RLP 325: Using AI with Locality Research

Nicole (2s):
This is Research Like a Pro episode 325 Using AI with Locality Research. Welcome to Research Like a Pro a Genealogy Podcast about taking your research to the next level, hosted by Nicole Dyer and Diana Elder accredited genealogy professional. Diana and Nicole are the mother-daughter team at FamilyLocket.com and the authors of Research Like a Pro A Genealogist Guide. With Robin Wirthlin they also co-authored the companion volume, Research Like a Pro with DNA. Join Diana and Nicole as they discuss how to stay organized, make progress in their research and solve difficult cases.

Nicole (45s):
Let’s go. Today’s episode is sponsored by Newspapers.com. Hi, welcome to Research Like a Pro.

Diana (49s):
Hi Nicole. How, are you doing today?

Nicole (51s):
I’m great, mom. How are you?

Diana (53s):
I am doing well.

Nicole (55s):
Well, what have you been doing?

Diana (57s):
I have been working on all sorts of things, you know, how my life goes, this and that, but one of the things that I thought was really interesting was an email that showed up in my inbox this morning from Ethan Mollick, you know, it was his newsletter. He didn’t personally email me, but it did come through email and it was his latest article, which is titled The Post-Apocalyptic Education. And I know you read it as well. So let’s talk about that for a minute. What did you think of it?

Nicole (1m 28s):
Oh, it was so good. As people who’ve been using artificial intelligence tools in the last few months, it’s helpful to think about how it will affect learning and students, especially since we’re both teachers.

Diana (1m 41s):
I agree, and it’s such a temptation for students to just use AI to complete their homework, but they’re showing that unless teachers are really careful with the kind of homework they’re actually giving their students, then they exam scores are going down. Students that use AI for all their assignments and homework, their test scores are going down, which is not a surprise because you know, the assignments are supposed to help you learn. And so if it’s not the right kind of assignments to help you learn, then you’re not going to perform well on the exams, which makes sense. But I think the tricky thing for teachers is trying to understand what would be the best kind of homework and learning opportunities for students.

Nicole (2m 21s):
Yeah, that is challenging. And I, remember when I was teaching middle school social studies and history, just really trying to do a lot of project-based learning, and that’s what we’ve always thought in our Research Like a Pro study groups too, that like doing your own research project helps you learn so much more than trying to read something or do a worksheet and then spit back information. Applying what you’re learning to a real world, world situation is so much better for learning. And it was interesting in the newsletter from Ethan Mollick that the homework that AI can help with just becomes kind of a crutch. And the AI is a crutch and doesn’t help the students learn as well as them completing the homework themselves and figuring out something hard and putting forth mental effort.

Diana (3m 11s):
Right. And he has a nice chart in there where he talks about the different types of prompts and categories that AI could take in teaching. And he’s always so thoughtful about this. I appreciate it because he’s a professor at Wharton, so he has tried all these things with his own students. He’s not just saying, well, this is what you should do. You know, what I mean he’s, he’s speaking from experience here and he is been using AI in his classroom for a while, so he’s had a lot of experience practicing with this and seeing what’s happened,

Nicole (3m 43s):
Right. In any case, I think it’s funny that the title of the email was Post-Apocalyptic Education and talking about what comes after the homework apocalypse. And he really put the onus on educators to recognize that even though at the beginning we all kind of felt like we could recognize AI generated writing, it’s not gonna be that way very much longer. And it’s already too hard for tools and humans to detect all writing that’s generated by AI. So instead of just assuming students won’t use it if you tell them not to, and then trying to detect it, there’s gotta be a new way of working with it and helping students to recognize what it can do to help them with their learning and what it can’t do to help them with their learning.

Nicole (4m 38s):
And that’s gonna be a challenge and a change in the way education has worked.

Diana (4m 45s):
I agree. Well, our listeners may be wondering how to get the same information. And so if you go to Ethan Mollick’s blog or his website, it’s titled One Useful Thing, and you can just Google his name, his last name is spelled M-O-L-L-I-C-K. And then you can subscribe and he comes out with a new blog post every, I don’t know, maybe week, couple of weeks. And I really like his writing. We’ve talked before about his book Co Intelligence. His writing is accessible and very thoughtful when it comes to ai.

Nicole (5m 20s):
So true.

Diana (5m 21s):
Alright, well let’s do some announcements for today. We have our Research Like a Pro webinar series coming up on October 15th, and this is a Tuesday at 11 AM Mountain Time and the title is Crossing the Pond: Tracing Dorothea’s Roots in 19th Century Pomerania. The presenter is Emma Lowe, who is one of our fabulous researchers at Family Locket and her topics are Germany, immigration, Evangelical-Lutheran church records, German civil registration, locality survey, resolving conflicting evidence, German research resources.

Diana (6m 11s):
So Emma writes for her description that a passenger list recorded by a particularly conscientious clerk and a new index entry for a German civil registration record provided clues that opened the doors to tracing Henry and Dorothy Trotz’s origins in Greifswald, Pomerania, Prussia, Germany. This case study follows the Research Like a Pro process to systematically identify and search relevant record collections, following the clues that enabled the discovery of new generations in the homeland of Germany. This case study follows the Research Like a Pro process to systematically identify and search relevant record collections following the clues that enable the discovery of new generations in the homeland of Germany. So I’m very excited to follow that and watch that presentation. Our next Research Like a Pro with DNA study group begins in February, 2025 and we invite all of you who are thinking about joining to really look at your schedule and see if you could be part of that group. Registration will open in December, and our peer group leader application is on our website.

Diana (6m 50s):
We are looking forward to conferences that are coming up. We’ve got the East Coast Genetic Genealogy Conference, October 4th through 6th, and Nicole And I will both be presenting virtually through our recorded lectures. And then I will be presenting three recorded lectures at the Texas State Genealogical Society Family History Conference. So kind of fun to have some conferences to look forward to. Well, today we are talking more about AI in research and this is locality research. And we’re going to talk a little bit more about my project about Isabella Weatherford. So the first two episodes we had about Isabella, we talked about using AI with objectives and timeline and analysis.

Diana (7m 38s):
So now we are going to go into locality guides and just as a reminder, we’ve talked about locality guides before on the podcast, but some reasons why we really need to slow down our research and create them is because they give us historical context for our ancestors lives. They help us understand available records and where to find them. They show us migration patterns and local events that may have impacted our ancestors. So one of the stumbling blocks about creating a locality guide is perhaps not wanting to take the time because it can seem tedious to do Google searches, click on links, put them into your guide, and sometimes you get a whole bunch of text, a really long article that looks good, but you don’t wanna have to dig through it and pull out the relevant pieces.

Diana (8m 35s):
So can a large language model like ChatGPT, Claude, Gemini or Perplexity help make this task more efficient? So to see what I could find out about locality guides, I created this prompt: you are an expert genealogist. I need to create a locality guide for a research project and need accurate web links and data, which large language model is the best to use, provide the pluses and minuses for each. I just thought it would be fun to see what they each had to say about themselves and each other.

Nicole (9m 9s):
Yeah, so Gemini responded with some overarching things that were needed and one of them was accurate information retrieval, finding reliable data about specific locations, and then data synthesis combining information from various sources into a coherent guide, which is one of the things we love about large language models. So it’s that they’re always very coherent. And then web search capabilities efficiently locating relevant online sources, which isn’t something all of the tools have. And then critical evaluation, assessing the credibility of found information, which probably should be up to the human in the loop, not the large language model, but, but those are some things to think about.

Nicole (9m 52s):
So Gemini stated that of all of the large language models, it was the most promising option due to its overall capabilities and potential for accurate information retrieval. It gave Claude and Perplexity as other possible models to try, but gave some cautions for each and that it didn’t even mention ChatGPT. So then Gemini gave this excellent tip, ultimately the best choice depends on your specific requirements, the complexity of the project and the availability of the models.

Diana (10m 23s):
Hmm, well then I pasted the same prompt into Perplexity and Perplexity also provided insights on the strengths and limitations of the different models and indicated that because it can use different underlying models and has real-time web search capabilities for current information, it would likely be the best choice. And it gave this wise observation that no single AI model should be relied upon exclusively for this task. It recommended starting with itself and then cross-checking the information with your expertise and trusted genealogical resources. And it also recommended combining its search capabilities with the analytical strengths of Claude’s sonnet or the general knowledge of GPT-4.

Diana (11m 10s):
So I thought that was pretty intuitive and pretty good recommendations. Then when I pasted the same prompt into chat GPT-4 o, it chose itself and offered several reasons. And interestingly it listed Gemini as a good secondary choice because of its powerful search capabilities. And then finally, Claude 3.5 sonnet explained that it couldn’t browse the internet or access external databases. Instead it recommended a combination of AI tools, traditional research methods and expert human knowledge.

Nicole (11m 44s):
That was probably the best answer.

Diana (11m 45s):
It was kind of a fun exercise just to see what they’d say. And of course there was a little bit of bias there with most of them choosing themselves,

Nicole (11m 53s):
Right? And, I don’t think they’re always that self-aware either. Like sometimes they don’t even know what they can do and what they can’t do. And sometimes like Gemini will say, oh, I can’t do that. And I’m like, yes you can, you just did it yesterday. You can do it again. I know you can do it.

Diana (12m 10s):
That’s so funny.

Nicole (12m 11s):
Well, let’s look at how you used AI in creating a locality guide for Dallas County, Texas for the 1870s. And the research objective for the project that you’re working on is to examine the economic and social conditions in Dallas County, Texas in the early 1870s and their influence on Isabella Weatherford’s life and marriage prospects. Isabella was born in 1858 in Missouri, and her first marriage was to John Carpenter in 1874 in Dallas County. Later she married Robert Cisnie Royston, our ancestor in 1877 in Van Zant County, Texas. She died in 1942 in New Mexico.

Nicole (12m 53s):
Well the timeline analysis, after doing that, you had found no records for Isabella between 1860 that census in Dallas County and her 1874 marriage also in Dallas County. And so knowing that this was the Civil War and the reconstruction era, you were thinking that maybe knowing more about the location would help identify additional records and context for her life. Well, the locality guide template that we use in Research Like a Pro is divided into two sections, the background for that locality, and then the record collections and the sections for the background give you a place to add quick facts, history, laws, repositories and so forth.

Nicole (13m 35s):
And the record collection section has suggestions for various types of genealogical documents such as censuses and land tax, newspapers and so forth.

Diana (13m 46s):
So for the historical and geographical information, I took categories directly from the locality guide template that we have and put it right into the chat bot And I gave it this prompt: you are an expert genealogist. I’m creating a locality guide for Dallas County, Texas for the timeframe of 1845 to 1880. Provide information for the following categories. Each category has suggestions for what to provide, search the public internet for resources and provide specific links. And then under that I pasted the different categories. And I did put categories, so the responses from each of the different AI models were similar, but I was so fascinated to see that each model did have some unique data.

Diana (14m 35s):
And so I just went through each one, gathered the unique links and found maps details about Dallas County’s history. And as I suspected and as I believe Perplexity suggested, I did need to use all four models to get the best overall information. so I was very selective. I was the human in the loop. I copied and pasted, and of course I verified the links, you know, if they did give me links and made sure that I was getting something valid and it was information I really did want to include in my guide.

Nicole (15m 12s):
Great job on that. Well, I like how you used Claude 3.5 sonnet to summarize Dallas County’s geography and history. The AI here provided a lot of information such as the total area of the county, which is 909 square miles, the elevation range, which is about 500 feet above sea level, some major bodies of water and adjacent counties. Also, one of the models gave a response that pointed to a nice collection of maps for Dallas County on freepages.rootsweb.com. This website didn’t come up in a Google search and it’s interesting to note that you maybe wouldn’t have found it unless AI had helped you.

Nicole (15m 57s):
And one of the maps was for Dallas County in 1866 and you had already located Isabella’s family on the 1860 census in Dallas County precinct six near the Siene post office. And it was neat to see that this map had the post offices hand drawn by the county surveyor. So with this specific information, you could now better see where the family lived and make more connections.

Diana (16m 26s):
Right? This was probably the best find of my locality guide because I really didn’t know where the family was living. You know, precinct six is not very descriptive in the county, it’s not like a township or anything, and post offices are usually, you can’t find those again. You know, those can be difficult to locate. So it was really neat to see that this person had drawn that in. And now I have a really specific place within Dallas County. It was right to the east of the main city of Dallas. So that was really fun. And it was from a microfilm publication at the National Archives. so I thought this was another interesting collection.

Diana (17m 8s):
It was called Post Office Department, reports of Site Locations 1837 to 1950. And I really didn’t know this collection existed, so I learned something new there as well. So wow,

Nicole (17m 21s):
That’s really cool. The National Archives has so many treasures.

Diana (17m 24s):
Yeah, and we just don’t know about most of them. We know the basic ones that we use all the time. So this had been copied into, as we said, the freepages.rootsweb.com. So you know, one of the models found that, and that was great. Now let’s have a word from our Sponsor. Today’s episode is sponsored by Newspapers.com. Break down at genealogy brick walls with a subscription to the largest online newspaper archive. Did you know Newspapers.com has over 1 billion pages of digitized newspapers dating back to 1690? Their growing collection includes papers from the US, UK, Canada, Australia, and beyond. Discover, birth and marriage announcements, obituaries and everyday stories about your ancestors in seconds.

Diana (18m 9s):
Newspapers.com can help you fill in the gaps between vital records and reveal details about your ancestors’ lives that you can’t find anywhere else. They’re easy to use search feature lets you filter your results by date, location, specific paper and more. When you find something interesting, Newspapers.com makes it a snap to share it with family and friends. You can even save it directly to your Ancestry tree. Come explore 1 billion pages and make infinite discoveries today on Newspapers.com. Use promo code Family Locket for a 20% discount on your subscription.

Nicole (18m 45s):
Thank you. Well, let’s talk about your timeline of major events for the Locality Guide. This is a really good thing to include in a locality guide. It helps you understand kinda what happened, kinda an overview for that area. Because this guide was focused on specific years. You asked ChatGPT to help create a timeline of significant events in Dallas County from that time, so about 1845 to 1880. And the first time you asked the response was a little bit lacking in detailed information. So like we often have to do with ChatGPT and Claude, we have to ask for more details. And you were really happy to see that they had some sources to verify the information and it wasn’t just hallucinations.

Nicole (19m 33s):
So this was a great timeline that included the formation of the county and the early development. And kind of like some summaries for this, each of these little subcategories and years. So for 1861 to 1865 Civil War period, Dallas County, how it was affected, a brief little blurb; 1872, railroad expansion; 1873, city Incorporation; 1874 to 1880, economic and population growth. So it did a great job with that and it gave you links to Wikipedia and this Texas State Historical Association.

Diana (20m 8s):
Right? It basically is two sources for that. But I like the way it was formatted and that it gave me a little, you know, a little blurb about each one. I didn’t know need to know tons of details because I could go explore that at the website. I just wanted to have something basic in my guide. And something that I learned that I didn’t know before was this whole idea of the railroad expansion. And so Isabella married in 1874 and seeing that the railroad had expanded into the county in 1872 just made me wonder, is that where her husband came from? Because as John Carpenter, I haven’t been able to find him anywhere, you know, I don’t think he’s in the area in Texas in 1870.

Diana (20m 51s):
And so when I saw that immediately I thought, oh, maybe he is a Civil War veteran. He’s coming in from a whole different place because of the railroad coming up to Texas. Yeah. So it just gave me another thought, another idea for my research,

Nicole (21m 4s):
Right? And that’s one of the great things about these tools is that sometimes they give us ideas for further research that we wouldn’t have thought of ourselves.

Diana (21m 14s):
Exactly. So another section that I really hoped AI could help with was laws and government. So we hear all the time and we know that we need to find the laws for the specific time and place of our research, but that can be a challenge. And I was curious to see how well the various AI models would perform this task. Well ChatGPT and Gemini gave me very general ideas in some links, but I was really pleased with Claude’s response and the reference to Laws of Texas 1822 to 1897 by Gemel. And that was a resource I had seen before, but you know, sometimes you forget about different things, and so I appreciated that it reminded me of that, gave me the link to it on the portal to Texas history.

Diana (22m 4s):
And the funny thing was that sometimes the links didn’t work. And so in particular, Perplexity gave me some good information, but almost all the links didn’t work. Because I did have the actual title though I could quickly find the correct links on the internet. So you know, it’s so funny, that’s why you always wanna click on the see if it’s right. It gave me good information, I just had to go find the right link, which I thought was very interesting.

Nicole (22m 30s):
And we can often do that with the responses from a language model. We can go search for the sources, kind of like how Gemini has that G button to let you search for sources for the sentences that it generated. And we can do the same thing. We get the ideas from the language model and then we go look for a source that could say the same thing. But now we know the words to look for in a Google search.

Diana (22m 56s):
Exactly.

Nicole (22m 56s):
Well, in the second half of a locality guide, that’s where we have the record collections. And this is where you can include links to specific collections for various types of records. And so for this, you prompted the models for links and descriptions for specific categories that you copied from the locality guide template into the prompt window. So the categories were general collections, bible records, cemetery, census records, church court, ethnic land, legislative, military, and so forth. And the prompt that you gave with it is I am creating a locality guide for Dallas, County, Texas for the timeframe of 1845 to 1880.

Nicole (23m 40s):
Provide information for the following categories. Each category has suggestions for what to provide, search the public internet for resources and provide specific links.

Diana (23m 49s):
Well, here’s how the various models stacked up based on this prompt. So Claude provided a bulleted list with each category and at least two record collections. And again, not all the links were accurate, but with the webpage titles, I quickly found them. And a few of the databases were unusual and ones that I would not have found easily or even thought of. And then ChatGPT gave me a nice list on the surface, but the sources were really vague. Many of the links didn’t work again or just went to the FamilySearch wiki, but it did provide a good reminder of places to look. Gemini provided very general sources and all the links were accurate.

Diana (24m 31s):
Perplexity focused on providing sources and almost all the links were accurate. However, they all went to the FamilySearch wiki for Dallas County. So I was not super impressed with how it went with finding the record collections, but it did give me some information. So I was very selective as I copied and pasted into my guide, making sure again that I had the right links and added descriptions. And I also used the FamilySearch catalog, which is my go-to for finding very specific collections. The AI couldn’t find these, those are sort of buried down in FamilySearch. So there I needed to go find them myself.

Diana (25m 11s):
One of the things that I could have done, I don’t, I didn’t really do this, but FamilySearch does have a little description in the catalog for each collection. And so I could have put that into the AI model and had it maybe summarize it if it was kind of long. But usually it’s pretty short summary anyway that I can copy and paste in. So as I always do when I build my guide, I site, I sought out the most relevant records for the research objective, which was pretty focused this time on that time in Dallas County in the mid 1800s so I tried to give it the prompt to find me those sources that would be for that era.

Nicole (25m 51s):
Nice. I was just thinking about how, how could AI help with the catalog because sometimes we want to take a lot of the links from the catalog and put them into our locality guide, And I just wondered, like, I wonder if I could just expand all the categories for one of the counties, copy and paste that into ChatGPT or Claude and just say, make this a little bit more easy to include in a locality guide or some like some figure out, some prompt that would help with that.

Diana (26m 18s):
I know because right now we have to go and click into each one and it is kind of time consuming. So it would be wonderful if we could somehow use AI to help us with that.

Nicole (26m 30s):
Yeah, it’ll be something to try. But you know, even if you click add to print list, if you added them all to your print list, then maybe you could do something with that. Even like who knows?

Diana (26m 42s):
Oh, I like that idea. Because that’s pretty easy to do that and then you could copy that in or have AI organize that for you. Yeah, but we’ll have to try that. That’s a good idea.

Nicole (26m 54s):
Yeah, the FamilySearch catalog is wonderful, but in some ways it’s clunky, you know?

Diana (26m 59s):
Yeah.

Nicole (26m 59s):
Especially with that where I kind of just wanna see like the full citation to that catalog entry rather than just only the author and the title of it. But usually I can tell what I want from looking at the author, you know, like when you click into land and property or whatever it is and you’re trying to find the deeds for that county, and sometimes it’ll be like five books of abstracts, but if you find the one that was where the author is, the county, then you know you’ve got the right one, you know?

Diana (27m 31s):
Right. And it just takes experience to start seeing that when you’re working with it. So at the beginning you just click on everything to see what it is, but the more you work with the catalog, the easier it gets to find the information you want.

Nicole (27m 44s):
Right. And that’s where we come in. You know, it’s hard for the AI tool to know these things and sometimes we just have to go in and do that part ourselves, which is fine. The AI tool can help us do a lot of the busy work and then there’s parts that we have to do as well.

Diana (27m 58s):
Right.

Nicole (27m 59s):
Well, and this process of making a locality guide, you experimented with several AI tools, ChatGPT, Claude, Gemini, and Perplexity. And each tool had its strengths and it sounds like you found it beneficial to really cross check between them all and gather information from each one that was relevant. So that’s good.

Diana (28m 25s):
Yeah, I think it’s really good to try all of them. Why not? You know, I just had my prompt in my Google Doc and could just copy and paste it easily into each one. I also thought about the idea of not putting all my record collections, you know, into one prompt to maybe just be a little bit more selective and do two or three at a time to see if that worked and maybe ask it specifically for five things for each bullet. You know, I think there’s a lot of things with the prompting and working with the models that with more experimentation, I probably could get it to work better for me.

Nicole (29m 2s):
Yeah, I think you’re right. And, I think there’s kind of a standard length of response that usually comes and if you’re asking it to do something that will give a much longer response, I kind of feel like it truncates the response to not do everything you asked because it’s kind of trying to fit its response into a certain length And. so I have found it’s better to break it into chunks too, because then you get a good answer for that chunk and then you can move on the next chunk.

Diana (29m 29s):
I agree.

Nicole (29m 29s):
Well, you did play around with the Custom GPTs at ChatGPT for locality research and Mark Thompson created a custom GPT for that. It’s called Locality Guide for Genealogical Research by Mark Thompson. And this can be really helpful for not having to create a prompt, but just saying like, I’m working on the locality guide for this county and then it can use the saved instructions that Mark put in there to help you generate what you need. And then you created one too. What’s the name of yours?

Diana (30m 2s):
Mine is Diana’s Genealogy Locality Guide Builder. Which I think that it helped me write that title and said, is this okay? And I said Yes, this is fine. So I will just make a note that Mark spent a lot more time putting his together. Mine is pretty simple. I basically took our locality guide and uploaded that and gave some basic instructions. So, you know, I would love to hear from our listeners if you try both of them. You know, I’m sure you’ll see different things within them. Just be fun to compare and see a little bit which one works better for different things.

Nicole (30m 37s):
Right. So if you don’t know how to use a custom GPT, you can find them in the GPT store at ChatGPT. And just searching for locality guide will probably bring them both up.

Diana (30m 49s):
Right. And you can also search for genealogy and that usually brings up a lot of different things that you can use for your research. It’s fun to explore those. Well, let’s do some key takeaways for Using AI in Locality Research. So here’s some things to remember. It can be very valuable, but we wanna make sure that we are verifying information because AI can introduce biases or inaccuracies. We want to experiment with different tools to find out what works best for your research style. And one thing that I, we didn’t really talk about that much was, it’s so helpful to summarize dense historical texts.

Diana (31m 30s):
So one of the county histories had really in-depth information about Dallas County during this time, but it was about three pages long and it was written in 1870 something and it, it was so hard to wade through. So I put that entire thing into Claude and had it summarize it for me, which was so much better to put in my guide than the entire thing or having me wade through it and summarize it. So that’s a tip. Another tip is to break down your locality guide into specific sections as we just discussed. And then make sure you’re always citing both the original source and the AI summary in your research log.

Diana (32m 10s):
So if you did use say Claude to summarize a history like that at county history, note that and the date because we wanna make sure we can get back to the original. But if AI’s doing the summary, that’s good to note. So you know, it, it’s been so fun to experiment And I think that as we combine AI with our own expertise, we can create more comprehensive and efficient locality guides. Perhaps it will take away that stumbling block of not wanting to spend so much time. And of course our locality guides are so important because it really helps us to do the next step, which is going to be research planning.

Diana (32m 51s):
Well, I was pleasantly surprised at how working with AI as my tutor and coworker made creating my Dallas County guide much quicker. And it was more fun. You know, honestly it was just fun to see what it would come up with. It wasn’t just me plugging along, you know, it was me and my tutor or my, my coworkers. so I would encourage everybody to go give it a try.

Nicole (33m 15s):
Right? And we always talk about how it is fun to use AI tools, And, I think. Part of the reason is that it’s like a new exciting thing that we get to try and see what it can do. And then we’re always, I think, pleasantly surprised with seeing that with a little prompting and a little work and trying different things, we can get it to do things that will save us time. So it’s fun in many ways

Diana (33m 41s):
And it finds things that maybe we wouldn’t have found like that map. Of course, as with anything, it will just take practice as we learn best how to use it.

Nicole (33m 51s):
Alright, well thanks everyone for listening and we hope you have a great week and we’ll talk to you next week.

Diana (33m 57s):
Alright, bye-Bye everyone.

Nicole (33m 58s):
Bye. Thank you for listening. We hope that something you heard today will help you make progress in your research. If you want to learn more, purchase our books, Research Like a Pro and Research Like a Pro with DNA on Amazon.com and other booksellers. You can also register for our online courses or study groups of the same names. Learn more at FamilyLocket.com/services. To share your progress and ask questions, join our private Facebook group by sending us your book receipt or joining our courses to get updates in your email inbox each Monday, subscribe to our newsletter at FamilyLocket.com/newsletter. Please subscribe, rate and review our podcast. We read each review and are so thankful for them. We hope you’ll start now to Research Like a Pro.