: Ancestors and Algorithms: AI for Genealogy - www.facebook.com/groups/ancestorsandalgorithms/

Golden Rule Reminder: AI is your research assistant, not your researcher.

Join our Facebook group to share your AI genealogy breakthroughs, ask questions, and connect with fellow family historians who are embracing the future of genealogy research!

New episodes every Tuesday. Subscribe so you never miss the latest AI tools and techniques for family history research.

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, Campbells, Camerons, or any of the great Gaelic families of the northern parishes, the techniques in this episode apply directly to your research.

What you will learn:

• How to use Perplexity to orient yourself to an unfamiliar Scottish archive system before you search a single record, including a four-part orientation prompt that maps ScotlandsPeople, the Disruption of 1843, Gaelic naming conventions, and the historical context of the Highland Clearances in one session
• How to use Gemini via AI Studio (free) to transcribe 19th-century Old Parish Register (OPR) handwriting with expert-level accuracy, including the exact prompt structure that handles Scottish ecclesiastical abbreviations correctly
• How to use Claude to correlate evidence across multiple documents simultaneously, resolve census age conflicts, analyze the Highland naming tradition, and surface the Free Church records gap that explains why so many Highland families vanish from the OPR after 1843
• Why the Great Disruption of 1843 is the single most important historical event in Scottish Highland genealogy research, and how to find your ancestors in the Free Church records at the National Records of Scotland when the OPR goes silent
• What the 1841 Scotland census's age rounding convention means for your research and how to use it to resolve apparent conflicts between census records
• How the Highland naming tradition works as genealogical evidence, including its limits, and how to use it correctly without overstating what it proves

Records and archives referenced in this episode:

• ScotlandsPeople (scotlandspeople.gov.uk): Old Parish Registers, Scotland census 1841 to 1921, Highland and Island Emigration Society records 1852 to 1857
• National Records of Scotland: Free Church records, reference CH16, 1843 to 1977
• Trove (trove.nla.gov.au): For Australian listeners researching Scottish emigrant families in colonial newspapers
• Highland Archive Centre, Inverness (highlandarchives.org.uk)

AI tools demonstrated:

• Perplexity (perplexity.ai): Free tier
• Gemini via AI Studio (aistudio.google.com): Free, used for OPR handwriting transcription
• Claude (claude.ai): Free tier, used for multi-document correlation and evidence analysis

For Australian and UK listeners:

Australian researchers will find the Highland and Island Emigration Society records on ScotlandsPeople an essential starting point. Trove at trove.nla.gov.au holds Scottish emigrant community newspapers from Victoria and New South Wales that name home parishes in Scotland. UK researchers: the National Records of Scotland in Edinburgh holds the Free Church collection that covers the records gap created by the 1843 Disruption.

Connect with Ancestors and Algorithms:

📧 Email: [email protected]
🌐 Website: https://ancestorsandai.com/
📘 Facebook Group: Ancestors and Algorithms: AI for Genealogy - www.facebook.com/groups/ancestorsandalgorithms/

Golden Rule Reminder: AI is your research assistant, not your researcher.

Join our Facebook group to share your AI genealogy breakthroughs, ask questions, and connect with fellow family historians who are embracing the future of genealogy research!

New episodes every Tuesday. Subscribe so you never miss the latest AI tools and techniques for family history research.

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-by-step AI-powered workflow for resolving conflicting genealogical evidence, using a German immigrant ancestor from the Rhine Province of Prussia who arrived through New York in the 1860s and spent the rest of his life in Pennsylvania's coal region. This is Episode 35 and Part 2 of the GPS Mini-Series, with a full-episode focus on GPS Element 4: the resolution of conflicting evidence.

Three AI tools are demonstrated with exact copy-paste ready prompts you can apply to your own conflicting records today. Perplexity with Comet Browser researches historical context for German immigrant Lutheran church records and documented immigrant identity patterns. Claude performs systematic document comparison and evaluates which informant knew what, and when. ChatGPT brainstorms every ranked explanation for why an ancestor might tell his own pastor a different birthplace than he gave the census enumerator five years later.

What you will learn in this episode:

• Why death certificates are the least reliable source for immigrant birthplace information, and what the research literature says about why
• How 19th-century German Lutheran Kirchenbucher in Pennsylvania captured birthplace information and how immigrant identity shaped the answers given
• The critical difference between explaining a conflicting record away and actually resolving it to a defensible professional standard
• How all five elements of the Genealogical Proof Standard work together when your evidence fights itself
• A three-step AI framework applicable to any conflicting records problem in any era and any country

If you research German ancestors, Pennsylvania family history, 19th-century immigration records, or any ancestor whose census records, church records, and death certificate simply do not agree, this episode gives you the exact prompts and a repeatable framework you can use today.

Tools demonstrated: Claude (claude.ai), Perplexity with Comet Browser (perplexity.ai), ChatGPT (chat.openai.com). All free tiers.

Australian and UK listeners: this conflict resolution framework applies directly to convict transportation records, colonial census data, Scottish parish registers, and General Register Office civil registration. Same approach, different archives.

Advanced resources including 12 expert-level prompts and a GPS Research Checklist are available for Patreon members at ancestorsandai.com.

Connect with Ancestors and Algorithms:

📧 Email: [email protected]
🌐 Website: https://ancestorsandai.com/
📘 Facebook Group: Ancestors and Algorithms: AI for Genealogy - www.facebook.com/groups/ancestorsandalgorithms/

Golden Rule Reminder: AI is your research assistant, not your researcher.

Join our Facebook group to share your AI genealogy breakthroughs, ask questions, and connect with fellow family historians who are embracing the future of genealogy research!

New episodes every Tuesday. Subscribe so you never miss the latest AI tools and techniques for family history research.

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 Gold Rush ancestor through the scattered, incomplete, and overlooked records of 1849-1860 California using Perplexity, Claude, ChatGPT, and Gemini via AI Studio. What starts as a hunt for a legendary forty-niner becomes something better: the discovery of a Sacramento Valley farming pioneer who traded a gold pan for a land deed after six weeks in the diggings. The family legend was not wrong. It was incomplete. The technique that uncovered the truth works for any migration-era ancestor who has gone quiet in the standard records.

What you will learn:

► How to use Perplexity to map every surviving California record type from 1849 to 1860 before searching a single database 

► How to use Claude to compare two same-name individuals across records and redirect your research when the evidence points elsewhere 

► How to use Gemini via AI Studio to transcribe a degraded 1851 Sacramento County land deed and confirm your ancestor's identity from a blurred microfilm image 

► How to use ChatGPT to surface non-obvious record types, including 1880s county histories, that standard genealogy databases never return 

► Why an ancestor's absence from the expected records is evidence, not a research failure 

► How the Genealogical Proof Standard's analysis and correlation element applies directly to Gold Rush and migration-era research 

► A copy-paste ready AI research workflow for any ancestor who disappears between census years

Records Covered: 1850 Federal Census, 1852 California State Census, Sacramento County deed records, California county tax assessments, Sacramento Union newspaper, 1880s county history biographies. All referenced platforms verified and currently accessible.

Perfect For: Genealogists researching California ancestors, Gold Rush family history, Western expansion, or any migration-era ancestor who goes cold in the standard records. Equally valuable for any researcher building a coordinated, multi-tool AI workflow.

Free Tools Used: Perplexity (perplexity.ai) | Claude (claude.ai) | ChatGPT (chatgpt.com) | Gemini via AI Studio (aistudio.google.com)

Keywords: California genealogy, Gold Rush ancestor, AI genealogy tools, family history AI, Claude AI research, Perplexity genealogy, ChatGPT family history, Gemini handwriting transcription, FamilySearch California, 1852 California census, Sacramento County records, Genealogical Proof Standard, brick wall genealogy, forty-niner research, migration ancestor, AI research workflow, family tree AI

Connect with Ancestors and Algorithms:

📧 Email: [email protected]
🌐 Website: https://ancestorsandai.com/
📘 Facebook Group: Ancestors and Algorithms: AI for Genealogy - www.facebook.com/groups/ancestorsandalgorithms/

Golden Rule Reminder: AI is your research assistant, not your researcher.

Join our Facebook group to share your AI genealogy breakthroughs, ask questions, and connect with fellow family historians who are embracing the future of genealogy research!

New episodes every Tuesday. Subscribe so you never miss the latest AI tools and techniques for family history research.

If you have a brick wall ancestor with a common name; a William Harrison, a Mary Smith, a John Thomas this episode will change how you research forever.

In Episode 33 of Ancestors and Algorithms, host Brian walks through a completely upgraded FAN Club cluster research workflow that goes far beyond what was covered in Episode 16. The FAN Club method, coined by renowned genealogist Elizabeth Shown Mills, teaches researchers to find answers through their ancestor's Friends, Associates, and Neighbors when direct records fail. Combined with today's AI tools, it is one of the most powerful brick wall strategies available to family historians anywhere in the world.

This episode features four free AI tools; Claude, ChatGPT, NotebookLM, and Perplexity, each assigned to a specific role in a step-by-step research pipeline:

→ Perplexity researches the geographic migration corridors and record repositories tied to your ancestor's community 

→ ChatGPT builds a structured cluster analysis strategy before you search a single record 

→ Claude analyzes your extracted census neighborhood data to identify surname clusters, birthplace patterns, and priority FAN club members 

→ NotebookLM organizes all your research evidence into a single, source-grounded command center

You will hear a complete composite research case from start to finish, including how a neighbor from the same Indiana county led directly to the ancestor's Ohio origins; using only free tools and publicly available records.

Whether you research US census records, UK parish registers and tithe apportionments, or Australian colonial musters and land selection records, the FAN Club principle works in every record system. This episode explicitly addresses all three research traditions with actionable strategies for each.

The research methodology demonstrated aligns with the Genealogical Proof Standard and is referenced throughout the episode; showing how AI assists serious genealogy without replacing rigorous research practice.

What you will walk away with: three copy-paste ready prompts, a four-tool workflow you can use this week, and a new way of looking at every census page you have ever seen.

All prompts and resources from this episode are available free at ancestorsandai.com. Patreon members at ancestorsandai.com receive additional intermediate and advanced prompt guides built directly from this episode's research workflow.

Connect with Ancestors and Algorithms:

📧 Email: [email protected]
🌐 Website: https://ancestorsandai.com/
📘 Facebook Group: Ancestors and Algorithms: AI for Genealogy - www.facebook.com/groups/ancestorsandalgorithms/

Golden Rule Reminder: AI is your research assistant, not your researcher.

Join our Facebook group to share your AI genealogy breakthroughs, ask questions, and connect with fellow family historians who are embracing the future of genealogy research!

New episodes every Tuesday. Subscribe so you never miss the latest AI tools and techniques for family history research.

"All the Irish records burned." Every genealogist with Irish ancestry has heard this warning and most have believed it long enough to stop searching. In Episode 32 of Ancestors and Algorithms, host Brian shows why that warning is not the whole story.

In a live AI-assisted genealogy research session, Brian traces his own Irish ancestor, Caitlin Flanagan, born around 1831 in County Clare, Ireland, who emigrated to Boston during the Great Famine and left almost no Irish paper trail. Using Perplexity and Claude, he navigates the surviving substitute records for pre-Famine Irish genealogy, the land surveys, tithe records, and Catholic parish registers that the 1922 Four Courts fire did not reach; and builds a credible, documented case for a specific family in a specific townland in western County Clare.

Whether your Irish ancestors came from Clare, Cork, Galway, Mayo, Donegal, Tipperary, Kerry, Limerick, or anywhere across Ireland's 32 counties, the AI-powered research workflow in this episode applies to your search.

This episode is for anyone who has Irish blood in their family tree and hasn't known where to start, or who started searching and walked away when the wall felt impenetrable. It is equally valuable for experienced Irish genealogy researchers ready to integrate AI tools into their workflow.

What you'll learn: 

► How to use Perplexity to map every surviving Irish genealogy record for your ancestor's county before searching a single database 

► How to search Griffith's Valuation (free at askaboutireland.ie) and use Claude to analyze hundreds of entries and pinpoint your ancestor's townland 

► How to cross-reference the Tithe Applotment Books (free at nationalarchives.ie) to build 30 years of corroborating land record evidence 

► How to read Catholic parish register images at registers.nli.ie, including what the Latin abbreviations actually mean 

► Why the 1926 Irish Census, releasing FREE on April 18, 2026  could be the breakthrough your research has been waiting for

3 copy-paste ready AI prompts included. Every workflow uses 100% free tools.

AI tools featured: Perplexity, Claude. Records covered: Griffith's Primary Valuation, Tithe Applotment Books, NLI Catholic Parish Registers, irishgenealogy.ie, Virtual Record Treasury of Ireland, 1926 Irish Census. Topics: Irish genealogy, Irish ancestry research, AI genealogy tools, AI family history research, Irish records 1922, Four Courts fire genealogy, Great Famine emigration, County Clare genealogy, Catholic parish registers Ireland, Griffith's Valuation, townland research, Irish census substitutes, civil registration Ireland, Genealogical Proof Standard.

Companion Guides with 17 advanced Irish research AI prompts available for Patreon members at ancestorsandai.com.

Connect with Ancestors and Algorithms:

📧 Email: [email protected]
🌐 Website: https://ancestorsandai.com/
📘 Facebook Group: Ancestors and Algorithms: AI for Genealogy - www.facebook.com/groups/ancestorsandalgorithms/

Golden Rule Reminder: AI is your research assistant, not your researcher.

Join our Facebook group to share your AI genealogy breakthroughs, ask questions, and connect with fellow family historians who are embracing the future of genealogy research!

New episodes every Tuesday. Subscribe so you never miss the latest AI tools and techniques for family history research.

What happens when your ancestor filed a homestead claim, worked the land for a decade, and then vanished from every surviving record?

In Episode 31 of Ancestors and Algorithms, Brian follows the trail of a Volga German family who filed a homestead entry in Rush County, Kansas in 1877. They built a house, dug a well, broke forty acres of Great Plains prairie, and raised five children on the American frontier. Then in April 1886, they filed a relinquishment notice and walked off the land. Three months later, the drought of 1887 began emptying western Kansas of settlers by the tens of thousands.

After that point, the family simply disappears.

This is a brick wall episode. The mystery is not solved. And that is exactly the point.

WHAT YOU WILL LEARN:

The BLM General Land Office Records database at glorecords.blm.gov is free and holds over five million federal land patents, but it only covers completed claims. If your ancestor abandoned their homestead before receiving a patent, their records live somewhere else. This episode shows you exactly where.

How to request a homestead case file from the National Archives using NATF Form 84, even when no patent was ever issued. The 31-page file Brian received contained witness testimony, citizenship affidavits, neighbor names, and land improvement records that no census could provide.

How to use Perplexity AI (free) to map every repository holding homestead research for your state, including the critical difference between completed patents and abandoned claim files.

How to use Claude AI (free) to analyze a multi-document homestead case file simultaneously, identify every named individual and date, and surface the gaps that point toward what happened to the family next.

Why the 1885 Kansas State Census, free on FamilySearch, is one of the most underused records for Great Plains, Midwest, and German-Russian family history research.

What genealogists can do when the 1890 federal census is almost entirely gone. Ninety-nine percent was destroyed in a 1921 fire, and real, searchable solutions exist.

This episode shows what honest, methodical research looks like when the records run out, and how that standard is achievable for every family historian with the right tools.

Every technique shown uses the free versions of Claude and Perplexity. No paid subscriptions required.

Whether your ancestry includes Kansas homesteaders, Nebraska settlers, families from the Dakotas, Iowa, Colorado, or any of the 30 public land states, the AI-assisted research methods here apply to your family history research today.

AI is your research assistant, not your researcher.

Hosted by Brian, an 13-year genealogy researcher and daily AI practitioner. New episodes every Tuesday at ancestorsandai.com, your one-stop hub for every episode, our private research community, The Research Lab, and everything you need to integrate AI tools safely and effectively into your genealogy research.

Connect with Ancestors and Algorithms:

📧 Email: [email protected]
🌐 Website: https://ancestorsandai.com/
📘 Facebook Group: Ancestors and Algorithms: AI for Genealogy - www.facebook.com/groups/ancestorsandalgorithms/

Golden Rule Reminder: AI is your research assistant, not your researcher.

Join our Facebook group to share your AI genealogy breakthroughs, ask questions, and connect with fellow family historians who are embracing the future of genealogy research!

New episodes every Tuesday. Subscribe so you never miss the latest AI tools and techniques for family history research.