AI: Meta Prompting

If you have attended one of my AI presentations, then you know how important it is to develop prompt engineering skills to get the most out of Large Language Models (LLMs). The good news is that we do not always have to create the perfect prompt on our own!   

There is a harsh term used in my field, GIGO, which stands for Garbage In, Garbage Out. When it comes to AIs, this applies to the fact that the LLM response (output) will only be as good as our prompts (input).  

A simple explanation of meta prompting is to have one Large Language Model (LLM) create a prompt for another one. Meta prompting is more involved than that because it builds a prompt with more specific instructions about the steps to take to realize the goal of the prompt. It is as if the LLM is translating what you want to do into LLM language!

The cinematic arts student at my home gave me some insights into his practical use of meta prompting. He was having an issue with an AI that generates video. It was not creating what he was describing, so he turned to ChatGPT to explain his vision and ask for a prompt to use for generating that image. ChatGPT dutifully responded with a prompt that did work with the AI video generator. The message is that when it comes to crafting prompts, we are not on our own.

While working to understand meta prompting, I thought of an example application to try before applying this skill to genealogy. I asked ChatGPT to create a prompt for me that I could use to have a research report generated for me about a topic. I also specified what and how I wanted to investigate the topic, as well as the fact that I wanted sources and in-text citations. Using the power of the AI to recognize patterns, I certainly wanted analysis to be part of generating the data in the report.

A prompt was created, but ChatGPT had some specific questions that it included in its response about the type of citation I wanted and asked if there were other constraints, such as word count or including quotes. We had a conversation to refine the prompt, starting with a 308-word prompt and concluding with the final response which was a modular, reusable 1122-word prompt.

The prompt began with: “You are an expert in …

The prompt contained sections for FOCUS & SCOPE, RESEARCH & SOURCES, STRUCTURE OF THE REPORT, STYLE & LENGTH and FINAL OUTPUT

ChatGPT’s prompt also included some interesting anti-hallucination guidance: “If there are areas where evidence is limited (for instance, few direct author comments about a particular name), clearly indicate uncertainty and base comments on reasonable inference, not fabrication.”

I decided to use the prompt in ChatGPT, and opened a new chat. I pasted in the prompt, and it responded with a request for clarification:

It offered me options, providing details, which are omitted for brevity:

• Option A — Use only 100% verifiable, well-known, widely documented sources
• Option B — Allow me to cite plausible but harder-to-verify sources
• Option C — A blended approach

Then it asked me to respond with which option it should use:

After the clarification interaction, ChatGPT told me that

It waited for my response before it began to generate the report:

The report was reasonable, and described patterns. ChatGPT offered me formats for downloading the report and other products based on the report, an executive summary and PowerPoint presentations. If I want to dig deeper, this report is valuable to me as a starting place.

Of course, the caveats still remain about not using this for school reports (unless the assignment calls for the use of AI) and not submitting it to a client. There can be tell-tale signs of an AI-generated report, as I know from a high school science fair project done by that same cinematic arts student, and documentation out on the web.

So, will you try meta prompting? Let me know how you do.

NCGS Fall Conference 2025

Recently I had the pleasure of presenting at, and attending, the North Carolina Genealogical Society Fall Conference 2025. The Conference was very well planned and organized at a wonderful venue with great food. As much as I appreciate the reach of virtual presentations to give presentations at many places far from where I am based, it was nice to be with a group of genealogists, learning and chatting.  

At the Conference, I presented sessions about Military Research and Artificial Intelligence (AI). When speaking about military research, I always customize my presentation to include finding military records for the location of the audience. North Carolina has great resources, both in person and online!

With a Ph.D. in Computer Science and Engineering, I am always reaching deep into the technology of AI to learn its inner workings, and to then share an understanding of how it works and how to use it. As a graduate school professor in cybersecurity, and having tested computer code used on military aircraft for years, I also have a perspective about what we should be concerned about and what can go wrong.

What was also fantastic about the Conference was that people could attend the lectures virtually. The NCGS members and technical staff streamed the presentations and recorded them for attendees to watch later. I knew everything was working when questions from online viewers came during the lectures and insightful questions via email were waiting when I returned to my hotel.

Even though my research in North Carolina is limited to a few months during WWII at Camp Davis, I did attend J. Mark Lowe’s presentation, “Creating North Carolina Local and Regional Locality Guides.” (Mark’s smile is even bigger in person!) The presentation definitely had information that I will carry forward to the places where I do research. I will never look at detailed maps the same way again.

I attended another terrific presentation about using DNA to solve maternal surnames by Kate Penney Howard. Jon Smith’s workshop about using AI for creating locality guides certainly shifted my mindset from the free form text I have been using, and his tips about using Gemini in Chrome tabs were game changers. Thankfully the presentations were recorded so that I can enjoy Diane L. Richard’s presentation about Researching Your Ancestors as Kids. (Diane and I share an educational experience: Go RPI Engineers!)

The beginning-to-intermediate artificial intelligence presentation I gave on the first morning may have provided a warm-up for Steve Little’s intermediate artificial intelligence presentation. It is always interesting to see how other genealogists are using AI tools, and how its use is gaining acceptance. Promise to keep checking your output and stay sensitive to privacy concerns!

Thank you to everyone who planned and worked on making the 2025 North Carolina Genealogical Society Annual Conference such a great experience, to the audience members who shared their time with me, and all the other instructors and attendees for a rewarding and fun time!

NCGS 2025 Fall Conference

Will I see you there?

I am excited to be invited to present in person and online!

On Friday, I will be presenting Ancestors, AI, and Prompt Engineering.

On Saturday, I will be presenting a Crash Course in Researching Ancestors in the US Military.

There are great speakers, and great talks, Friday and Saturday. There is also an optional Beginner Day on Thursday, featuring four lectures just for beginners!

Thomas Kennedy as a Clergyman

In previous posts I have been relating my searches for and research about the Rev. Fr. Thomas Kennedy. I learned of his existence and connection to my family through a FamilySearch Full-Text Search Finding Amelia Small in FamilySearch Full-Text Search. First, I looked into records about his life in Tracking the Rev. Fr. Thomas Kennedy and then I followed the trail to learn about The Military Service of Thomas Kennedy. Now it is time to see what I can find about his life as a clergyman.

After searching Brooklyn City Directories (both by name, and by Municipal Registers for clergy assigned to Catholic Churches) and censuses, and not finding anything that seemed to fit definitely, it was time try Google. Through Google, I learned about the Diocese of Brooklyn, and its archives. Those archives contained a list of historic churches. These were were good resources, but at this point they did not help me tune into this ancestor.

From the Google results, I followed a link to the text of Priests and Parishes of the Diocese of Brooklyn: 1820 to 1944 which is where I found a big break. There was only one Thomas Kennedy in the alphabetical listing, and his time as a priest fit with what I had learned about him. The entry for him with abbreviations and dates:

Kennedy, Thomas J., ––-, -–– (SBA 6-22-1873) 9-26-01 S John Evangelist-73; S Malachy-74; S Francis Col -78; ILR-83; S Joseph, Hewlett-84; 0 L Sorrows, Corona-85; S Malachy Home -01

I decoded several of the abbreviations, then decided to copy the text that contained the explanation of the coding of the entries into ChatGPT, and told it to use those instructions to decode the Thomas Kennedy entry. Between us, we had a history of his religious life.

• Name: Kennedy, Thomas J.
• Birth date, Birthplace: Unknown/unrecorded
• Death date: 26 Sept 1901 [this is one day different than what I had]
• Seminary: St. Bonaventure, Alleghany [Allegany], Pennsylvania [this is in New York State]
• Ordination: 22 June 1873

His assignments were listed by year (approximately). The entry for “ILL” is for Illness, Leave, Resignation. Presumably it was for illness as he resumed his service as a priest after it. The instructions in decoding the entries included a note that his ordination may not have been at the seminary.

Later in the book his order is given as the Society of Fathers of Mercy (S.P.M.).

With what I learned from the Office of Diocesan Archives for the Roman Catholic Diocese of Brooklyn, I knew that Diocese covered Brooklyn, Queens and Long Island. That helped to make sense of where the churches were (and are). I also learned that their archives contains deceased priest personnel files.

His last assignment was at St. Malachy’s Home, in Rockaway, Queens, New York.

The next stop was the webpage for St. Bonaventure’s University, and their archives. In their digital archives I located an Alumni directory of Saint Bonaventure’s College and Seminary, 1859- published in 1928 (with no copyright restrictions). On page 123 there were several Rev. Thomas Kennedy entries, but the years and Diocese matched what I knew:

In the Catalog of St. Bonaventure’s College there were several other mentions of a Thomas Kennedy who distinguished himself in Logic, Natural Philosophy, and Rhetoric, but I will have to analyze these more to be certain it is our Thomas Kennedy.

With all the knowledge I now had, it was time to go back to the newspapers. Newspapers are one of my favorite resources. They were the social media of past times. I located articles about the Rev. Thomas J. Kennedy in the Brooklyn Eagle.

One article from 1873 how Thomas Kennedy of this city [Brooklyn] was among those receiving orders at St. Bonaventure’s College.

Another article in 1897 celebrating his silver jubilee as a priest included a biographical sketch, which discussed how he turned to religion when being nursed by the Sisters of St. Vincent in a Washington hospital after his left arm was wounded at the Second Battle of Bull Run. He had been ordained by the Bishop Ryan of Buffalo. Due to his wound and his health, he had resigned and was stationed at Malachy’s orphanage. (See picture above.)

Then, in 1901, an article titled “Father Kennedy Dying” appeared. (The link to the clipping may not require a free account at Newspapers.com to view.) This column held the answers to so many questions. Some were about details of his service in the military, and why he was absent without leave (his wound). It included other facts, like his studies at and graduation from Notre Dame before attending seminary at St. Bonaventure’s College. He was a member of the Great Army of the Republic (G.A.R.) Post No. 569, which had the distinction of being composed of all priests. Sadly, his health had deteriorated, and in his retirement he had moved to Kentucky to spend his final days in the monastery [the Abbey of Gethsemani].

It also included the fact that he was born in County Longford, Ireland, and immigrated with his parents. This points to where his sister (my great-great-grandmother), as well as my great-great-great-grandparents, came from in Ireland. They lived in Harlem [Manhattan, New York County] after arriving in the United States.

There are many more avenues to follow about his education, his service the military, and his time as a priest in the Diocese of Brooklyn. Other avenues come with limitations in the passenger lists of the time, and the scarce records in Ireland during the mid-1800’s. But finding a county or origin in Ireland is a start!

Without a doubt, I had won the genealogical lottery. You can be sure that I immediately called family members to come into my office to view the column, and his picture!

Finding Amelia Small in FamilySearch Full-Text Search

Researching an Irish family in New York City can have its challenges. Some surnames were very common, and traditional naming patterns often resulted in many individuals with the same names across different branches of the same family group. The passenger lists of the mid- to late-1800s contain little identifying data. It can be difficult to trace these ancestors back to their place of origin in Ireland. With these challenges, one strategy to unravel the stories is searching for family units rather than individuals. The other strategy is to use collateral research.

Of course, I have searched through the unindexed probate and land records available on FamilySearch, but the indexes built into those records will only show the name the name of the main subject. The text of these documents may contain other names and events, and the Full-Text Search helps you find them!

I have been entering the names of these mysterious ancestors into the Full-Text Search and recently had a success connecting one ancestor to another relative who came to the US. This might open an opportunity to do collateral research. You can view a previous blog post describing how to use this tool at FamilySearch Labs: Full-Text Search.

I began at https://www.familysearch.org/labs, and entered the name my ancestor Amelia Small in the search box. Since this search focuses on pattern matching, remember to search for a woman’s birth name and married name. As a reminder, Full-Text Search works better by entering the person’s name between quotation marks into the Keyword field (rather than the Name field).

One of the results was intriguing. My ancestor Amelia Small’s name appears in a probate record, and the address is where she resided.  

Clicking on the record collection name at the top of the result opened a new tab with the record and the full transcript. The search terms were highlighted.

ChatGPT offered a better formatted transcription of the text:

…kin of the deceased, adopted child or children, as far as they are known to your Petitioner or can be ascertained by him with due diligence, are as follows:

JOSEPH N. MATIER, a nephew residing at 226 Bridge Street
FRANK A. MATIER, a nephew
CATHERINE P. MATIER, a niece
CASSANDRA L. APPLEGATE, a niece residing at Gravesend, L.I.
AMELIA SMALL, a niece residing at #364 Hart Street, Brooklyn.
BRIDGET MATIER, a widow of William F. Matier, who died at the County of Kings, on the 24th day of October 1901, residing at 694 Sackett Street, said Borough.
THOMAS MATIER, a grand nephew (son of William F. Matier deceased) residing at 694 Sackett Street, Brooklyn.
WILLIAM MATIER, a grand nephew (son of William F. Matier) residing at 694 Sackett Street, said Borough.

Amelia Small was an heir! I recognized her siblings from the family structure, and from the address listed for her. A list of heirs can be valuable, and in this case, it provided siblings’ addresses, women’s married names, and even a sibling’s death date.

Amelia was the niece of the subject of this document. I followed the back arrow to see the first page of the Application for Letters of Administration for the deceased, Thomas Kennedy, who had died intestate (without a will).

From Amelia’s death certificate I knew the names of her parents, William Matier and Mary Kennedy, both born in Ireland. Some pieces were falling into place. This suggests that Thomas Kennedy was Amelia’s mother’s brother.

There was some other information on that first page.

Thomas Kennedy had died at the Abbe[y] of Gethsemany [sic], Nelson County, Kentucky, on the 25th day of September 1901. This raised questions of whether he was a monk, a priest, or a visitor at the Abbey of Gethsemani is a Trappist Monastery located in Trappist, Nelson County, Kentucky.

While this document contained the explicit information (given by his nephew) that Thomas Kennedy had no wife or children, there might be other avenues to trace his life and connections.

There will be more in this blog to share what more was learned about Thomas Kennedy, and how it was learned.

FamilySearch Labs: Full-Text Search

If you don’t already have a free account for FamilySearch, you need one!

You may have used the indexes that are a part of court and land records will only list the principal people in the records. That means that you would find your ancestors’ probate records or the land to which they were a grantor or grantee.

But what about the other names that are mentioned in these documents? You have probably seen a will that includes a list of individuals inheriting something from the deceased. These lists may be very helpful, as they may reveal the addresses of relatives, or show female ancestors under their married names.

To find those other names in unindexed records, try the Full-Text Search experiment at FamilySearch labs.

FamilySearch labs is where users can try and test new tools that are under development.

Go to https://www.familysearch.org/labs, and Sign In. There are several ways you can sign in, and if you do not already have an account, select CREATE A FREE ACCOUNT.

Once you are signed in, you will see the available experiments that users can try and offer feedback.

Scroll down until you see “Expand your search with Full Text.”

Select “Go To Experiment.”

The Full-Text Search page gives reasonable cautions given that this is not a fully released project. Among them are that the experiment may not always be available and that there may be errors.

My recommendation is to begin by using the search box.

The search seems to yield better results when the name between is entered as a keyword and put within quotation marks. You can leave the name field blank.

Since this search is done by matching patterns in the text, try different searches using women’s maiden names and married names.

Keywords: “Amelia Matier”

Keywords: “Amelia Small”

Be prepared to search using variations on place names, or different places where your ancestor may have lived.  

Keep in mind that records that were not created in Brooklyn may appear in the results. This means that Brooklyn appears in them.

For comparison, when I searching by putting her name in the Name field, there were 99,842 results. In the search results, you get the name of the record set and a preview of the parts of the record that match the search terms. Currently, the maximum number of lines appears to be four. This helps to see the context of how the search terms appear.

Clicking on MORE will give all the parts of the record that match. Clicking on the name of the record set (Steuben, New York, Marriage Records 1821-1923) opens a new tab where the record is accompanied by a transcript. The words from the search terms are highlighted in the document and the transcription.

Select “Summarize the document” for an AI-generated summary of the transcription. This may be helpful to assess the usefulness of the record, but I did not use it.

Use the Download arrow for options of what you would like to download. Choose if you want a PDF version with or without the highlights. You can also use the check boxes to include the Transcription and the Citation in the PDF document. The transcription and/or citation can also be downloaded without the image. (I downloaded multiple versions of the record including PDFs with and without highlights as well as JPG only.)

When you download the image, a pop-up box may appear offering the option to attach the record image to the Family Tree.

In another blog post I will show you one of the finds that I made, and the search that it commenced.

Give it a try and let me know what you find!