RLP 320: Using AI to Find Research Questions and Write Objectives

Nicole (1s):
This is Research Like a Pro episode 320, Using AI to Find Research Questions and Write Objectives. 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. Let’s go.

Nicole (41s):
Today’s episode is sponsored by Newspapers.com. Hello everyone. Welcome to Research Like a Pro

Diana (48s):
Hi. Nicole. How are you today?

Nicole (51s):
Good. I’ve been doing a lot of teaching lately. How about you?

Diana (56s):
Well, I have been working on a few different things. Yesterday I worked on transferring or connecting my family tree on FamilyTreeDNA to MyHeritage. I’d been getting those emails for the last couple of weeks and save those saying, oh, I’ve gotta do this sometime. So before our office hours for our E-course yesterday, I decided that would be a good thing to share with everyone. So I went through the steps. And, it wasn’t that hard. You just have to do a few steps and you have to do a little bit of thinking about where you want your tree to be, which tree you want to use, because if you’ve got trees on my heritage, you could connect to one of those or you can just use your existing family tree on FamilyTreeDNA and have that be added to MyHeritage.

Diana (1m 46s):
So there were a few things to think through, but it was fun to get that done. So now I need to do it for the other kits that I manage on FamilyTreeDNA and get all of those connected or transferred.

Nicole (1m 58s):
Oh good. Yeah, I learned a lot when you shared about that because I had been seeing those emails as well and thinking, oh no, what do I need to do? So, exactly. I’m glad to know that when we transfer or copy over our FamilyTreeDNA in MyHeritage, that it preserves any DNA matches. We’ve linked to our family tree there, so that’ll be nice.

Diana (2m 18s):
Right, and that’s one of the things that I learned that that linking will be preserved if you have already linked them over on FamilyTreeDNA. So if you do want to do that, you just wanna make sure you’ve got things set up. And I referenced Roberta Estes’s blog about this on her blog, DNA Explained, she has a great blog post all about it, screenshots really walking you through it. So Roberta’s such a great resource on FamilyTreeDNA, so I recommend checking out her blog posts. If any of you listening still need to do this because she’ll, she’ll really walk you through it and you can see exactly what to do.

Nicole (2m 55s):
Yeah, and she has that new book too about FamilyTreeDNA.

Diana (2m 59s):
Yes. And I’ve been reading it. It’s So good. If any of our listeners have taken a FamilyTreeDNA test specifically, the autosomal information is great, but if you’ve been wondering what in the world to do with your Y-DNA and mitochondrial DNA, she really takes you through everything on the website about how to use it, what it means, what to do next. It’s a really good manual for using your results on FamilyTreeDNA.

Nicole (3m 28s):
I’m excited to read that book too. Well, our announcements are that our webinar for this month, September 21st, is by Karen Ramon. She is a graduate and peer group leader in the Research Like a Pro study group. And her topic is Proving the Parents of John G. Winn: A 19th Century New England Study. So this will be fun. It’s a little bit of a different locality than some of the other ones we’ve had in the past in New England in Massachusetts. And she’ll be talking about how an undocumented history gave clues to John Winn’s parents. And using the Research Like a Pro method, those clues turned into evidence.

Nicole (4m 9s):
And she developed a strong locality guide and took a journey through courthouses and cemeteries and combine that with online sources and a town clerk’s office. And that led to various records that helped conclusively document John’s connection to his parents. So we look forward to that. And the Research Like a Pro study group begins in just a couple days on August 28th. So we’re excited to begin that. And then looking ahead for future study groups, we’ll be doing Research Like a Pro with DNA in February, 2025. If you want to join us, we’ll start registration in December and you can start thinking about if you would like to apply to be a peer group leader for complementary registration.

Nicole (4m 51s):
As always, join our newsletter comes out every Monday, you’ll receive updates of new blog posts and podcast episodes and new classes and various offerings. We’ll see you at a few upcoming conferences. The Association of Professional Genealogist Professional Management Conference is September 19th through 21st. It’s a virtual conference. I’ll be teaching about creating a brand kit with Canva, and I’ll be talking about what you can do with Canva, including their AI tools. On October four through six, we’ll see you at the East Coast Genetic Genealogy Conference, which is in Maryland and online. Our classes will be online, so I’ll be talking about research logs, lineage diagrams, and Airtable and Diana will be talking about DNA reports.

Nicole (5m 39s):
Then the Texas State Genealogical Society Family History Conference is November 1st and second, and Diana will be teaching three classes. This is a region that she’s accredited in, in Texas, so it’s fun to be able to use that expertise and teach about that area. So she’ll be talking about tracking and migrating ancestor through land and tax records and research planning and settlers of Indian territory, discovering their story in this unique place and time.

Diana (6m 8s):
Well, thanks for going through those. I am excited to be part of the Texas conference because as probably most of our listeners know, who’ve been with us for a while, all of my paternal ancestors on my dad’s side, Nicole’s grandpa’s side, they all came to Texas in the 1880s from all the different southern states and then moved up into Indian territory and which became Oklahoma. So when I was first researching, I really didn’t know much about Indian territory. It took a while to figure out the records, figure out what I could do with that area. So it’s fun to be able to teach about it. So I’m excited about that.

Diana (6m 48s):
Well, today we are going to talk about using artificial intelligence to find research questions and write objectives. So Nicole and I have been having so much fun learning how to apply the new tools with the large language models to our research, and specifically the Research Like a Pro process. So one of the things that can be a little bit challenging is how to narrow down our research focus and to formulate that objective that will guide your research. And as I was thinking about how AI could help with this, I decided the best way to really explore was to do an actual research project and for each step to try using the large language models to see if they could help me.

Diana (7m 37s):
So I wanted to do something about my Isabella Weatherford. So my entire project follows her life. And so we’re going to talk today about how I tried to figure out a good research question and an objective. She is an ancestor I have researched quite a bit. I used her for my accreditation project, she was part of generation number two. And you know, sometimes these ancestors we have researched a lot we just wonder if, what else can we find about them? So we’re going to be talking all about Isabella, and I’m not going to tell you what we found because I found something really exciting about her that just goes to show when you focus in on some specific times and information, you can find things.

Nicole (8m 23s):
I can’t wait for you to share what you found. Well, when starting a new project, it’s really important to analyze your pedigree and identify gaps or areas that need further investigation. And that’s one thing that AI tools can help us with. They can analyze our family tree data and suggest potential research questions. So one thing we can do is use a GEDCom and a custom GPT to analyze our pedigree. To create a GEDCom file from your genealogy software, just go to file, export, and then select the number of generations you want to include. Choose your starting person and then export only the basic facts, notes and other relevant information.

Nicole (9m 4s):
And so for this project, Diana created a 10 generation ancestor GEDCom, starting with her dad, Bobby Jean Schultz. And a custom GPT is a specialized AI model that’s trained on a specific topic or task. And so for genealogy, you can use the family tree expert custom GPT, which is free for all users. To create your own custom GPT, you’ll need a paid account, but free accounts can use GPTs that others have made. These are available in the Open AI ChatGPT platform. And on the left side of the home screen you just have to click on Explore GPTs. And once you’re there looking in the GPT store, you can search for genealogy or family tree.

Nicole (9m 46s):
So here are some tips for using custom GPT. You can ask the custom GPT what it can do and inquire about the best way to use it to explore its capabilities.

Diana (9m 57s):
Right. And, it was really fun to try this out. I had a few different things I wanted to explore when using my GEDCom. You know, we’re always trying to think what’s a good prompt? What is a good way to use AI? So here’s some ideas. One is to analyze this GEDCom file and identify gaps or inconsistencies in the family tree. Another suggestion that I tried based on this GEDCom, suggest four generation research project ideas, focusing on ancestors with events in your specific region, or review this family tree data and propose research questions for ancestors with incomplete information. So it’s fun to explore a little bit and see what it can find in your family tree that you’ve created.

Diana (10m 42s):
I think often we might have some inconsistencies or gaps or we may have ancestors, we thought we’d research, but there’s something incomplete and the AI can look for that. So because I’ve done accreditation, I thought it would be fun to see if it would do a good job in trying to find some specific generations that would work. And with ICAPGen, the accrediting body that I went through, you have specific states that you have to have had at least a life and event in. So I created a prompt and used the upper South state. So my prompt was using this GEDCom suggest four generation research project ideas were at least one life event occurred in Kentucky, North Carolina, Tennessee, Virginia, and West Virginia.

Diana (11m 31s):
Remember, I’m using the custom GPT family tree expert, which works really well with GEDComs And. it looked through my GEDCom and, it gave me a possibility, well first of all it said, I have identified four linked generations with life events in North Carolina and Virginia, starting from an individual born about 1820. And then it gave me the people it gave me Susanna Clanton, who was born in North Carolina. Her father John who was born in North Carolina, her grandfather Edward who died in North Carolina, born in Virginia, and a great-grandfather who was born in Virginia and died in North Carolina. So that actually worked. It was a little far back. It was between 1817 and 1708.

Diana (12m 13s):
So I don’t know if I would really use that being a little bit more difficult, but it would be fun. And I did enjoy seeing what it could give me. So here’s some benefits of using a GEDCom with custom GPTs. Well, as I said, it can give you a really good overview of what you have in the tree. And, it can quickly process large amounts. This is one of its great skills that really quickly it can go through your tree. Could I have found this group of four people? Of course I could have and I could have, you know, put in locality searching and and done some work finding them. But it was nice to see that really quickly I could get an answer that worked.

Diana (12m 56s):
And then it can also look for patterns. It might spot relationships or migration patterns that you’ve overlooked. And, it can give you specific research ideas for your family’s history and geography. And, it can really save you some time to generate some research ideas to further explore in your next project.

Nicole (13m 18s):
I love that. And one thing I think that is really interesting about what you said is that the AI can quickly process a large amount of data. And of course you could do it yourself, but it would be very slow and a boring process clicking through individuals in your tree or doing some kind of like search within your software program to pull up all the people who have a life event in a certain location. Then checking to see if any of them are related to each other and like three generations. So having the AI tool do this kind of thing for you. It’s such a good use case because we can use AI tools for these tasks that are kind of slow for us. And they don’t take a lot of analysis or anything difficult.

Nicole (14m 0s):
It’s just kind of like analyzing a whole bunch of texts quickly and spinning out something that’s the perfect thing for a computer to do.

Diana (14m 7s):
Right? And the really nice thing is that you just talk to it like it’s a human, even though we know it’s not a human, you know, you just type in your thoughts about what it gives you. The first time I did it, I was trying to find four generations in one of the accreditation regions and I simply did not have any. So it made it some things up. So that’s one of the dangers that it will hallucinate if it’s trying to please you. So you have to be careful about that. But it was really interesting just to see what I could do and then I would refine and say, no, that doesn’t work for this reason. And then it would say, oh, I’m so sorry, how about this?

Diana (14m 48s):
So you know, it’s, it’s actually fun. It can make some of these tedious tasks really interesting and fun.

Nicole (14m 53s):
Great. Well here’s another way to do it and I love that we’re gonna talk about an alternative possibility to GEDComs because as we discussed with Steve Little last week, sometimes GEDCom files are challenging for large language models to process because of their structure being a little bit less straightforward. An alternative to that is using an ahnentafel report. So for the Isabella Weatherford project, Diana created an ahnentafel report from Family Tree Maker for the same 10 generations. So for that type of report, it’s numbered, so it’s like one and then two and three for the parents and so forth. Each ancestor is numbered. So it’s a little bit more straightforward, it’s a little more like a narrative report rather than like a, GEDCom file is more computer code.

Nicole (15m 39s):
This 10 generation ahnentafel file was a PDF that the AI tool had a little bit of an easier time reading it seems like. And so Claude by Anthropic, the 3.5 Sonnet model was utilized. And the prompt she used was, you are an expert genealogist. Analyze this ahnentafel report and suggest five research questions for Isabella Weatherford. AI provided several interesting suggestions, including what were the economic and social conditions in Dallas County, Texas in the early 1870s that influenced Isabella’s life and marriages. And another one, how did Isabella’s migration from Missouri to Texas impact her life and family relationships?

Nicole (16m 21s):
And then a third one, what factors led to Isabella’s two marriages in close succession 1874 and 1877? At this point, a tip would be that you can refine your query and if the initial suggestions aren’t quite what you’re looking for, you can ask for a little bit of something different. So a prompt refinement here was please suggest research questions focused specifically on Isabella’s early life in Missouri and her first marriage. Another warning that the AI tools, these large language models, they want to please us. And so if you ask for something impossible in your pedigree, it will hallucinate and make up answers.

Nicole (17m 1s):
So just know that that can happen. And like Diana already said it, you know when she asked for research questions that fit certain parameters and ancestors from a certain time and place it and there weren’t any, then it made some up. So just be aware of that possibility. Well for this example, Diana asked ChatGPT 4.o to find ancestors born in Missouri between 1850 and 1900. And it came back with some answers, but none of them fit the parameters exactly. So some of them had life events before 1850 in Missouri, and so only Isabella Weatherford met the criteria.

Nicole (17m 42s):
And so when Diana told the chatbot, this is incorrect, none of these people have life events between 1850 and 1900 except her, it said, yep, only Isabella meets the criteria. So when you correct it, it recognizes that, but it doesn’t always give you correct answers.

Diana (17m 60s):
Right? It was trying to get close because some of them had events, but they just were not specifically born in Missouri. Between 1850 and 1900 So, it got pretty close. It was trying to do what I asked it to do. I think it’s just so important that we understand the limitations but not let the limitations keep us from using it because it did prove to be very helpful.

Nicole (18m 24s):
Yeah, and we can even start with like a broad request, like list everyone who has a life event in Missouri. If there’s too many, then we can narrow it down just like any kind of search you might do in a database.

Diana (18m 37s):
Exactly. I think it all just speaks to exploring and thinking outside the box of what you can have the large language model do for you. Now let’s have a word from our Sponsor Newspapers.com. Today’s episode is sponsored by Newspapers.com, your go-to resource for unlocking the stories of your ancestors. Dive into the newspapers where your family’s history unfolds as you search nearly a billion pages and seconds. Newspapers.com offers an unparalleled treasure trove of historical newspapers providing a window into the past with papers from the 17th century to today. Newspapers.com is the largest online newspaper archive. It’s a goldmine for anyone seeking to uncover stories from the past.

Diana (19m 18s):
Whether you’re a seasoned genealogist or just starting your journey, Newspapers.com makes it easy to search for obituaries, birth announcements and the everyday stories that shaped your family. It’s like having a time machine at your fingertips. And here’s the best part, our listeners get an exclusive offer. Use promo code FamilyLocket for 20% discount on your subscription. That’s FamilyLocket at Newspapers.com. Sign up today at Newspapers.com and embark on a journey of discovery.

Nicole (19m 46s):
Well, I know we read that ad every week and I just have to give a shout out to Newspapers.com because I do use it frequently. And it’s really a perfect sponsor for this podcast because there are so many things within Newspapers.com that we can find and use in our research that can help us, especially when we have burned counties or just a difficult ancestor where we need to find every clue we can. And Newspapers.com is just one of my favorite newspaper sites. Well, let’s talk about using another tool besides a GEDCom or an ahnentafel file to help us with their research questions. And that is a timeline. So this is an a simple way to give the AI large language model tool information about a specific ancestor to help it to have some context and some information to search through to help us think of potential research questions.

Nicole (20m 38s):
So just copying and pasting a simple timeline can work really well. One thing you can do is use a timeline that’s already been generated by your family tree software or an Ancestry or FamilySearch, or you can generate the timeline yourself, which is part of the Research Like a Pro process. That’s one of the very first things we do, is gathering all the known facts about our ancestor, all the sources we already have. This is our starting point. And for Isabella Weatherford Diana had compiled information from various sources including census and marriage and her widow’s pension application. So Diana organized this into a simple timeline format with the date and the event.

Nicole (21m 17s):
So 1858: born in Missouri; 1860: residing in Dallas County, Texas; 1870: never been found on that census; 1874: married John Carpenter in Dallas County, Texas; 1877: Married Robert Royston in Decatur, Wise County, Texas; 1880: residing in Johnson County, Texas; 1884: moved to Chickasaw Nation Indian Territory; 1915: death of husband Robert C Royston in Stevens County, Oklahoma; 1929: applied for widow’s pension in Oklahoma;

Nicole (21m 57s):
and 1942: she died in Oklahoma City, Oklahoma. And like I mentioned, an even easier way to generate a timeline is to just copy and paste the person’s profile information from Ancestry or FamilySearch. And you can just copy and paste that into the chat bot. You can even just select everything on the whole page using control A and then control C to copy that. And then once you get to an AI tool like cloud or ChatGPT, you can simply paste that data into the chat bot and write your prompt and then hit enter. And if you’re pasting in something and then you wanna write a prompt in a different paragraph, just remember to use shift enter to create a new line.

Nicole (22m 39s):
Otherwise you’ll hit enter too soon.

Diana (22m 41s):
I’ve done that a few times, but then in the next prompt it’ll say, what do you want me to do with this? And then I’ll say, oh, okay, this is what you’re supposed to do with,

Nicole (22m 49s):
Right? It’ll think of something to do with it, but it won’t. It’ll just make it up itself like, oh, you gimme, gimme timeline. Well here’s some info about what you gave me.

Diana (22m 57s):
Exactly. Well, once you get your timeline into the chat bot, then you can use AI to help you analyze it and give you some ideas for research questions. So here’s a prompt that I used with Claude. You are an expert genealogist. I would like to do a research project on Isabella Weatherford write a detailed narrative about Isabella from this timeline. So that was really fun to see. So I had gone to Isabella Weatherford’s page on Ancestry her profile page, and just copied everything you know, using Control A and Control C and then pasted that in and so it had the information on her children and, it had sources and different things. And I was curious to see what it would do in writing a narrative from that.

Diana (23m 38s):
So first I had to write the narrative, which did a great job and use the details that I had given it. It didn’t make anything up because it actually had the information. And then after getting the narrative, I felt like now I wanna have five research questions, suggestions from Isabelle’s narrative And. it did give me some really interesting research questions. Here are the five that it gave me. What circumstances led to Isabella’s family’s move from in Missouri to Texas between 1858 and 1860? How did the Civil War impact Isabella’s family given she was a child in Texas during this period? What factors influence Isabella’s first marriage in 1874?

Diana (24m 21s):
How did Isabel’s life change with her move to Indian territory in 1884? And what was Isabel’s experience as a widow in early 20th century Oklahoma? And how did the Confederate widow’s pension affect her life? Well, I tried this exercise with both Claude and ChatGPT and received a lot of suggestions from both of them. They all were a little bit different. And finally, I settled on this research question. Isabella married twice before the age of 19, first to John H. Carpenter in 1874, and then to Robert C Royston in 1877. What were the social and economic factors that might have influenced these early marriages?

Diana (25m 6s):
So as Nicole mentioned in 1870, the family has not been found on the census. So there’s really a black hole between that 1860 census in Dallas County and her marriage in 1874 in Dallas County. And knowing this was civil war time reconstruction in Texas, I really wanted to learn a little bit more about what was going on. So I had the marriage records, I didn’t need to search for that, but I was trying to get more context. And I thought that the research questions were all really interesting because they did focus on context for various parts of her life.

Nicole (25m 46s):
Yeah, that is interesting. And I think I would’ve expected it to do more. Like when was she exactly born? ’cause that’s what we tend to wanna know as Genealogists sometimes we tend to want to get all the dates exactly right. And sometimes it’s harder for us to think of these questions. So this was really a great exercise.

Diana (26m 6s):
Right? And I actually would like to go back and do some writing and research on several of those questions. it

Nicole (26m 12s):
Could be so valuable for thinking of themes to write about for like a biography or just something that has a little bit more historical context than a proof argument. Like this person was definitely the child of so and so. So it can be fun for developing their life a little more.

Diana (26m 28s):
Yeah. How to write a history that people will really want to read.

Nicole (26m 33s):
Yeah. Well some of the benefits for using a timeline to generate a research question are that it can identify gaps. And so this is one thing we really love about our timelines when we’re analyzing them, is that, that we can clearly see the time periods where information is missing And. it allows us to put a lot of data into one area to see visually. And we can really highlight migrations and notice any significant life events that maybe we’re missing or that we need to investigate more. Also, we can learn more about historical context. So seeing their life events in chronological order alongside historical events can lead to questions about how larger forces shaped their lives. And then of course, it can spotlight in any conflicts or inconsistencies.

Nicole (27m 17s):
And contradictory information in a timeline becomes more apparent because becomes, we’re able to see it right there visually. So that can bring up some questions to help resolve those conflicts.

Diana (27m 27s):
Right. So once we have a research question, the next thing we do in our research process is to write a specific objective. And we want our objective to be clear and have the key identifiers. So AI can help us craft that. Often we have an idea in our head of how we want to say something, but we can’t get the words to quite fit. So using a large language model that’s really good with words is a great use for this. So for the Isabella Weatherford project, I use this prompt create a research objective for investigating the economic and social conditions in Dallas County, Texas in the early 1870s. And their influence on Isabella Weatherford’s life include key identifiers such as birth, marriage, and death dates and places.

Diana (28m 15s):
So the thing that I gave it that helped with this was a sample objective so it would know how I like to write my objectives. So I gave it one that I’d already done. The format I had used in the past and, it generated this objective for me. And keep in mind, I didn’t have to put in the dates and places because it already had my timeline information. It already knew all of that. So I didn’t have to rewrite that for it. So it wrote the subjective, the objective of this research phase is to examine the economic and social conditions in Dallas County, Texas in the early 1870s and their influence on Isabella de Weatherford’s life and marriage prospects.

Diana (28m 55s):
Isabella was born on four March, 1858 in Missouri. She first married John H. Carpenter on 16 January, 1874 in Dallas County, Texas. Then later married Robert Ney Royston on 16 January, 1877 in Van Zandt County, Texas, and died on nine May, 1942 in Tucumcari, Quay County, New Mexico. So wow. Now I have an informative objective to guide my project. And if I hadn’t liked that, I could have asked it to rewrite it in a little bit different format. Or if some of the dates were incorrect, you know, it would figure that out. One of the things that I noticed was an inconsistency.

Diana (29m 37s):
So it got this timeline I was using was straight from my Ancestry tree And. it did have a correct place of death Tucumcari, Quay County, New Mexico ’cause I had her death certificate and the timeline I had generated earlier, I had her dying in Oklahoma City. So that’s interesting. That must be in my family tree program. Or perhaps it took that from her widow’s pension. So interesting. I hadn’t noticed that inconsistency. So this is why we always check all of our facts.

Nicole (30m 9s):
Right. And I also noticed an inconsistency with her marriage to Robert Royston. Was it in Wise County, Texas or was it in Van Zandt County?

Diana (30m 16s):
Okay, that is a good question. I believe that she says in her pension that it was Wise County, and I believe that people had thought it was Van Zandt because their child mentions that he was born there. So yeah, I’ve got some inconsistencies that this is pointing out

Nicole (30m 35s):
Tri, How the data in our trees can change over time. Yes. And if you don’t keep them in sync, then it will be different. So that’s another thing that I’ve noticed in doing this exercise is that I can sometimes see where there’s conflicting data or data that I haven’t seen before. Like, you know, other people can edit the FamilySearch tree. And so when I took a timeline about one of my ancestors from there, And, it had two different locations for the 1870 census and talked about how this person moved back and forth in one year. And I was like, oh,

Diana (31m 3s):
That

Nicole (31m 3s):
Clearly is wrong. So the source data was bad. And so then you can really see it more clearly when you’re reading a narrative that’s generated by AI sometimes that helps you spot those inconsistencies,

Diana (31m 14s):
Right? Because our eye can just glide right over that and not pay attention. Yeah, that’s good.

Nicole (31m 21s):
Well, to wrap it up, I’ll give some tips for using AI with research objectives. So like Diana said, it’s really helpful to give it a sample objective when you’re asking it to write an objective for you that it can understand what they’re supposed to look like. And this is exactly how GPTs and large language models have been trained on a lot of example data. And they’re really good at mimicking that. And then you can also provide those key identifiers. So if they’re already in the timeline you provided, it can just draw from that. Or you can give it some data to, to put into sentences for you. If the objective you’ve written is not very clear or it’s kind of lengthy or needs to be broken up into smaller sentences, you can give your research objective draft to the AI tool and say, please reword this and make it more clear.

Nicole (32m 8s):
You can also use AI to help you find new ideas for old tired projects where you’ve been maybe working on them for a long time. You have several research reports, maybe uploading those reports to Claude or ChatGPT and asking for ideas for new research objectives could help you. And you can even ask for help creating a phased approach to tackling a challenging research question by asking AI to suggest multiple research objectives that could be done in order in research segments. So this could be a way to really help you brainstorm how you want to tackle your research project and have it write your objective for you.

Diana (32m 47s):
Well, it certainly is fun and it can make the research process just have a little extra zip to it when you are talking with someone about it, whether it’s a real person or it’s a chatbot. I really enjoy chatting with the chatbots about my project and getting ideas and new, new suggestions. So I don’t know if I would’ve thought of that specific objective on my own. ’cause I kind of have objectives in my head that I always use and this was not one of them.

Nicole (33m 18s):
Yeah. And we, we like to talk to each other about our research projects and get ideas and just in that same way it’s, it is interesting to bounce ideas off another language model.

Diana (33m 31s):
It is absolutely fun. It’s great. All right, well thanks everyone for listening and I’m excited to share my progress on the Isabella Weatherford Project. In the next few episodes, we’ll have some fun discussing what I did and what I learned as I was working with artificial intelligence. So thanks for listening everyone, and we’ll talk to you next time.

Nicole (33m 55s):
Bye everyone.

Diana (33m 58s):
Bye-Bye

Nicole (34m 35s):
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.