Aliens in Their Own Country, Stateless Women and AI

While researching the registration of aliens in the U.S. in 1940 and learning how to obtain an ancestor’s AR-2 form covered in Born in Brooklyn: An Alien in WWII, I wondered if other countries might have had similar laws at the time. (NOTE: This blog post is not intended as definitive, and is not intended as legal advice.)

I am always looking for resources to help to investigate topics. AI has become a resource to find and interpret credible sources. As a genealogical assistant, an AI can explain concepts to me and help me reason through how these laws applied to my ancestor.

The first sections describe the prompts I used, then a list of do’s and a couple of do not’s, with the last section summarizing what I learned about Canadian and British laws, and how they affected my ancestor.

---

I asked AI to help me research similar laws in other counties, specifically in Canada and Britain:

I am interested in learning more about women’s citizenship in Canada and UK when they married an alien

What followed was an informative conversation, where I asked for sources and clarification. ChatGPT provided relevant details and provided sources for the laws.

I then asked the AI to help me reason through how these laws affected my ancestor. Since these people have been dead for many years, I used initials. I could have used single initials or “Person 1” or “Person A” to be less precise. ChatGPT had asked if I had a specific woman I wanted to research, and this time I my prompt was a response:

K.S. (woman) was born in the U.S. and married J.Y. (man) born in Scotland. They married in New York City in 1913. J.Y. died in 1929. K.S. remarried in 1932 to J.G. (man) who born in the U.S.

ChatGPT outlined the timelines of the laws and how K.S. was affected by them, and asked for clarifications at times.

---

When writing the previous blog post I asked:

Can you find me a source that urged people who thought that they might be aliens to register in 1940? Give me the source. If you find a poster of flyer from the time, show me and of course, give me the source where it might be found

The response contains some very good sources for me to use, including the regulations published by the Department of Justice/Immigration and Naturalization Service published its Regulations Governing the Registration and Fingerprinting of Aliens in the Federal Register, including the section number.

and The National Registration of Aliens: Instructions for Registration and Specimen Form,” issued by the U.S. Department of Justice, Immigration and Naturalization Service, Alien Registration Division.

---

Do

• Include in the prompt “Cite sources”
• Anonymize people’s names for privacy
• Ask for explanations of terms and passages that may not be straightforward
• Ask for help to find additional sources

Do not

• Hesitate to ask “Where in the document did you find this information”
• Forget about peoples’ privacy when using AI tools

---

What I learned about Canadian and British laws, and how multiple countries’ laws affected my ancestor:

Like much legislation, the laws surrounding women’s citizenship were complicated. Repeated subsequent legislation would later their status.

What I learned was that women’s situations were similar to the United States in Britain and Canada (although British law considered that there were other countries where a woman to automatically become a citizen of her husband’s country). The following is a simplified version covering some of the key events; you will want to dig farther into the details for your specific ancestors.

Britain’s Naturalization Act of 1870 tied a women’s nationality to her husband’s nationality. The British Nationality and Status of Aliens (BNSA) Act of 1914 explicitly stated, “the wife of a British subject shall be deemed to be a British subject, and the wife of an alien shall be deemed to be an alien.”  The 1914 British Nationality and Status of Aliens Act allowed women who were widowed or divorced the status of British subject.  

Until 1947 there were no Canadian citizens because Canadians were considered British subjects. That meant before 1947 a Canadian woman marrying a foreign national, became an alien. Before15 January 1932, a woman married to a man who naturalized became a British subject even if she was not named on his certificate, and a married woman who was a British subject lost her nationality if her husband became a citizen of another country. After 15 January 1932 a women marrying an alien lost her British nationality if her husband’s country considered her to be a citizen. In 1947, the Canadian Citizenship Act gave women separate citizenship that they retained separate from their marriage. The “Lost Canadians” did not have their citizenship returned automatically. It was legislation in 2009 that retroactively returned their citizenship. In 1948 UK women were given separate citizenship. (In 1947, a woman who married a Canadian did not automatically derive her citizenship from her husband.)

On 22 September 1922, the Cable Act repealed the 1907 Expatriation Act, and women no longer lost their citizenship based on their husband’s nationality. But for women married before then, the situation was more complicated. In 1936, divorced or widowed women could repatriate via an application, and upon its approval taking an oath of allegiance. As of 2 July 1940, an act allowed women to repatriate no matter what their marital status was. The repatriation oaths could be filed in any county, state or federal. They might be separate in a court’s naturalization records (as in Westchester County, NY).

Consider this situation pre-1932: a woman born in Canada (British subject) marries an American man in 1930. By Canadian law she loses British nationality. But after the U.S.  Cable Act of 1922 did a foreign woman did not automatically become an American citizen when she married an American. This woman would be stateless, neither British, nor American.

The widowed Kathryn remarried in 1932 to an American citizen, so she did cease to be a British subject. Since this was after 1922, her marriage to an American citizen did not automatically make her an American citizen. Therefore, legally she may have been in limbo, neither British nor American. She may have been stateless at that time.

In 1933, the situation was remedied for Kathryn and other women in her situation. The British Nationality and Status of Aliens Act 1933 changed the rule. “Under the 1933 Act, a woman would not be deemed to have ceased to be a British subject automatically on marriage to an alien (or when, during the marriage, her husband ceased to be a British subject) if she did not actually acquire her husband’s nationality” (Resumption (History)). Retroactively, women in Kathryn’s situation, who had not gained citizenship through their marriage, regained their British subject status.

On 20 December 1940, Kathryn filed an Alien Registration Form, reporting her citizenship as “Great Britain” (without any notation in the margin that “Applicant doubts need for registration”).

Learning More

When Saying “I Do” Meant Giving Up Your U.S. Citizenship by Meg Hacker https://www.archives.gov/files/publications/prologue/2014/spring/citizenship.pdf

Historical background information on nationality (accessible), Updated 22 May 2023. https://www.gov.uk/government/publications/historical-background-information-on-nationality/historical-background-information-on-nationality-accessible

Resumption (History) [Archived]. https://assets.publishing.service.gov.uk/media/5a81dce5ed915d74e3400763/resumption.pdf

Ethnic Origin And Nativity Of The Canadian People, EIGHTH CENSUS OF CANADA, 1941. https://publications.gc.ca/collections/collection_2017/statcan/CS98-1941M-35-eng.pdf (See document pages 114–115 describing the national status of married women.)

Good luck with your research and let me know how you do!

Born in Brooklyn: An Alien in WWII

Researching women can be challenging. Research married women can be more challenging. Researching women who marry an alien can become more complex. Researching this topic was intriguing and challenging. Then, finding a way to explain its complexities clearly and understandably made this blog post take considerably longer to write than I had anticipated. I learned a lot, and hope you will too! Additional resources to learn more are listed at the bottom of the post.

I always try out databases, and there was only one person I could think of in my family tree who might not have been a citizen in the 1940’s. She married a subject of Great Britain. After her Scottish husband’s death, she had remarried a U.S. citizen, so I did not think I would find her in the database of people who registered under the Alien Registration Act of 1940. (Other countries had similar laws: stay tuned for another blog post about that.)

Surprisingly, her name appeared.

On 6 Aug 1913 my great aunt married James Howie Young, a man who lived in Scotland in her parent’s home. They sailed off to travel through Europe, then live permanently in Glasgow, Scotland. James died in 1929. Later, she married a citizen, John J. Greene in 1932.

The Expatriation Act was passed on March 2, 1907, and at that time “any American woman who marries a foreigner shall take the nationality of her husband.” On 22 September 1922, the Cable Act repealed the 1907 Expatriation Act and women no longer lost their citizenship based on their husband’s nationality when they married. But for women married before then, the situation was more complicated. In 1936, divorced or widowed women could repatriate via an application, and upon its approval taking an oath of allegiance. As of 2 July 1940, an Act allowed women to repatriate no matter what their marital status was. The repatriation oaths could be filed in any county, state or federal. They might be separate in a court’s naturalization records (as in Westchester County, NY). What we do know from the AR-2 is that even though a statutory path to repatriation existed by 1936, Kathryn apparently had not completed it by the date of her 1940 alien registration (20 December 1940).

My first reminder that she had been affected by the Expatriation Act was when her citizenship was listed on a ship manifest for a cruise from Bermuda in 1931. She was shown as a citizen of Britain. (Race or people: German; Returning Resident; Place of birth: Brooklyn.) The record was definitely for her, as she lived at the same address on Stuyvesant Avenue in Brooklyn as the person she was going to join, her mother. (This was also a known family address.) The German race or people was interesting; her late father was a German immigrant to the U.S. who naturalized.

Further searching uncovered that she had returned to the U.S. in 1929 on SS Laconia. Her nationality (country): Britain; Race or people: American. She was a widow, with her nearest relative in the country she departed being her mother-in-law, and she was going to join her mother in Brooklyn. She had been in the United States from 1928 to 1929.

After watching Researching Immigrant Ancestors: Alien Registration (AR-2) Forms Elizabeth Burnes and John LeGloahec in the 2025 NARA Genealogy Series https://www.archives.gov/calendar/genealogy-series/2025#Session%205, I searched for an AR-2 for Kathryn. (Use the link to view the video of the presentation, and to download the presentation slides.)

The parts of the Alien Registration Form are shown below. NARA has the AR-2 itself, but additional parts of the form may be found in A-Files or may no longer exist.

I searched from Access to Archival Databases (AAD) at https://aad.archives.gov/aad/and selected the Flexoline Index Database, which is the finding aid to the AR-2 forms.

Alternatively, you can go directly to the search page at https://aad.archives.gov/aad/series-description.jsp?s=5259&cat=all&bc=sl

If you are having issues finding a person, remember to try advanced searches with broader information like surname and location, and alternate spellings. There were no results for either of her two married names, but there was a result for her maiden name. The use of wildcards is also an option (e.g. Kath* Small).

There was only one result.

I viewed the record.

I clicked on the icon in the View Record column to see the result. (Only the top of the full result is shown below.)

From the information in this search result compared to what I knew of Kathryn’s life, I was sure that this was a record for her. Alien Registration: A4790720

Using the instructions in the presentation, I used the A-number to search the NARA Catalog to see if NARA had an Alien File (A-File) for her. That search was unsuccessful.

I began the process to order her AR-2 file from NARA by sending the email that is described in the instructions at https://www.archives.gov/research/immigration/alien-registration-ar-2. This page also contains a link to sample forms. Since she was born over 100 years ago, the process was simpler than for deceased individuals who were born more recently than 100 years ago.

There was an automated email response reminding me to be sure that I had submitted the required information. I had sent the email on a weekend day, and on the next business day, a NARA Archivist responded that their search in the Flexoline Index had returned a record for Kathryn, and provided both of her married names. (Her married names were not included in the search result from the AAD.) The email also confirmed the results of my search, that NARA did not hold an A-file for her. If you find that NARA has the A-File for your ancestor, follow the instructions in the NARA video for information about how to order it.

The email contained information about how to complete the payment for the order. There is no option to pay online, so follow the instructions. Not wanting to email my credit card information, I elected to wait a couple of days to be sure the order number existed in their system, then called to my provide payment. Within a couple of weeks, a link to download the form was emailed to me. The link is advertised to only stay active for 30 days, so be sure to download it.

Kathryn’s Alien Registration Form gave her physical description, showed her profession as a housewife, and included that she had not been arrested. The date of the affidavit was 20 December 1940. People who were unsure that they were an aalien were encouraged to register, and in the Federal Register, August 14, 1940, §29.4(n), the official was instructed to write “Applicant doubts need for registration” in the margin of the form. According to the Statement by the Department of Justice paragraph in Congressional Record of the Senate, 1941, thousands of people doubted their status and registered for their own protection. Kathryn has no such notation.

Upon not finding an A-File at NARA, the suggestion is that I could possibly pursue if USCIS might still hold an A-File for her, and had not yet transferred it to NARA. What I learned from the Westchester County, NY, courthouse was that these women could have filed an Application to take Oath of Allegiance as a Naturalization Repatriation. (The database had no entry for her in that County of her residence.) USCIS may not hold an A-File for her, and searching for one incurs a cost, so I may not do this check. It is also possible that she never did repatriate.

Upon prompting, ChatGPT put together an infographic about the AR-2 to A-file process using information at: https://www.archives.gov/research/immigration/alien-registration-ar-2. Google Gemini verified the information in this image using information found at the NARA AR-2 webpage.

The laws concerning a women’s citizenship in these days was not straightforward, so I did a little more digging. Stay tuned for another blog post with more information about other countries’ similar laws and how Kathryn may have been stateless after her second marriage.

Learning More

Alien Registration (AR-2) Forms https://www.archives.gov/research/immigration/alien-registration-ar-2

To learn more about Flexoline files, go to https://www.archives.gov/research/immigration/flexoline

Researching Immigrant Ancestors: Alien Registration (AR-2) Forms Elizabeth Burnes and John LeGloahec in the 2025 NARA Genealogy Series https://www.archives.gov/calendar/genealogy-series/2025#Session%205

When Saying “I Do” Meant Giving Up Your U.S. Citizenship by Meg Hacker https://www.archives.gov/files/publications/prologue/2014/spring/citizenship.pdf

Westchester County County Clerk: Index for N – O https://archives.westchestercountyny.gov/county-clerk/n-o#series11

Federal Register, August 14, 1940, https://www.govinfo.gov/content/pkg/FR-1940-08-14/pdf/FR-1940-08-14.pdf (see §29.4(n) on p 2840)

The National Registration of Aliens: Instructions for Registration and Specimen Form https://digital.sciencehistory.org/works/rnpj9e5

U.S. Congress, Congressional Record, 77th Cong., 1st sess., April 1, 1941, vol. 87. https://www.congress.gov/77/crecb/1941/04/01/GPO-CRECB-1941-pt3-9-1.pdf (see Statement by the Department of Justice paragraph 3 p 2773 )

Give it a try, and let me know who you find!

Researching WWI Contractors

There is a picture of Thomas Patrick McMahon in a dough boy’s uniform, but no records can be located that document any military service. So, why was he wearing a WWI US Army uniform in a picture?

This post includes how artificial intelligence (AI) was used to begin the investigation of the answer, and how it provided context for additional work.

At the time of his WWI draft registration he was 25, single, and a naturalized citizen. His trade was carpenter and he was self-employed.

The answer was discovered by his descendant, my cousin, in the US Army Transport Service (US ATS) records. If you have read my books or blog, or seen me lecture, then you know how much I appreciate these records. They are a mini-census, showing details of Army personnel who were transported on US Navy ships. Thomas McMahon had sailed from Hoboken, NJ, and traveled to France as a 2nd Class Civilian Employee in the organization: U.S. Civilian Employees, U. S. Engineer Department, James Stewart & Co. Contract, on Agamemnon and returned on

The US ATS records found online are digitized of records that were originally stored in folders; there was one folder for each sailing. When you find a manifest containing an entry with the person you are researching, I recommend going backwards through the images to the front of the set to locate the pages containing details about the sailing. In this case, the front images contained the description of cargo that was transported on Agamemnon to France (both handwritten and typed) was interesting. Agamemnon was transporting 25 tons of telegraph supplies, 9 tons of aviation supplies, 79 tons of Signal Corps General supplies, 993 tons of French steel, and other supplies.

The Naval History and Heritage Command (NHHC) provided information about Agamemnon (Id. No. 3004) during 1917-1919, which included her voyage to Europe in mid-January 1918. Five days into the voyage the convoy faced heavy seas, and Agamemnon turned on lights and circled back after a report of a man overboard. Falling into a trough, a 43-degree roll caused the loss of some material. Fortunately, no one was lost. She continued on for a brief stop at St. Nazaire, then on to Brest where she docked on 24 January.

The images at the front also included information about the cablegram received by the Navy Department stating that the ship had made it safely to France.

I decided to use AI as an assistant to strategize how to learn more about contractors in WWI and the specific contractor.

ChatGPT provided some information about the engineering effort during WWI, and recommendations about where to search. It suggested searching in NARA’s Record Group 77, which contains records for the Army Engineers which would have information about the contracts let by the organization. I suspect all that we might find is what the contract was for; it would be up to the company to find the people to fill the roles.

Google Gemini was more helpful in this case.

Gemini explained that uniforms were worn by civilians so that they would not be mistaken for spies if captured, and they would receive treatment under the Geneva Convention. (This explains photographs of civilians wearing uniforms in war zones!) It also shared information about James Stewart & Co. recruiting a skilled workforce for infrastructure project in France, such as piers, warehouses, fuel tanks and depots.

It captured its findings in a nifty report WWI Civilian Contractor Research Report
Subject: James Stewart & Company | Port of Brest | Militarized Civilians

Gemini referred me to a source: United States Army in the World War 1917-1919 General Orders, GHQ, AEF, Volume 16. This volume was one of seventeen which compiled selected American Expeditionary Forces (AEF) records. Volume 16 captured all of the General Orders given by General Pershing.

The General Orders contain directives issued from the top, the General Headquarters. They dictated the command structure, logistical support, and standards of conduct for the entire force. I scanned these orders for the reference material that Gemini promised. I did not find details of the contractors’ uniforms in the G.O.’s listed by Gemini. There were many references to uniforms, but I did not find full details of the contractors’ uniforms. G.O. 46, 1917, did have details about the uniforms worn by the French interpreters, including the sphinx insignia they wore. G.O. No. 63, 20 Nov 1917, address identity cards which were required for all the AEF and the militarized civilians. There were G.O.’s with details of civilian pay. Additionally, G.O. No. 30, 15 Feb 1918, IV. 7. (n)(1) “Two aluminum identification tags, to be furnished by the Q. M. C. [Quarter Master Corps], will be habitually worn by all officers and enlisted men, and also by all civilians attached to the A. E. F.” G.O. No. 23, 20 Aug 1917, 1. 5. discussed the importance of clerks and civilians in uniform saluting officers.

Thomas P. McMahon traveled back to the U.S. on the U.S.A.C.T. Honolulu, which sailed from France on 1 Dec 1918. He arrived at Newport News, VA, on 21 Dec 1918. His Group or Classification was shown as “Civilians for Discharge.”

The war was over for Thomas, and he was back home in the U.S. for Christmas. His brother, my grandfather, would march to Germany after the Armistice and participate in the Army of Occupation. He would return in July of 1919.

I had one question left. From the information I could find about the contractor, Thomas was probably working at Brest. (The NHHC excerpt did not indicate any one/thing leaving the ship at St. Nazaire.) If Thomas were working at the port of Brest when Joseph arrived in August 1918, did they see each other? In the activity of that port, it would be remarkable if they might have
seen each other, but the 51st PIR spent time at the port unloading the Kroonland
after they arrived (joys of being a Pioneer Infantryman!), so maybe, just maybe.

Fortunately I was able to locate “A Century of Construction (1844–1944)” James Stewart & Co.” through an interlibrary loan. While work done in the United States and around the world was documented, little was recorded about WWI in the narrative. WWII was much better documented. There was a table listing War Construction projects in the United States during WWI. There was also a table of projects done for the American Expeditionary Forces in France. Brest was not listed among them, but St. Nazaire was. It may be that the list was incomplete, or that he worked in another place. Either way, there is more to learn.

FamilySearch Full-Text Search for the Win!

Recently I followed up on an Ancestor hint relating to a branch on my maternal line, which led me to interesting discoveries.

In my family tree, Maria, a seemingly abandoned Irish woman and her three children entered a workhouse in England. Fortunately, she and the children left it in a year. At least one of the children (my great-grandmother, Mary Ann) made her way to Providence, RI, where she married my great-grandfather. (I have previously blogged about finding an ancestor in a 19th century workhouse in https://aweekofgenealogy.com/found-ancestors-in-the-workhouse/).

A death certificate record was located in Providence, RI, for a woman whose data seemingly matched Maria’s. Standing alone it was certainly of interest, but no other records had been found to put her in that place and time. I admit to being somewhat skeptical. Knowing Irish naming patterns, causing the repetitive use of names within family units, I wondered if this might be a relation rather than Maria herself. Were these common names where she originally hailed from in Ireland? Or was it coincidental?

The Ancestry hint sent me to a family tree that contained a person with the same name of my great-great-grandmother along with her two sisters. The documentation for those two sisters was more detailed than that for my great-great-grandmother, suggesting the owner of the tree was not along the same line as I. I followed the suggested records and built out a detailed pictures of two women who had immigrated to the United States and came to call Providence, RI, their home.

I always look for the records that document facts in a person’s life, link people, and tell a story, and I found some. In my own family tree I added these two women without connecting them to Maria in the main tree When I found records on Ancestry, I attached them to these women, downloaded them, and copied the source information. I also took snipped screenshots of the relevant data and captured it in a timeline built in a Word document. So far, so good.

Margaret, the elder of these two sisters, had come to Providence and married before Ellen. Ellen arrived in 1880 and was shown in the census of that same year, living with married Margaret. (This suggested a chain migration.) Ellen worked in Providence and married several years later in 1889. Sadly, Ellen died in 1899 at age 38. At that time, she was already a widow, and she left behind two young daughters. Margaret died in 1904, leaving behind a husband and six children. My great-great-grandmother, Maria, died in 1902. The records for all three women that contained parents’ names were consistent:

Father, William Connaughton

Mother, Bridget

As I searched through the records Ancestry suggested, a standout was the Providence, Rhode Island, U.S. Old Stone Bank Records, 1844-1924 at https://www.ancestry.com/search/collections/62959/. Both Margaret and Ellen had bank accounts, and along with other identifying information, there was common data:

Birthplace: Co. Roscommon

Margaret’s entry contained additional data:

Mother, Bridget Murphy

So, parents had the same names. If Maria was in fact their sister, I would then know the county where she was born, and the maiden name of her mother.

I looked at Maria’s death information again and noted the address where she had died. It was the house owned by Margaret and her husband. Evidence was mounting, but I was still wondering if she might have been a cousin or another relation.

Contacting the owner of the tree was a good idea, but had I tried before? I checked the messages on Ancestry and viewed the messages exchanged 2019. (I could have consulted my correspondence log, but this was more convenient. I admit to being on a fishing expedition rather than focused on answering a research question.)

Based on that previous correspondence, I doubled checked DNA matches. By my calculations, we were fourth cousins, once removed. Yes, this contact did know more about Margaret and Ellen than Maria.

At this point, circumstantial evidence was being built, but I wanted one record to connect Maria with one of her sisters. Searching for Maria, or her daughter Mary Ann, in the Old Stone Bank records and the 1900 US Census in Providence (and Rhode Island) was not fruitful.

It was time to move laterally to check other indexes and other databases. I decided to search on FamilySearch for records that would be helpful in connecting Maria to these two women.

I decided to jump in and use FamilySearch’s Full-Text Search to find those records that might have mentioned Maria, even if the record was not about her. Full-Text Search has moved out of the FamilySearch Labs and can be selected from the Search Menu.

As a reminder, the best way to search for a person is to enter their name within quotation marks in the Keywords field.

Carefully reviewing results…there was result contained a death record I had not yet seen.

The same address was in the record, namely the home owned by her sister and brother-in-law. The parents’ names were there (without her mother’s maiden name).

In this record there was data that was not included in the register:

Name of Informant and Relationship to Deceased: Thos. Kelly Brotherinlaw

Thomas was Margaret’s husband! He and Margaret owned that house. Since he was Maria’s brother-in-law, that made Margaret her sister. (None of her late husband’s people were identified in the proximity.) FamilySearch Full-Text Search for the win!

That was the definite piece of data I needed to call my brother and tell him that we had roots in County Roscommon, and that our great-great-great-grandmother’s name maiden name was Murphy. (Even though he lives in time zones behind mine, it was so late that I waited until the next morning to make the call.) It was also a good reminder:

Always look for all the records related to an event, focusing on the ones made closest to the event.

The details in Returns of death were recorded by a physician. The data on them was used to make an entry in the register. Death indexes and death certificates draw data from the ledger.

Engineers are known for being belt-and-suspenders people. Being that way meant that in addition to downloading the records, saving sources, and extracting the information into my timeline document, I added the record to my tree (my part of the one family tree) on FamilySearch.

That is where the middle-of-the-night surprise occurred.

A brother to Maria, Margaret and Ellen is shown in that tree! Back to the drawing board to see if the records prove out James Joseph Connaughton’s relationship to these sisters. (The first record I looked at was his Intention to Marry in Providence in 1883, with his parents: William Connaughton & Bridget Murphy.)

But right now it is time to connect Margaret and Ellen to their sister and parents in my family tree on Ancestry.

Google NotebookLM Tutorial

This is it! You have decided to give Google’s NotebookLM a try!

Maybe you want step-by-step instructions, or just want to look over the process before diving in. Either way, this tutorial stands ready to help.

What will you do in this Notebook? One suggestion is to upload a group of documents related to a subject or ancestor. These are documents that you want to understand better or analyze. Don’t overthink it. You just need to have an idea of your subject, because once you begin to use the Notebook more ideas will probably come to you.

In this tutorial, we’ll get started with a brand new NotebookLM, add documents to it, then based on those documents generate an Audio Overview, an Infographic, a Slide Deck and a Video Overview.

NOTE: For this tutorial, keep in mind that Google may change how it looks or add/remove specific functionality and labels at any time, but the basic ideas will remain.

When you have decided the topic for your Notepad, it’s time to get going and create it.

In my example I will add only a few documents: the homestead patents and pages from the tract books for Charles F. Gilroy.         

Here’s the link:

https://sites.google.com/view/notebook-lm/login

Login to your Google account here. If you are already logged into Google in the same browser, you may go directly to this page:

You’re in!

Select Create new notebook to start.

After you have created a new notebook, a window pops up asking you to add media. (This is the same window that will open when you select + Add sources)

As of this writing the Notebook supports: Google Docs, Slides, PDFs, text files, web URLs, YouTube transcripts, and audio files. When you enter a link a YouTube video, only the transcript will be used and the video has to be public.

For best results, enter documents with text in them. There is no guarantee that images will be transcribed properly.

From this window you can drag and drop the files you want to add to your Notebook.

When adding to this Notebook, I have to admit that I did not follow the text-is-best rule. That means I will need to verify the transcription that the Notebook is using was done correctly. I added Land Patents and Tract Book images. (The Tract Book images had been located by FamilySearch Full-Text Search!)

On the left, I selected one of the sources, and viewed a description of the document containing key information from it that had been extracted. 

The workspace that opens is called the Notebook, and it has three windows labeled: Sources, Chat, and Studio. The first two are self-explanatory.

The third window is the Studio Window, which is also called the Studio Panel.

There are two sections within the Studio Panel. One section is home to the buttons, called Action Tiles, where you ask the Notebook to generate complicated multimedia products. By selecting an Action Tile, the Notebook to generate audio or visual presentations, infographic, slide decks, reports, mind maps and more. At this point, several Tiles are labeled “Beta” which means they are almost ready to be full-fledged features but are still being evaluated. Do not let that dissuade you from trying them! Test them out for yourself.

The second section is the Generated Resource List. When you request a product, you will see it added to that list. The list is empty for a new Notebook. As you choose products, the list is populated with the generated media. Next to each resource in that appears in the list there is a 3 dot menu (snowman) where you can Rename, Download, Share or Delete a resource. When you rename a resource, that changes only the name and does not change any of the media’s content.

After uploading the documents, a name for the notebook was automatically generated.

I renamed the Notebook.

Audio Overview

First, I tried an Audio Overview based on the few documents I had uploaded. This action offers to “Generate an AI podcast based on your sources.”

Documentation for the Notebook had explained that it may take some time for the Audio Overview to be generated.

Within minutes, I was listening to audio in a podcast format of two people explaining and discussing the documents and their context in a pleasant conversation presentation. It was 19 minutes, 12 seconds in length.

A clip from this audio is here:

Infographic

Next, I decided to generate an Infographic based on the documents.

In the Generated Resource List at the bottom of the Studio Panel, there was a spinning circle to indicate that the infographic was being generated. When it was done, I could select it from the list.

I clicked on the Infographic in the list in the Studio window

and a Viewer opened up. I had options to share, download, collapse the Viewer and close the Viewer in the upper right hand corner.  

After I closed the Viewer, I could click on the snowman (3 dot menu) and to be presented with options: Rename, Download, Share, Delete

This is one of the features that in BETA, but the infographic that was generated was interesting.

Slide Deck

An option is to generate a Slide Deck. At this time, this feature is in BETA.

I selected Slide Deck and waited while it was generated

When I clicked on the Slide Deck in the Resource List, a Viewer opened up where I could look at the slides, and interact with them.

I particularly liked this slide

NotebookLM Generated Slide

I also liked the option to download the slide deck as a PDF or a PowerPoint document.

Selecting “Revise” gives you the chance to interact and make change to the slide. The pending changes will be generated in a few minutes (or longer).

Video Overview

I selected the Video Overview Tile

and accepted the default selections, which included the longer Explainer format.

Generating that video took a long time. When I quizzed Gemini if I could find out how long it took to generate a product, I was told no, but that this task usually took from 5 to 30+ minutes.

At the end of that response, Gemini asked me if generating was taking a long time, and when I said yes, Gemini recommended that I refresh the webpage because the user interface had not updated. When I followed this recommendation, it appeared that the Video Overview generation had failed.

I deleted the Video Overview entry on the Generated Resource List, and tried again. This time I selected the option for a Brief Format.

The brief format video was generated within minutes, providing me with a video 1 minute and 50 seconds long.

When I clicked on the Video Overview in the Generated Resource List it opened a window within the Studio Panel. The video gave the context of the Homestead Act then dove into presenting data about the two homesteads’ and their patents.

An excerpt from the video:

An Experiment in the Chat Window

I have engineering experience in testing, which matches my style of pressing the buttons and trying the features. That made me want to see if I could get some general information in a Chat within the Notebook.

I asked in the Chat window of the Notebook: If I upload a Word document with newspaper clippings can you transcribe all of them?

This was answered literally, using only the data within the Notebook. (At that point, there was no Word document in the sources containing newspaper clippings.) So if you have a general question that is not based on the information loaded into the Notebook, or have a question about how NotebookLM works it would be better to ask it in Google so that Gemini can answer it.

Gemini told me that “…if the clippings are embedded as images (e.g., photos or scans of newspaper pages), NotebookLM may not automatically transcribe that visual information into searchable, readable text” reminding me that “NotebookLM is designed to work with machine-readable text. If your Word document contains photos of newspaper clippings, the AI may be unable to “read” or transcribe the text inside those images.”

Getting back to my Notebook

When you need to revisit your Notebook, or login on a different computer, you can choose it from your list of Recent notebooks.

Current Limitations

According to Gemini, currently free accounts have limits of generating approximately 3 Audio/Video Overviews per day, and can only send 50 chat queries per day. The Free accounts are limited to 50 sources per notebook, and are limited to 100 notebooks. (Workaround for large projects: Try combining multiple, smaller documents into a single PDF or Google Doc before uploading.)

Google has a tutorial that provides good information in an overview, and it can be found at: https://sites.google.com/view/notebook-lm/tutorial

Give this a try and explore the Tiles and Chat. Let me know how you do.

Have You Tried Google’s NotebookLM Yet?

Trying out NotebookLM has been on my to-do list for months. I just did, and I was blown away by it. The accessibility of technologies that I knew existed but had so well not seen integrated was impressive. You can chat with the AI about what has been added to the Notebook, and you can generate products based on what the uploaded documents. The AI-generated media and responses in the Notebook are all based on the documents that you upload to it, which should reduce the opportunity for AI hallucinations. Keep in mind that the best idea is to enter documents with text; there is no guarantee that images will be transcribed properly.

I had already identified a couple of ancestors as test cases. One is all-time family favorite who was born and raised in Newport, Rhode Island, served in the Army during Spanish-American War, then settled on a homestead out in Oregon. He was a poet and a raconteur who loved to travel and was always involved in social movements.

Another ancestor is one of my brick walls. He is the only German immigrant in my tree (so far), and while I have clues about his origins in Germany, I cannot pin down his arrival to the United States or from whence he came. What I have learned about him is in the U.S., and begins when he was married to an Irish woman, after he had anglicized his name. From the time of his marriage, he never lived near other German immigrants. Very knowledgeable and generous researchers in Brooklyn, New York, and in Germany have helped me follow up on the very limited clues I have developed. The ability to pull together the material and look at it from different perspectives has the potential to help with this brick wall.

If you have not had a chance to try out NotebookLM, here is the link:

https://sites.google.com/view/notebook-lm/login

If you are interested, I have put together a step-by-step tutorial that will get you started here: Google NotebookLM Tutorial.