 Record every genealogy clue to strengthen your descendancy research and uncover new family connections. The Most Important Genealogy Habit You Can Develop: Record Every Clue: Descendancy Research Series – Part 4When people ask me what the most important genealogy habit is, they often expect me to say something like "cite your sources" or "search every census." While those are certainly important, there's one habit I believe comes even earlier in the research process: record every clue. After years of researching my own family, clients, descendants, unknown parentage cases, and brick walls, I've learned that some of the biggest breakthroughs don't begin with a major record; they begin with a tiny clue. A passing comment. A family story. A nickname. An address. An occupation. Something that seems insignificant today may become the missing piece of the puzzle years later. That's why I write down everything. Clues Are Not the Same as Evidence One of the first things I explain to beginning genealogists is that clues and evidence are not the same thing. A clue points you in a possible direction. Evidence helps prove or disprove a conclusion. Think of a clue as a lead that deserves further investigation, not as proof that you've found the right answer. Learning to separate clues from evidence helps prevent one of the biggest genealogy mistakes: drawing conclusions too early. Small Details Often Lead to Big Discoveries I've learned never to underestimate the value of seemingly unimportant information. Over the years, clues have come from places I never expected:
Together, they often tell a much larger story. One of My Favorite Research Lessons One research experience has stayed with me for years. While trying to identify my mother's biological father, our family had only fragments of information—small clues collected over many years. Some came from family conversations, others from memories shared by relatives. None of them proved anything on their own. Rather than dismissing those clues because they didn't immediately solve the mystery, I carefully documented each one. As more records were gathered, those individual clues began fitting together. Eventually they pointed to one particular family. Contact with a living relative provided additional information, including an old family photograph, and much later DNA evidence confirmed the conclusion. Had I ignored those early clues simply because they seemed incomplete, that discovery may never have happened. That experience reinforced a lesson I still follow today: Never underestimate a clue simply because it doesn't make sense yet. Don't Decide Too Soon What's Important It's human nature to filter information. We naturally think: "That probably doesn't matter." But genealogy has taught me otherwise. A witness on a marriage record. A neighbor in a census. The informant on a death certificate. A recurring occupation. A church affiliation. A family friend mentioned in an obituary. I've seen each of these become important pieces of evidence in later research. Instead of deciding too quickly what matters, record it first. You can always determine its significance later. Patterns Solve Genealogy ProblemsRarely does a single clue solve a mystery. Instead, genealogy is often about recognizing patterns. Perhaps five different records mention the same town. Several documents identify the same occupation. Multiple relatives consistently use the same unusual given name. Each clue strengthens the overall picture until a conclusion becomes much clearer. The more clues you collect, the easier those patterns become to recognize. Keep a Clue Log One habit I've found especially helpful is maintaining a simple clue log throughout a research project. It doesn't have to be complicated. Record:
Think Like an Investigator Genealogy isn't simply collecting names and dates. It's investigating lives. Every record, conversation, photograph, and document has the potential to provide another clue. Sometimes the answer isn't found because we located one spectacular record. Sometimes it's found because we patiently collected dozens of small clues until the evidence finally pointed to the correct conclusion. That's why I believe recording every clue is one of the most valuable habits any genealogist can develop. Every Clue Has the Potential to Matter The next time you're working on your family history, resist the urge to dismiss a detail simply because it doesn't seem important today. Write it down. Document where it came from. Keep an open mind. Because in genealogy, today's insignificant clue may become tomorrow's breakthrough discovery. Descendancy Research Series – Part 4 This is #4 in a series based on my 2017 "Finding Descendants in Your Family Tree" presentation More Genealogy Research Methods & TipsGet more genealogy research tips, under the Genealogy Research Tips and Genealogy Quick Tips categories.
1 Comment
9/27/2026 Testing ChatGPT Deep Research for Genealogy: Can It Create a Professional Locality Guide?Read Now Testing ChatGPT Deep Research for genealogy to create a professional locality guide for family history research. Testing ChatGPT Deep Research for Genealogy: Can It Create a Professional Locality Guide?One of the first things I do when researching in an unfamiliar place is learn the locality. When was the county formed? Did the boundaries change? What records survive? Where are they held? What isn't online? Were there courthouse disasters? Which neighboring jurisdictions matter? In other words, I don't want to start by randomly typing an ancestor's name into databases. 😉 So for another ChatGPT test, I decided to see whether Deep Research could build a professional genealogy locality guide for me. Deep Research itself isn't new—it was introduced in 2025 and is designed to search, analyze, and synthesize information from many sources into a documented report. What interested me in 2026 was combining that research ability with ChatGPT Work's newer ability to turn information into finished documents and reports. My Test Locality: Gentry County, MissouriNaturally, I went back to Samuel Steinman. 😂 Much of Samuel's adult life was spent in Gentry County, Missouri, so I asked ChatGPT to create a professional genealogy locality guide covering approximately 1850–1930. The finished guide wasn't simply a collection of links. It included jurisdiction and boundary history, record survival, census resources, vital records, land and property, probate and court records, newspapers, maps, churches, cemeteries, military records, repositories, research strategies, and a client-file locality checklist. And ChatGPT produced the guide as an editable Word document and a finished PDF. ExamplesExamples of pages 1-3 of 13.
The Part That Really Got My Attention One of the most interesting discoveries came from the county's nonpopulation census schedules. Deep Research surfaced an 1880 industrial/manufacturing schedule specifically for slaughtering and meat-packing in Gentry County. Why was that interesting? Because Samuel was documented as a butcher by 1880, and one of my research questions involves how and when he entered the trade. I had not asked ChatGPT to “find Samuel in that record.” It identified a period-appropriate, occupation-specific record set that could potentially help answer the question. That is exactly what I want from a locality guide. Not just: Here are the usual genealogy websites. But: Here are records you might not have thought to look for. And importantly, the guide correctly treated that schedule as a research target, not proof that Samuel or his associates actually appear in it.
It Also Caught a Locality TrapAnother useful example involved the county's formation date. Some derivative genealogy sources repeat an 1841 date for Gentry County, while the official Missouri source identifies the county as organized on February 14, 1845, from Clinton County. That is exactly why source selection matters. The guide prioritized government archives, historical societies, national repositories, and local institutions rather than automatically treating every genealogy webpage as equally authoritative. Would I Trust It Without Checking? Absolutely not. 😉 A locality guide can contain a tremendous amount of information—record dates, jurisdiction changes, repository holdings, online access, courthouse history, collection availability, and more. Any one of those can be wrong, incomplete, or outdated. I would still verify important information against the underlying repository or authoritative source before relying on it professionally. But as a way to rapidly build the framework for locality research and uncover less-obvious record groups, this was a very useful test. My Takeaway The biggest value wasn't that ChatGPT researched Gentry County faster than I could type up a guide myself. It was that it brought together two different jobs: Deep Research found and synthesized the information. ChatGPT Work turned it into a finished, organized research tool. That's where these newer AI workflows are becoming much more interesting to me. AI Reminder AI-generated locality guides should always be independently reviewed and verified. Record availability, repository holdings, access procedures, fees, digitization, and jurisdiction information can change. A Note About This Test This was a quick capability test, not a complete professional genealogy research project. I intentionally used limited information to see what ChatGPT could produce. The resulting guide does not replace the deeper locality research, source evaluation, or verification I would conduct for professional client work. More AI and Genealogy ResourcesLearn about more AI and family history & genealogy resources under the AI in Genealogy and Genealogy Resources category and on my dedicated Genealogy Resources page.
 ChatGPT Work for genealogy: AI tools for family history websites, workbooks, presentations, and research deliverables. ChatGPT Work for Genealogy: A First Look at What It Can Really DoI thought I understood what ChatGPT Work was. Apparently, I didn’t. If you’ve seen a couple of my recent posts, including my test of an interactive ancestor Site and my genealogy Research Command Center workbook, you’ve already seen some of the experimenting this discovery started. 😉 But I realized I never published the overview that explains why I suddenly started testing all of this in the first place. When OpenAI introduced Work in July, most of what initially caught my attention involved connected apps, files, browser access, and allowing ChatGPT to take on longer, multi-step tasks. I understood the general idea, but nothing I had seen made me rush out to test it for genealogy. Then, while working on a genealogy presentation, I discovered something I had completely missed: Work could go beyond helping me develop a presentation and actually create the editable PowerPoint itself. That discovery sent me down quite the rabbit hole. 😂 I started taking a much closer look at what Work can really do and, naturally, how genealogists might use it. So, What Is ChatGPT Work? OpenAI describes Work as an agent designed for longer, multi-step work and finished deliverables. Regular Chat remains geared more toward conversational assistance and everyday questions, while Work is intended to take a larger goal and carry more of the task through to completion. That distinction can be a little confusing because many individual tasks are not new. I have already been using regular ChatGPT for years to analyze records, develop research plans, create timelines, draft family histories, work with spreadsheets, organize information, and help build presentations. Projects also already give us a place to keep related chats, files, instructions, and research together. So I do not see Work as a replacement for either Chat or Projects. The difference seems to be more about how much of the job ChatGPT can carry out for you. Instead of only helping me plan or develop something, Work may be able to take the material I provide and create the finished output for me to review and edit. What Can Work Create? This is the part that finally got my attention. Work can create and edit documents, spreadsheets, presentations, reports, and analyses from instructions, attached source material, or existing templates. It can also work across supported apps, files, and other tools as part of a larger workflow. OpenAI describes Work as being able to bring scattered notes, drafts, files, and ideas together into finished work. And then there are Sites. ChatGPT Sites can create, preview, publish, and share actual interactive websites and lightweight apps directly from ChatGPT Work. That one surprised me enough to immediately start testing it with genealogy research too. How Could Genealogists Use Work? I started testing, and several possibilities immediately came to mind:
That is actually one of the things I plan to pay close attention to as I continue testing: Is Work genuinely giving me something new, or is it simply another way to do something I could already do in Chat or Projects? If regular Chat already handles the task well, I don't see any reason to use Work just because it is newer. The Finished Deliverables Are What Interest Me Most So far, the biggest difference for me has been the ability to move from: “Help me create this.” to: “Create this so I can review and edit it.” That is exactly what happened with my presentation test. ChatGPT has helped me build presentations for years—ideas, slide titles, timing, visuals, and more from my notes or instructions. But I still had to manually build the actual PowerPoint and the daunting task of designing it. With Work, I received the editable presentation itself. Then I tested ChatGPT Sites using research, documents, and photographs from one of my ancestors. Instead of giving me website code and leaving me to figure out what to do with it, ChatGPT created an actual hosted Site that I could preview, edit conversationally, and eventually share by link. Those capabilities turned out to be interesting enough that I began testing them individually, and one test quickly led to another. Where Work May Be Most Useful for Genealogy I think Work may be especially helpful when the research or information already exists and the challenge is turning it into something useful. For example: Research → presentation Research → interactive family-history Site Existing notes and files → organized deliverable Blog or article → presentation Completed research → client or family-history experience That does not replace the research itself. But it could reduce some of the time-consuming work that happens after the information has already been gathered and analyzed. For genealogists who speak, teach, write, work with clients, or create family-history projects for relatives, that could be very useful. Responsible Use Still Matters As with any AI tool, more capability also means more responsibility. Genealogy can involve living people, DNA information, unknown parentage, private family stories, client material, personal photographs, and copyrighted records or publications. Before using Work with genealogy material, consider what you are uploading, whether you have permission to use it, and whether the resulting output should remain private. And, of course, verify everything. A polished report, presentation, spreadsheet, or website can still contain an incorrect date, relationship, interpretation, or unsupported detail. AI may help create the finished product. The genealogist is still responsible for the genealogy. My First Impression I am still figuring out where ChatGPT Work fits into my own workflow. So far, I do not think its value is that everything suddenly became new. Much of what Work can do overlaps with things we already do in regular ChatGPT. What interests me is where it can take an existing task farther, especially when it can create something I would otherwise have to build myself. What began with two examples, editable PowerPoint presentations and interactive Sites, quickly turned into a much larger series of hands-on genealogy tests. Since then, I’ve experimented with research workbooks, presentation handouts, printable and fillable genealogy worksheets, locality guides, interactive charts, ancestor biographies, and more. Some impressed me more than others. Some needed revisions. And a few showed me possibilities I genuinely had not considered before. I’ll be sharing each of those tests separately so I can look at what worked, what didn’t, and whether the result actually offers something useful for genealogists. And knowing me, I’m probably not finished testing yet. 😉 If I find another Work capability that makes me think, “Now this really is different,” you can probably guess what will happen next. More AI and Genealogy ResourcesLearn about more AI and family history & genealogy resources under the AI in Genealogy and Genealogy Resources category and on my dedicated Genealogy Resources page.
 UGA Summit of Excellence 2026 Wrap-Up: Three Days of Genealogical Learning UGA Summit of Excellence 2026 Wrap-Up: Three Days of Genealogical Learning The Utah Genealogical Association’s (UGA) Summit of Excellence 2026 has wrapped up, and once again, it was three full days of genealogical learning! I had the pleasure of attending the virtual conference again this year, and presenting as well. One of the things I enjoy most about the Summit is the variety. From beginner topics to DNA, records, technology, international research, writing, military research, and more, there is always something new to learn, or a familiar subject presented in a way that makes you look at it differently. Day 1: Getting Started DayThe conference kicked off with the traditional free beginner day, followed by the keynote address from Michael L. Strauss, MA, AG, AGL, at the end of the day. Even though the sessions were geared toward those getting started in genealogy, I joined them all. Because why not? It’s free. 😉 One presentation that especially stood out to me was Bringing Your Ancestors to Life: Going Beyond the Facts by Karen A. Fortin. Karen used an interesting ancestor story to demonstrate how we can move beyond simply collecting names, dates, and places and begin developing a fuller picture of our ancestors and their lives. That is something I always appreciate—using the records we uncover to tell more of the story rather than leaving our ancestors as a collection of facts on a pedigree chart. Day 2: DNA, Records, International, Military, and Ethnic ResearchDay 2 offered tracks covering DNA, Records, International, Military, and Ethnic topics. There were ten sessions offered throughout the day, with two running at each time slot, which meant attendees could choose five to watch live. Fortunately, the recordings will be available through the end of December, so we can go back and watch the sessions we had to miss. I was able to attend four sessions live instead of five because this was also the day of my own presentation, COLD CASE: An Investigative Protocol for Genealogical Brick Walls. Of course, one of the presentations I wanted to see happened to be scheduled at the same time as mine, so that one will have to wait for the recordings! One of my Day 2 standouts was Year by Year: Reconstructing Families with City Directories by Kate Townsend. This was a very, very good presentation and extremely useful. City directories can contain so much more information than we sometimes realize when we look at only a single year. Following an individual or family year by year can help reveal residences, occupations, household changes, relationships, migrations, and clues to other records. It was also a topic that particularly interested me because this is a presentation topic I have been working on myself, so I found the session especially valuable. Day 3: Writing, Technology, Records, International, DNA, and Military ResearchDay 3 included tracks covering Writing, Technology, Records, International, DNA, and Military topics. As with Day 2, ten sessions were offered, with two running at each time slot, allowing attendees to choose five live presentations. Well...in theory. 😉 I was able to watch four sessions instead of five. Unfortunately, one speaker did not show up. After waiting about ten minutes, we were asked to join the other presentation being offered during that time slot. I tried, but after waiting another ten minutes to be let into that session, I finally gave up. So, once again, I’ll be looking forward to the recordings! Two presentations especially stood out to me on Day 3. Testing Family Legends: When Oral History Meets the Archive The first was Testing Family Legends: When Oral History Meets the Archive by Sue McNelly. I almost didn’t choose this presentation because, based solely on the title, I didn’t think the topic would particularly interest me. I’m very glad I changed my mind. This turned out to be an excellent presentation and much more research-focused than I had expected from the title. Sue presented a very interesting approach to following clues through the records and systematically testing family claims. She covered testing claims with records and research, correlating information, collateral and cluster research, evaluating evidence, and more. It was thorough, very well thought out, and easy to follow. It was definitely one of those conference sessions that reminds me not to judge a presentation entirely by its title! What the Law Put Asunder: Divorce in Americas Another standout was What the Law Put Asunder: Divorce in Americas by Sara Cochran. This was another session I almost skipped because divorce records were not a topic I was particularly interested in at the moment. Boy, am I glad I didn’t! Sara was excellent, as always. She took a topic that many genealogists may not immediately think of as an important part of their research and showed just how useful these records can be. Divorce records can contain information about family relationships and circumstances that may not appear anywhere else. The presentation was informative, practical, and interesting—and made a very good case for why divorce research deserves a place in our genealogical toolbox. Looking AheadOnce again, the UGA Summit of Excellence offered a great mix of genealogy education over three days. One of the biggest advantages of a virtual conference like this is not having to truly “miss” a presentation simply because two interesting sessions are scheduled at the same time. With the recordings available through the end of December, I still have plenty more sessions to watch—and a few I already know are at the top of my replay list. That ability to go back and catch the presentations I couldn’t attend live is one of my favorite parts of the Summit. I still have more learning ahead of me even though the live conference has officially ended. A huge thank you to the Utah Genealogical Association, the organizers, volunteers, speakers, and attendees who made the 2026 Summit of Excellence possible. I was thrilled to be part of the conference again this year, both as a presenter and as an attendee. And now...time to start working my way through those replays! 😉 More Events, Classes, and PresentationsLearn about more fantastic genealogy events, classes and presentations under the Genealogy Events category and my upcoming speaking events. Looking for a Genealogy Speaker?Explore my genealogy presentations for societies, conferences, seminars, workshops, and other genealogy events.
 Microsoft Publisher Is Retiring: My Last-Minute Family History File Rescue Microsoft Publisher Is Retiring: My Last-Minute Family History File Rescue I have spent part of the last couple of days doing something I definitely did not have on my genealogy to-do list: opening hundreds of old Microsoft Publisher files and making sure anything important was saved in a format I could still use in the future. And when I say hundreds, I mean hundreds. 😉 I actually started working on this a couple of months ago, but with Microsoft Publisher's retirement now just weeks away, I realized it was crunch time. At first, I didn't think Publisher's retirement would affect me very much. I barely use it anymore. I have a few old business items and templates created in Publisher—things like invoices, business flyers, cards, and other materials—but most of what I create today is done with newer tools. Then I remembered my books. And suddenly, Publisher's retirement became a much bigger project. More Than a Few Old Business Files Over the years, I have published books and created family heirloom books, and many of the photograph and picture pages in those books were originally designed in Microsoft Publisher. Some of those files go back more than a decade. Although many had already been saved or exported as PDFs or images somewhere along the way, not all of them had. So, there I was, going through old folders and Publisher files one by one, checking what I had, opening files, and saving anything I might want or need again as a PDF and, for some of the individual picture pages, JPEGs as well. It wasn't particularly exciting genealogy work. But it was definitely family history preservation work. And that is what made me realize this was worth sharing. Microsoft Publisher Is Retiring in October If you still have Microsoft Publisher files tucked away on your computer, external drives, or cloud storage, this is a deadline you should know about. Microsoft is officially retiring Publisher in October 2026. For Microsoft 365 subscribers, Publisher can continue to be used through October 1, 2026. After that date, Publisher will no longer be available through Microsoft 365, and subscribers will no longer be able to use Publisher to open or edit their PUB files. Microsoft has specifically recommended converting existing Publisher files into other formats before then. But there is an important distinction if you own a perpetual version, such as Publisher 2021. Your copy will not suddenly stop opening on October 1. Microsoft says perpetual versions of Publisher can continue to be installed and used after retirement. However, support for Publisher 2021 ends in October 2026 along with Office 2021. Once support ends, Microsoft will no longer provide security updates, bug fixes, or technical support. So although Publisher 2021 may continue working, that doesn't mean I want important family history material to exist only as a Publisher file. Future Windows changes, computer replacements, software compatibility issues, or simply not having Publisher installed someday could eventually make those files difficult—or impossible—to use. And there isn't going to be a Publisher 2024 waiting for us. Microsoft did not include Publisher in Office 2024. Publisher really is reaching the end of the road. That's When My Little Backup Project Became a Big One Once I understood what was happening, I started thinking beyond the handful of Publisher files I use—or used to use—for my business. What old files did I have that I hadn't opened in years? What had I created in Publisher that existed nowhere else? What would happen if ten years from now I wanted one of those family heirloom book pages and could no longer open the original file? That led me straight to those old book folders. Many of the picture pages contained family photographs arranged into carefully designed layouts. Some had captions and other information incorporated into the page. They weren't simply photographs that I could pull from my photo collection and instantly recreate. Yes, I still have my original photographs. Yes, I still have my published books. And yes, many pages had already been saved in other formats. But I didn't want to assume everything important had been preserved. So I checked. And checked. And checked some more. 😉 What I Saved For anything I might want to view, print, share, or reference in the future, I made sure I had an accessible version outside Publisher. For me, that primarily meant:
I'm not throwing away my original Publisher files simply because the program is retiring. Those are still the original working files, and I may be able to open and edit them for years. I'm simply making sure they are not my only copies of the content. For family history preservation, I would much rather have the original proprietary file and an accessible copy than depend entirely on software that is reaching the end of its supported life. Do You Have Forgotten Publisher Files? If you have ever used Microsoft Publisher, this is probably a good time to find out. Publisher was popular for all kinds of projects genealogists and family historians might have created over the years: family history books, reunion booklets, newsletters, pedigree charts, photo pages, memorial programs, cemetery or society publications, flyers, invitations, calendars, certificates, family reunion materials, and more. And because some of these files may be 10, 15, or even 20 years old, you may not remember everything you created. Microsoft recommends searching your computer or storage for Publisher files by looking for the .pub file extension. That's essentially what I did—although in my case, I already knew exactly which folders were going to cause me trouble. 😉 A Quick Publisher Preservation Checklist If you have old Publisher files, I would do this before October: 1. Search for your PUB files. Look through your computer, external drives, backup drives, and cloud storage. 2. Identify anything you would hate to lose access to. Don't worry about every old flyer or abandoned project unless it matters to you. Concentrate first on irreplaceable family history, genealogy, photographs, books, and personal material. 3. Open important files while you still have Publisher available. Make sure they actually open correctly and that photographs, fonts, and layouts still appear as expected. 4. Save or export important items as PDFs. For visually designed pages, PDFs are particularly useful because the goal is often to preserve how the finished page looks. 5. Save images separately when appropriate. Depending on the project, you may also want JPEG or other image copies of individual pages or elements. 6. Keep the original PUB files too. Converting something to PDF doesn't mean you need to destroy the original. 7. Back everything up. Of course, converting a file isn't much help if your only copy is still sitting on one aging computer. The Bigger Family History Lesson This whole experience reminded me of something that goes far beyond Microsoft Publisher. Digital preservation isn't just about backing up our files. It is also about making sure we will still be able to access those files. Genealogists spend an enormous amount of time preserving old photographs, scanning documents, downloading records, building family trees, writing family histories, and organizing decades of research. But our digital family history can become dependent on a particular program, file format, website, device, or technology without us even realizing it. Today, for me, it was Microsoft Publisher. Years from now, it will undoubtedly be something else. A file can be perfectly backed up in three different places and still become a problem if none of the computers in your family can open it. That is why part of digital preservation needs to include occasionally asking: What software do I need to open this? Will this format still be usable years from now? Do I have an accessible version of the finished material in addition to the original working file? Apparently, this week my own answers to those questions involved several hundred Publisher files and quite a bit more time than I originally expected. 😉 But my published books, family heirloom books, photograph pages, and other important Publisher creations (including many my children created when they were little and are priceless) now have preservation copies outside the program. And I can finally cross "rescue old Publisher files before October" off my list. If you've ever used Microsoft Publisher—especially for genealogy, family books, photographs, newsletters, or other family history projects--now might be a very good time to search for those old PUB files and make sure anything important isn't trapped inside them. October is almost here. Learn more at Microsoft Publisher retirement and preparation information. More on Software for Genealogy & OrganizationLearn about more family history and genealogy software and organization under the Genealogy Software and Organization categories and on my dedicated Genealogy Resources page.
 ChatGPT turns ancestor research into a genealogy research workbook and an entire Research Command Center. Testing ChatGPT Work: Can It Build a Genealogy Research Workbook, using AI? When I think about fun new ways to use AI for genealogy, Excel spreadsheets aren't usually the first thing that comes to mind. 😉 But since ChatGPT Work can now create and edit spreadsheets along with documents, presentations, PDFs, and other finished deliverables, I decided to see what it could do with genealogy research. Naturally, I pulled out my favorite AI test ancestor again: my 2nd great-grandfather, Samuel “Sam” Steinman. This time, I wanted something completely different. I asked ChatGPT to turn Samuel's existing research into a Genealogy Research Command Center. For this quick test, I intentionally kept the input simple. I uploaded only Samuel’s ancestor profile, which already contained many of my researched facts, details, notes, and source information. I did not upload my complete research file, full citations, individual record images, newspaper articles, or every document I have collected for him. The purpose of the experiment was simply to see what ChatGPT could build from a limited starting file—not to create a complete professional research file for Samuel. More Than a Spreadsheet What ChatGPT created was an actual editable Excel workbook with multiple coordinated tabs for managing different parts of the research. It included areas for Samuel's ancestor profile, documented timeline, research log, evidence and conflict analysis, sources and citations, FAN Club research, tasks and next steps, findings and conclusions, and more. The Dashboard pulled the project together by tracking things such as completed and open tasks, logged sources, unresolved claims, timeline events, and research progress. This was much more interesting than simply putting genealogical facts into rows and columns. Turning a Brick Wall Into a WorkflowI especially liked that the workbook was built around an actual research objective. In Samuel's case, one question I've been exploring is when and how he entered the butcher trade. We know he was working on the family farm in 1870. By the 1880 census, he was a butcher. Then, in 1885, he purchased G. W. Shepherd's meat market. But what happened in between? Using the information available in the limited ancestor profile I supplied, the workbook turned that question into specific research tasks: search 1875–1880 newspapers, investigate directories and merchant records, build a timeline for G. W. Shepherd's business, and explore the Hulet/Shepherd/Steinman FAN network. That is where this became useful to me. It wasn't just storing research. It was helping manage the research process. Evidence, Conflicts, and Things That Are NOT Samuel Another tab separated claims from the evidence supporting them. Instead of treating everything as equally certain, the Evidence Matrix categorized conclusions as Proven, Supported, Unresolved, or Excluded and recorded conflicts, gaps, and possible next actions. That also gave me somewhere to preserve records that had been investigated and ruled out. For example, an old 1921 St. Louis newspaper item involving Prohibition stills had previously been associated with Samuel. Later research showed definitively that it was not him. Rather than simply deleting it and potentially rediscovering the same false lead later, the workbook retains it as an excluded identity issue. That is good research management. And I Didn't Have to Build the Excel System Myself This may be my favorite part. The workbook contains things such as formulas, status tracking, organized tables, and drop-down selections. I don't have to build all of that functionality manually. I can simply use the fields and dropdowns, add research as I go, and give the workbook back to ChatGPT later if I want something changed, expanded, or reorganized. That makes a fairly sophisticated spreadsheet much more accessible. Examples
My Takeaway I originally thought I was testing whether ChatGPT could make a genealogy spreadsheet. What it actually created was closer to a research-management system. I can see this being useful for:
No. But as a dedicated workspace for managing one complicated research problem? That is much more interesting. And once again, ChatGPT took something I could have spent a great deal of time building and gave me a functioning starting point instead. 😉 AI Reminder A well-organized workbook does not make the information inside it accurate. Genealogical facts, evidence classifications, research conclusions, and citations still require independent review and verification. A quick note about my testing: These were intentionally quick capability tests, not complete genealogy research projects. Depending on the experiment, I supplied only limited material—such as an ancestor profile containing selected research, notes, facts, and source information; a few documents or photographs; or an existing blog post. I did not provide my complete research files, full citations, or every supporting document unless the particular test required it. More AI and Genealogy ResourcesLearn about more AI and family history & genealogy resources under the AI in Genealogy and Genealogy Resources category and on my dedicated Genealogy Resources page.
8/23/2026 Testing ChatGPT Sites for Genealogy: Can It Build an Interactive Ancestor Website?Read Now Testing ChatGPT Sites for genealogy to see how AI can turn family history research into an interactive ancestor website. Testing ChatGPT Sites for Genealogy: Can It Build an Interactive Ancestor Website with AI?I have created plenty of family history pages and ancestor stories over the years, but building an interactive website around one ancestor is another matter entirely. So when OpenAI introduced ChatGPT Sites in July 2026, I immediately started wondering what it could do with genealogy. Sites is currently in public beta and allows ChatGPT to turn information into an interactive website or lightweight web app that can be previewed, refined, and shared through a URL. Naturally, I pulled out my official AI guinea pig—my 2nd great-grandfather, Samuel “Sam” Steinman. 😉 My First Genealogy Site Test Because this was only a test, I didn't upload every piece of research I have on Samuel. I started with his Ancestry ancestor profile containing facts, notes, sources, and timeline information, along with a few family photographs and selected records. Then I asked ChatGPT to turn that material into a family-history Site. And it did. Instead of giving me code or instructions for building a website myself, ChatGPT created the actual Site. It organized Samuel's story into sections covering his life, family, research evidence, photographs, and records, and turned the material into something that felt much more like a small ancestor website than a document pasted onto a webpage. That alone was an interesting test. But, of course, I couldn't leave it there. 😂 Could I Make It More Interactive? The first version looked nice, but it still felt somewhat like a long scrolling family-history page. So I created a second version and asked ChatGPT to make the experience substantially more interactive and exploratory while preserving the genealogy and overall visual style. The goal was to let visitors explore Samuel's life rather than simply read from top to bottom. That is where Sites became much more interesting to me. I could continue editing the Site conversationally—asking ChatGPT to restructure sections, improve navigation, change captions, add interactive elements, or refine the visitor experience. OpenAI specifically describes Sites as something you can preview and refine directly with ChatGPT before sharing.
Protecting Family PhotographsOne part of this experiment became especially important. I had included four personal family photographs, and I wanted them protected. At first, the watermark behaved more like a visual overlay and could disappear if someone opened or saved the image. That wasn't good enough. So I had ChatGPT replace only those displayed copies with flattened, permanently watermarked versions, while preserving the original source images. The watermark remained part of the actual served image rather than simply appearing over it in the Site viewer. That was a good reminder that when experimenting with new publishing tools, genealogists need to think beyond appearance. What happens when someone opens, enlarges, shares, or saves the material? For family photographs, documents, and other privately held material, that matters.
What I Like About Sites for Genealogy I don't see Sites replacing a full genealogy website or research database. What interests me is the possibility of creating focused family-history experiences. For example:
That is a very different way of presenting family history. A Few Cautions As with any AI-created genealogy product, the finished Site still requires careful review. I specifically instructed ChatGPT not to invent genealogical facts, relationships, dates, quotations, or evidence. I also reviewed the structure, captions, photographs, and research presentation myself. And because Sites are designed to be shareable and can potentially be published through a URL, privacy and copyright deserve special attention before putting family-history material online. My Takeaway This test surprised me because I originally expected something closer to a generated webpage. Instead, I found myself building and revising an interactive family-history experience through conversation. And because I created two versions of Samuel's Site, I could also experiment without destroying the original. For me, that is where the real potential is. Not simply: “AI can make a website.” But: “AI can help turn genealogy research into something family members can actually explore.” And that opens up a lot of possibilities. 😉 A quick note about my testing: These were intentionally quick capability tests, not complete genealogy research projects. Depending on the experiment, I supplied only limited material—such as for this quick test, I uploaded Samuel’s ancestor profile along with only a few selected records and family photographs—not my complete research collection for him. More AI and Genealogy ResourcesLearn about more AI and family history & genealogy resources under the AI in Genealogy and Genealogy Resources category and on my dedicated Genealogy Resources page.
 Why starting your descendancy research offline can lead to stronger genealogy discoveries Why I Don't Start My Genealogy Research Online: Descendancy Research Series – Part 3It may sound surprising coming from a professional genealogist, but one of the first pieces of advice I give people starting a new genealogy project, such as descendancy research, is this: Don't go online—not yet. In a world where millions of historical records are available with just a few clicks, it seems almost counterintuitive to avoid genealogy websites at the beginning of a project. But after years of researching my own family, clients, descendants, brick walls, and unknown parentage cases, I've learned that spending a little time offline first usually leads to better research, and fewer mistakes. Here's why. Start with What You Already Know Before searching a single online record, gather everything you already have. Talk with parents, grandparents, aunts, uncles, cousins, and longtime family friends. Pull out old photographs, letters, certificates, military papers, funeral cards, family Bibles, and other documents tucked away in drawers or boxes. You may be surprised how much information is already sitting in your own home, or in the homes of relatives. These first conversations many times reveal names, places, occupations, family traditions, and stories that never appear in historical records. Family Stories Are Worth RecordingFamily stories aren't always completely accurate. Names get mixed up. Dates change. Events become exaggerated over time. But I've found that most stories contain a kernel of truth somewhere within them. Instead of dismissing them, record everything. Later, you can compare those stories with historical records to determine which details can be confirmed. Sometimes one seemingly insignificant comment becomes the clue that solves an entire research problem. Record Every Clue—Even If It Doesn't Make Sense Yet One of the habits I've developed over the years is writing down every clue, no matter how small or insignificant it seems at the time. A nickname. A military branch. A hometown. An occupation. An illness. A family argument. A mention of "the twins." Even details that don't make sense initially may become incredibly important later. I've had research cases where a single clue, remembered years after a family conversation, eventually led to the correct person once enough evidence had been gathered. Draw Your Family Tree by Hand Yes... By hand. I know genealogy software is wonderful, and I use it regularly. But before entering information into a computer, I still recommend sketching out a simple family tree on paper. Why? Because drawing it yourself forces you to slow down. You begin noticing gaps. Questions naturally appear. Relationships become easier to visualize. You're thinking about the family instead of clicking hints. It doesn't need to be perfect. A rough sketch is usually all you need to organize your thoughts before diving into records. Why I Wait Before Searching Online This is probably the advice that surprises people the most. Online genealogy websites are incredible resources. But they also come with distractions. Within minutes you may find:
Beginning offline helps you develop your own understanding of the family before outside information influences your thinking. I want my conclusions to come from evidence, not suggestions generated by an algorithm. Build Your Own Foundation First Once you've gathered everything your family already knows and organized your information, then it's time to begin searching historical records. Now you're approaching those records with questions to answer rather than simply hoping the next hint will tell you where to go. That small shift in mindset usually leads to stronger research and more confident conclusions. Slow Down to Move Faster It may seem like you're delaying your research by avoiding online resources at first. In reality, you're building a much stronger foundation. The more organized you are before you begin searching records, the less likely you are to chase the wrong family, duplicate work, or overlook important clues already sitting in your own home. Sometimes the fastest way to solve a genealogy problem is to spend a little extra time at the very beginning. Part 2: How to Choose the Best Starting Ancestor for Descendancy Research This is #3 in a series based on my 2017 "Finding Descendants in Your Family Tree" presentation More Genealogy Research Methods & TipsGet more genealogy research tips, under the Genealogy Research Tips and Genealogy Quick Tips categories.
 Choosing the right starting ancestor when beginning a descendancy research project in genealogy How to Choose the Best Starting Ancestor for Descendancy Research: Descendancy Research Series – Part 2Once you've decided to research your ancestors' descendants, the next question is often the hardest: Which ancestor should you begin with? It may seem like a simple decision, but choosing the right starting point can make the difference between an enjoyable, productive project and one that quickly becomes overwhelming. Over the years, I've found that a little planning before you begin can save countless hours later. Rather than selecting an ancestor at random, I recommend choosing one that gives you the greatest opportunity for success while keeping the project manageable. Here are the factors I consider when deciding where to begin. Start with an Individual or an Ancestral CoupleOne of the first decisions you'll need to make is whether to begin with a single ancestor or an ancestral couple. In most cases, I recommend starting with an ancestral couple whenever possible. This allows you to research all of their children and descendants together, providing a more complete picture of the family. If information about one spouse is limited, however, beginning with an individual ancestor may make more sense until additional records are located. If an ancestor has more than one spouse, you may want to choose that individual to start with. Four to Five Generations Back Is Usually Ideal One of the most common mistakes I see is starting too far back in the family tree. While it may be tempting to begin with your earliest known ancestor, doing so can create an enormous amount of unnecessary work. Every additional generation dramatically increases the number of descendants you'll need to research. In many cases, I find that choosing an ancestor about four to five generations back strikes a good balance. The family is large enough to provide valuable clues while still remaining manageable for most research projects. Consider an Immigrant Ancestor If your goal is to better understand how your family arrived in a new country, an immigrant ancestor often makes an excellent starting point. Researching all of their descendants can reveal migration patterns, settlement locations, occupations, military service, family traditions, and how later generations spread across the country. You may discover branches of the family you never knew existed. Choose Someone with an Interesting Story Sometimes the best starting ancestor is simply the one who sparks your curiosity. Perhaps they served in the military, survived a historical event, immigrated from another country, or left behind an intriguing family mystery. Research is often easier, and a lot more enjoyable, when you're genuinely interested in the person you're studying. Why I Usually Recommend an Ancestor Who Was Living Around 1850 Whenever possible, I recommend choosing an ancestor who lived around the mid-1800s. For many researchers in the United States, this provides access to a growing number of census records and other valuable historical sources while keeping the project within a manageable timeframe. Beginning much earlier often means working with fewer surviving records and significantly more generations of descendants to research. Don't Make the Project Bigger Than It Needs to Be I learned this lesson firsthand. For one of my own family lines, I decided to begin one generation earlier than I normally recommend. While it certainly can be done, it also created considerably more work because every additional generation adds more descendants to research. That experience reinforced something I still recommend today: start with a project you can realistically complete before expanding it further. There's always time to go back another generation later. Think About Your Research Goal Before selecting a starting ancestor, ask yourself:
You Don't Have to Start with the "Oldest" Ancestor Many beginners assume they should always start with the earliest known ancestor in their tree. In reality, that's rarely necessary. A more recent ancestor usually provides plenty of opportunities to learn descendancy research techniques while producing faster and more rewarding results. As your confidence grows, you can always expand your research to earlier generations. Start Smart, Not Big One of the keys to successful descendancy research isn't simply choosing an ancestor—it's choosing the right ancestor. By selecting a manageable starting point that fits your research goals, you'll build a stronger, more organized descendancy tree while avoiding unnecessary frustration. Remember, every successful research project begins with a single ancestor. Choosing that ancestor wisely can set the stage for discoveries that extend far beyond your direct family line. This is #2 in a series based on my 2017 "Finding Descendants in Your Family Tree" presentation More Genealogy Research Methods & TipsGet more genealogy research tips, under the Genealogy Research Tips and Genealogy Quick Tips categories.
8/2/2026 Gemini's AI Video for Genealogy: My First Ancestor Video Experiments (The Good, the Bad, and the Hilarious)Read Now  Testing Gemini's new Omni AI video generation to create historical ancestor videos for genealogy Artificial intelligence continues to evolve at an incredible pace, and naturally, I couldn't resist testing another new feature. After experimenting with Google's new Lyria 3 and Lyria 3 Pro music generation tools, I decided to see what Gemini could do with AI-generated video. Could it create realistic scenes from an ancestor's life? Could multiple short clips be combined into a believable historical story? As usual, I turned to my "official AI test ancestor," Samuel Steinman. For the past few years, Samuel has been my consistent benchmark for testing new AI genealogy tools. Using the same ancestor across different AI platforms allows me to compare results more fairly over time. This time, however, I wasn't asking AI to write about Samuel. I wanted it to bring him to life. Experiment #1: No Prompt at AllFor my first test, I decided to do almost nothing. I uploaded only the AI-generated character portrait I had previously created of Samuel (in ChatGPT a little over a year ago)—no prompt, no instructions, no historical context. Gemini automatically generated a short 10-second video. To my surprise, it didn't simply animate the portrait. It also created an entire scene, complete with sound effects, dialogue, and a setting inspired by the background in the image. Because Samuel's character portrait happened to include a farm auction sign in the background, Gemini built an entirely new scene around that setting. While the story it created wasn't historically relevant to Samuel's actual life, it was very interesting to watch. The video felt surprisingly cinematic considering I hadn't given the AI any direction whatsoever. It was a pretty impressive demonstration of Gemini's creativity, but not necessarily of historical storytelling. Experiment #2: Directing "A Day in the Life of Samuel Steinman"Next, I wanted to see whether Gemini could create something much more meaningful for genealogy. Rather than letting AI invent its own story, I wanted to direct one myself. The idea was simple:
Samuel looked exactly like the character portrait I'd been using for a little over a year. The historical atmosphere was beautiful, the lighting felt cinematic, and watching him walk through town toward his butcher shop was genuinely impressive. At that point, I was thinking... "This might actually work." Then the AI Gremlins ArrivedThe second scene started well enough. Samuel unlocked the door to his butcher shop, reached up to remove his hat... ...and then immediately put it back on. Without explanation. Without reason. Apparently, he changed his mind. The third scene introduced an even more entertaining challenge. As Samuel prepared for the day, he began sharpening his butcher knives. Except the knives couldn't decide how many of themselves existed. One knife somehow became two. Then three. A cleaver suddenly appeared. Another knife seemed to duplicate itself. At one point, Samuel briefly wandered away from the butcher block before instantly returning as though nothing had happened. It reminded me a lot of the early days of AI image generation, when people mysteriously had six fingers or extra limbs. Instead of extra fingers... Samuel had extra knives.
What I LearnedDespite the amusing glitches, I actually came away fairly encouraged. Gemini did an excellent job maintaining Samuel's overall appearance from scene to scene. His facial features, clothing style, and the historical setting remained surprisingly consistent. Where the AI struggled was with object permanence and complex actions. Simple scenes, like walking, looking around, entering a building, etc., worked really well. Scenes involving multiple objects, hand movements, or several sequential actions were much less reliable. Hats developed minds of their own, knives multiplied, and continuity occasionally wandered off in unexpected directions. In other words, AI video today feels very much like AI image generation did a couple of years ago. The potential is obvious. The technology simply isn't quite there yet, at least maybe not for Omni. Will I Keep Testing It?Absolutely. This first experiment wasn't about creating a polished historical film. It was about discovering what today's AI video tools can, and can't, do for genealogy. As these models improve, I plan to continue using Samuel Steinman as my benchmark ancestor. Running the same prompts over time should provide an interesting look at how rapidly AI video evolves and whether it eventually becomes practical for creating historically inspired ancestor stories. For now, though... I'll probably keep a close eye on Samuel's hat. And count the knives. A Note on Responsible AI UseAs with all of my AI experiments, these videos are creative interpretations, not historical evidence. While AI can help visualize an ancestor's world, it should never replace documented research or be presented as an accurate reconstruction of events. If you choose to create AI-generated ancestor videos, consider clearly disclosing that they are artistic interpretations based on historical research. The genealogy, records, source analysis, and conclusions should always come from documented evidence, not the AI itself. Have you experimented with AI video yet? If so, I'd love to hear which tool you used and how your results compared. Did your ancestor behave perfectly...or did hats and household objects suddenly develop a mind of their own, too? More AI and Genealogy ResourcesLearn about more family history and genealogy resources under the AI in Genealogy and Genealogy Resources category and on my dedicated Genealogy Resources page.
|
Welcome to the BlogWelcome to Know Who Wears the Genes in Your Family! Here you'll find genealogy research tips, family history resources, DNA insights, technology and AI tools, genealogy news, and stories from my own research journey. Whether you're just starting your family tree, exploring your ancestry, or tackling a challenging brick wall, my goal is to help you discover, understand, and preserve your family's story. Categories
All
Top Posts
BlogrollEvalogue.Life, Heart of the Family, Molly's Canopy, Climbing My Family Tree, DNA Breakthroughs, Ancestral Findings, Genealogy Tip of the Day, Family History Daily, Heart of the Family Blog Party, Genea-Musings, Best of the Genea-Blogs, Genealogy à la carte, Empty Branches on the Family Tree, Our Growing Family Tree, AI Genealogy Insights, Family Locket, Beaumont Genealogy-AI
Archives
September 2026
|
RSS Feed
Ready to Discover your family's Story? Start Your journey Today! |
|
📌 Quick Links💡 Tips & Resources⚖️ Legal |
🧬 ServicesGenealogy Research | DNA Research | Brick Wall Research | Heir & Living People Search | Unknown Parentage Research | Ancestor Biographies | DNA Match Grouping | Family Tree Building | Publishing | Coaching | Workshops | Speaking
📚 Products |
📬 Stay Connected🕒 HoursMon–Sun: 8am – 8pm
🗺️ Map
|
|
Member of the Association of Professional Genealogists |
✨ Commitment
Know Who Wears the Genes in Your Family is dedicated to promoting family history and genealogy, while maintaining commitment to client care and professional service, and adheres to the Code of Ethics and Professional Practices put forth by the Association of Professional Genealogists.
© 2016–2026 Diane Henriks | Know Who Wears the Genes in Your Family. All rights reserved.