|
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.
0 Comments
 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.
 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.
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.
 Creative AI for Genealogy: Easy, Engaging Family History Projects with Little or No Prompting Creative AI for Genealogy: You Don't Need to Be a Prompt Engineer Discover how today's AI tools can help you preserve and share your family history in engaging new ways, without writing complicated prompts. Artificial intelligence seems to be everywhere these days. Open social media, browse genealogy forums, or attend a conference, and you'll likely hear someone talking about AI. Unfortunately, many genealogists still feel that AI is complicated, intimidating, or only useful for people who enjoy writing long, detailed prompts. The good news? It doesn't have to be. Many of today's AI tools can create meaningful and engaging family history projects with very little effort. In many cases, all you need to do is upload a photo, choose an ancestor, or click a single button. But before we talk about the tools themselves, I'd like to ask you a few questions.
As genealogists, we spend tons of hours researching records, solving mysteries, documenting sources, and building family trees. But many times, those years of hard work remain tucked away inside binders, filing cabinets, genealogy software, or online family trees that few relatives ever explore. Our research deserves an audience. More importantly, our ancestors deserve to be remembered. AI Is Simply Another ToolArtificial intelligence doesn't replace genealogy research. It doesn't replace careful analysis, original records, or sound conclusions. Instead, AI gives us new ways to share the stories we've already uncovered. Think of it this way. A beautifully researched ancestor can become:
Only the way we tell the story has. You Don't Need to Be a Prompt Engineer One of the biggest myths about AI is that you need to become an expert prompt writer before you can create anything worthwhile. That just isn't true anymore. Many AI tools now include built-in features that require little or no prompting at all. Others need only a short instruction such as: "Generate a biography." or "Create a one-minute video about this ancestor." The technology has become much more friendly, allowing genealogists to focus on creativity rather than complicated instructions. Why Creative Projects MatterFamily history is much more than collecting names and dates. It is about preserving lives. When we transform our research into stories, music, videos, or visual experiences, we create opportunities for others to connect with our ancestors in ways that traditional pedigree charts just can’t. A grandchild may never sit down to read a twenty-page research report. But they might happily watch a one-minute video about a great-great-grandparent. They may listen to a song inspired by an ancestor's life. They may become curious after seeing an old family photograph gently smile through animation. Those moments can become the doorway into a lifelong interest in family history. A New Series on Creative AI Over the next several articles, we'll explore some of my favorite ways to use today's AI tools to bring family history to life. We'll look at projects such as:
Most of these projects require little or no prompting and can be completed by genealogists of all experience levels. You don't need to be a tech expert. You just need a story worth telling. And if you're a genealogist, chances are you already have hundreds of them waiting to be shared. Final Thoughts Artificial intelligence isn't replacing genealogy. It's giving us new ways to preserve, experience, and share the family stories we've spent years discovering. After all, the goal isn't simply to build a family tree. It's to make sure future generations want to climb it. 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.
7/19/2026 AI in Genealogy: Creating Ancestor Songs with Gemini's New Lyria 3 Music GeneratorRead Now  Testing Gemini's new Create Music feature by turning my 2nd great-grandfather's life story into a folk ballad Ever since AI image generation became popular, I've wondered when AI music would become just as accessible for genealogists. I've been experimenting with AI music for a couple of years now using tools like Suno and AI Music Factory (you can read more about that at Creating Family History Songs with AI: Honoring Our Ancestor’s Through Music), usually by writing lyrics first (often with ChatGPT) and then letting the music platform bring those words to life. The results have ranged from impressive to surprisingly emotional. So when I recently noticed that Gemini now includes a Create Music feature powered by Lyria 3, I knew exactly what I wanted to test. Naturally, my official AI test subject made another appearance... My 2nd great-grandfather, Samuel "Sam" Steinman. My Test I actually discovered that this feature has apparently been available since around late February, but I simply hadn't noticed it. I spend far more time in ChatGPT and Claude than I do in Gemini, so this one slipped under my radar. For consistency, I used exactly the same source material I use for many of my AI experiments:
Test #1: No Prompt Required This may be the most beginner-friendly part of the entire feature. I simply selected the "Folk Ballad" template and uploaded Samuel's research profile. That was it. No prompt. No instructions. No songwriting. Anyone could do this. Gemini generated a song automatically. Actually...I generated two different versions, each about 30 seconds long. Version One I was pleasantly surprised. Although short, it actually included accurate information about Samuel's life and sounded pretty good. Version Two This one wasn't nearly as successful. Some basic facts were incorrect, despite using exactly the same uploaded research profile. That's one important reminder when using AI: Always fact-check the output. Wait...Why Was I Only Getting 30-Second Songs?After a little digging, I discovered something interesting. Everything I'd read suggested Lyria 3 was capable of creating songs closer to three minutes long, yet mine kept stopping after about 30 seconds. It turns out there are two different experiences:
The trick? I needed to switch my chat model from the default Flash to Pro before creating the music. Once I did that... Success. Test #2: The Three-Minute VersionNow Gemini produced a full-length song. This version was much more accurate than the second 30-second attempt. The problem wasn't accuracy. It was pacing. Samuel lived a full life. Trying to squeeze seventy years of births, deaths, moves, occupations, marriages, tragedies, and accomplishments into a three-minute song made everything feel rushed. Instead of telling a story... ...it sounded more like a timeline trying to sing. Test #3: Adding One Extra StepThis is where things became much more interesting. Instead of letting Gemini invent the lyrics, I first asked ChatGPT to write a proper folk ballad based on Samuel's research profile. Then I copied those lyrics into Gemini. I selected the same Folk Ballad music style. And let Gemini compose the music. The difference was dramatic. The lyrics flowed naturally. The story unfolded at a comfortable pace. The chorus repeated like an actual folk song. The music fit the lyrics instead of trying to summarize an entire lifetime in a few rushed verses. It sounded... Fantastic. My Overall Thoughts If you're completely new to AI... Gemini's Create Music feature is wonderful. Seriously. You don't have to know anything about prompting. You don't have to write lyrics. You don't even have to know where to begin. Choose a music style. Upload a document. Click Create. Done. That simplicity alone makes it worth trying. However... If you're willing to spend one extra minute creating better lyrics first, the results improve dramatically. For me, the winning workflow became:
Which Version Did I Like Best? Interestingly... My favorite wasn't actually the three-minute version generated entirely by Gemini. I actually preferred the original 30-second clip over Gemini's longer automatically generated song. The shorter version stayed focused and felt more polished. But the clear winner overall was: ChatGPT-generated lyrics + Gemini-generated music. That combination produced, by far, the best result. (I guess ChatGPT is still my favorite all-around AI tool!) Listen for Yourself I've uploaded all three versions to YouTube so you can compare them yourself. You'll be able to hear: I think hearing the differences side-by-side tells the story much better than words ever could. Final ThoughtsOne of my favorite parts of genealogy is finding new ways to tell our ancestors' stories. Sometimes that's through writing. Sometimes through photographs. Sometimes through animation. And... Sometimes through music. Will AI-generated songs replace carefully written family histories? Of course not. But they can add something wonderfully unexpected—a way to experience an ancestor's story rather than simply read it. And if a three-minute folk ballad inspires someone to learn more about the person behind the lyrics... I'd call that a successful experiment. 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.
Google NotebookLM's new Short Video Overview feature transforms genealogy presentations and blog articles into engaging one-minute videos with AI.
Google NotebookLM's New Short Video Overview: A Genealogist's First Look
When Google NotebookLM first introduced Audio Overviews, I was impressed with how easily it could turn research into a conversational podcast. Since then, NotebookLM has continued adding new AI-powered features, and a few days ago another one quietly appeared: Short Video Overview.
Naturally, I had to try it. As many of you know, I enjoy testing new AI tools to see how they can actually help genealogists—not just because they're new, but because they might save time, improve communication, or make family history more engaging. So I spent some time experimenting. My Test
Rather than uploading random documents, I decided to use material I already knew well.
My first test used the PDF of one of my PowerPoint presentations, complete with the speaker notes: Finding Descendants in Your Family Tree NotebookLM analyzes whatever sources you add to your notebook and then offers three suggested topics it thinks would make good short videos. You can also ignore those suggestions and create your own custom topic. I generated several versions, using each option. The first attempt wasn't particularly impressive. The second was noticeably better. By the third version, NotebookLM had created a concise one-minute video that did a nice job explaining Why Genealogists Trace Descendants, one of the suggested topics. It wasn't perfect, but it was certainly good enough to share. Want to see the result? ▶ Watch: "Why Genealogists Trace Descendants" Testing with a Blog Article
Next, I wanted to see whether NotebookLM worked just as well with written content.
This time I uploaded one of my blog articles: 4 Essential Websites for Early California Genealogy Research Again, NotebookLM suggested several possible video topics. I generated several versions, trying each option, until I found one I liked. One that caught my attention was: How to Find Pre-1850 California Ancestors ▶ Watch: "How to Find Pre-1850 California Ancestors"
Testing both presentations and blog articles gave me a better idea of where this new feature shines—and where it still needs some work.
What I Like
After creating quite a few videos, here are my first impressions.
Short and Easy to Watch Each video is only about a minute long. That makes them much easier for viewers to consume than longer educational videos, especially on social media. It Finds Good Talking Points I was pleasantly surprised by many of the suggested topics NotebookLM generated automatically. Sometimes it identified the exact angle I would have chosen myself. Multiple Versions One thing I quickly learned is that you're not limited to a single result. If the first video isn't quite right, simply generate another. Each version is slightly different, and sometimes the improvement is significant. Custom Topics You're not limited to NotebookLM's suggested topics. If you already know what you'd like the video to focus on, you can enter your own custom topic and let NotebookLM build the video around that idea. Where It Still Falls Short
Like most AI tools, the results can be somewhat inconsistent.
Some videos were excellent. Others completely missed the point I wanted to emphasize. That's why I recommend generating multiple versions before deciding whether a video is worth sharing. Another thing I discovered is that the videos themselves can become fairly large files, even for these shorts. Since I wanted to add my website address to each video, I imported them into Google Vids to add a small text footer. That simple edit nearly doubled the file size. Instead of uploading those large files directly, I chose to upload them to YouTube and simply share the links. For me, that's a much more practical solution. Ideas for Genealogists
As I experimented, I found myself thinking beyond presentations and blog posts.
This feature could be useful for creating:
My Overall Thoughts
NotebookLM's Short Video Overview feature isn't perfect, but it's surprisingly useful.
Some videos will miss the mark. Others will capture your content remarkably well. The key is experimenting with different sources, trying multiple generations, and taking advantage of both the suggested and custom topics. For genealogists who already create presentations, write blog posts, or produce educational content, this feature offers another creative way to repurpose the work you've already done. I'll definitely continue experimenting with it, and I'm looking forward to seeing how Google improves it over time. If you've tried NotebookLM's new Short Video Overview feature, I'd love to hear about your experience. Did it capture your content well, or did you have to generate several versions before finding one you liked? More AI in Genealogy
Learn about more AI in genealogy updates, tips, and resources (including more NotebookLM tools), along with other family history and genealogy resources under the AI in Genealogy and Genealogy Resources categories and on my dedictaed Genealogy Resources page.
 Testing Ancestry's new AI-powered "Fill in Timeline Gaps" feature to see how well it enhances ancestor timeline facts Testing Ancestry's New AI "Fill in Timeline Gaps" Feature: My First ImpressionsArtificial intelligence continues making its way into genealogy, and Ancestry has quietly introduced another AI-powered feature that caught me completely by surprise. About a week and a half ago, while I was in the middle of researching one of my ancestors, I noticed something new. As I worked through an ancestor's profile in the Facts view, I saw small "Description" buttons appearing next to some—but not all—of the timeline facts. Curious, I clicked one to see what it was. That led me to Ancestry's new BETA "Fill in Timeline Gaps" feature. Of course, I had to stop what I was doing and put it through a few tests. What Is the "Fill in Timeline Gaps" Feature? When you click one of the new Description buttons, a side panel opens displaying Ancestry's BETA Fill in Timeline Gaps tool.  Ancestry AI Fill in Timeline Gaps Feature- Example The feature uses AI to generate a description for a specific timeline fact. Before generating the text, you're given three options for how detailed you'd like it to be:
It's a pretty simple concept, but one that has the potential to make ancestor profiles much more informative—especially for users who don't normally add descriptions to their timeline facts.  Ancestry AI Fill in Timeline Gaps Feature- Detail Choices Example Why Fact Descriptions MatterMany Ancestry users simply enter a date and place for events like births, residences, marriages, or deaths and move on. While that's perfectly acceptable, the Description field provides an opportunity to add context that helps tell the story behind each event. For example, instead of simply recording a residence, you might note that the family was living with relatives, renting a farm, or appearing in a particular census enumeration district. A birth description might include details taken directly from a birth record, while a military fact might summarize information found in a pension file. Adding these details can make an ancestor's timeline much richer and easier to understand without having to open every attached source. That's exactly why I was interested to see how well Ancestry's new AI handled this task. My First Test The first person I tested was my fourth great-grandfather, Nehemiah Hulet, simply because I happened to be working on his profile when I discovered the feature. I selected the Birth fact and generated all three description options. This test actually impressed me. The AI stayed focused on the birth event itself.
So far, so good.  Ancestry AI Fill in Timeline Gaps Feature- Example 1
My Second Test Produced Very Different Results Next, I switched to my "official tester ancestor," my second great-grandfather, Samuel Steinman, whose tree I've often used to evaluate new genealogy features. Once again, I selected the Birth fact and generated all three levels. This time, however, the results were completely different. Instead of describing Samuel's birth, the AI began summarizing his life.
That wasn't what I expected the feature to do.  Ancestry AI Fill in Timeline Gaps Feature- Example 2
Testing a Residence Fact I decided to keep experimenting. I selected one of Samuel's Residence facts—one of only a couple that displayed the new Description button. This time, the results were much closer to what I had hoped for. The AI focused on the specific residence and even incorporated information from one of the three sources attached to that event. Seeing the AI reference a supporting source was encouraging because I think that's where this feature has tremendous potential.  Ancestry AI Fill in Timeline Gaps Feature- Example 3 A Bit Hit-or-Miss (For Now) After trying the feature on several facts, my overall impression is that the results are currently somewhat inconsistent. Sometimes the AI stays focused exactly where it should—on the individual timeline fact. Other times it drifts into summarizing the ancestor's life rather than describing the specific event. Fortunately, this isn't particularly surprising. The feature is clearly labeled BETA, and beta features exist so developers can identify issues, improve consistency, and refine the user experience before wider release. Where I Think This Feature Could Really Shine As someone who researches professionally, I can currently write these descriptions myself much faster and with greater precision. For me, it's still quicker to manually add information to a fact description than to generate AI text and then edit it. However, experienced genealogists are not necessarily the primary audience for this feature. The majority of Ancestry users are family historians who may not realize they can—or should—add descriptions to timeline facts in the first place. For those users, this tool could become incredibly helpful. If future versions consistently:
My Overall ThoughtsI always enjoy seeing genealogy companies explore new ways to use artificial intelligence, and I appreciate that Ancestry continues experimenting with features that help users better understand and present their family history. Like many beta features, Fill in Timeline Gaps shows promise but still has a few rough edges. At the moment, I'd describe it as somewhat hit-or-miss, depending on the ancestor and timeline fact you're working with. When it stays focused on the specific event, it does a nice job of expanding the information. When it drifts into writing a mini biography for a single fact, however, it becomes much less useful. I'm optimistic that Ancestry will continue refining the feature as more people test it and provide feedback. As with any AI-generated content, remember that it should always be reviewed before accepting it. AI can be an excellent assistant, but it shouldn't replace your own analysis or careful evaluation of the records and sources supporting your research. For now, I'll continue experimenting with Fill in Timeline Gaps, and I'm interested to see how it evolves over the coming months. Have you noticed Ancestry's new AI "Fill in Timeline Gaps" feature yet? If you've tried it, I'd love to hear what you think. Did it stay focused on the individual facts, or did it wander into life summaries like some of my tests? Let me know in the comments! More Ancestry and Genealogy ResourcesLearn about more Ancestry updates, tips, tools, and features and other family history and genealogy resources under the Ancestry.com and the Genealogy Resources categories of my blog and on my dedicated Genealogy Resources page. More AI Tips, Tools, and FeaturesLearn about more AI in Genealogy tips, tools, features, and resources under the AI in Genealogy category.
|
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.