Heads Up -- FamilySearch Record Hints may Produce the Wrong Document Image

It may be difficult to read from the screenshot, but this particular record hand for Xaverio Corsi GQHR-PGR is an example where the image of the record given did not contain his name or entry at all. However, it was possible to find Xaverio by manually searching the records in the collection, one-by-one. 

This is another example of a record hint that was inaccurate. 

Here is a comment from one of my friends about the situation. 

When I check the hints in my Italian tree, The images associated with the hints are never correct. If the system gives me 3 or 4 hints that are duplicates, the 3 or 4 images will all be different and wrong. Most of the time the correct image is in the same book and I can find it with the date but not thanks to AI. For Pellegrinas' son Raffaello, his baptism was on 4th of November 1834, one hints showed me an image from 1832, the other  from 1843 and another from 1871. None for the correct date. When I asked AI about the discrepancy, this is what I got: This link, 3 times offered, shows 3 different pages for the document. It should be 1834, it shows 1832, 1843, 1871...

It should be noted that FamilySearch Record Hints are typically generated through a mix of automated record indexing, traditional automated record-matching algorithms, and probabilistic linking rather than generative AI. Also, AI cannot search the records directly and can only see a record shown on the screen. 

The fact that the Record Hints may not show the corresponding digital record should be a warning to those who use the feature to check the image record. It may also be the case that these Italian records have not been verified. 

Adding Unconnected People to FamilySearch

The reality of the FamilySearch.org Family Tree is that it contains an innumerable number of snippets and partial pedigrees for individuals who are not definitively connected to the main tree. From time to time, as you add people, you will discover that an individual has already been entered. This is how some of the isolated records floating around in the Family Tree universe eventually become anchored to their proper places. FamilySearch provides a specific option for adding these unconnected people.

Before adding an unconnected person, verify they are not already in the Family Tree. While FamilySearch attempts to match records, common names and variations remain challenging for both researchers and the site's search engine. Once you proceed, you will complete a similar online form used for any new entry.

If you decide to add the unconnected person and you plan on looking at the record you created, you may want to record the person's ID number. Also, keep in mind, that you may have just created a duplicate record. 

FamilySearch Oral Histories -- Where are the oral files?

 

https://www.familysearch.org/en/search/genealogies/

There are 1,847,774 oral histories on the FamilySearch.org website as of the date of this blog post. All those oral histories are searchable and are located in the Genealogies section found under the Search menu.The oral histories originate primarily in Africa and the Pacific Oceania But there are numerous additional locations scattered through the collections.

There are more oral histories if you click on the arrow at the right side of the screen.

Records are gathered through targeted collection efforts, field projects, and direct user submissions. Submissions often include details regarding interviewees, foundational ancestors, specific regional locations, and tribal or clan names.

Field workers and researchers conduct recorded audio and video interviews with community elders and family historians. These conversations capture spoken lineages, traditional histories, and personal narratives in the local language. FamilySearch preserves the original digital audio files to retain the authentic voices, songs, prayers, and cultural expressions of the speakers. FamilySearch also processes the contents of these interviews to construct searchable pedigree structures and family trees, making oral records discoverable alongside traditional historical documents.

The Oral Histories projects are ongoing. More oral histories will be made available over time. 

RootsTech 2027 Class Preview

 

https://www.familysearch.org/en/rootstech/schedule?cid=EM-00065414&lid=o0pvp9nxmuo7

The upcoming RootsTech RootsTech 2027 conference, scheduled for March 4–6, 2027, invites family history enthusiasts from around the globe to gather both online and in person at the Salt Palace Convention Center in Salt Lake City, Utah, under the guiding theme of celebrating the joy of connection and discovering the stories that matter most.

For those participating from home, the virtual experience is entirely free and grants access to over 200 new online sessions translated into more than 20 languages, inspiring keynote addresses, virtual networking with fellow attendees, and an on-demand learning library available year-round. Meanwhile, attendees heading to Salt Lake City can secure early bird registration for $99 US for a 3-day pass or $69 US for a 1-day pass, unlocking over 225 exclusive in-person sessions, a sprawling Expo Hall featuring more than 200 exhibitors and sponsors, and early previews of cutting-edge family history technologies.

The extensive educational lineup spans a broad spectrum of specialized topics designed to sharpen research skills and break through stubborn brick walls. Attendees can explore dedicated tracks covering Artificial Intelligence in genealogy, DNA research, beginner fundamentals, regional research spanning Europe, Asia, Africa, Latin America, and beyond, as well as specific record types, methodology, archiving, and preservation. In addition, the event features specialized Latter-day Saint sessions, including uplifting Family Discovery Day broadcasts and Temple and Family History leadership instruction.

If you are traveling to Salt Lake City for the conference, I strongly recommend reserving a room right away. With the popular Plaza Hotel now gone, nearby downtown accommodations are in higher demand and booking up faster than usual.

Using the New AI Assistant GAIA on MyHeritage

 

https://blog.myheritage.com/2026/11/introducing-gaia-myheritages-groundbreaking-genealogy-ai-agent/

Quoting from the above blog article:

GAIA is powered by agentic AI, meaning that it can plan and carry out multiple connected tasks to achieve a goal. Unlike general-purpose AI platforms like ChatGPT, Gemini, or Claude, GAIA is built specifically for genealogy. It approaches research like a professional genealogist, using established research methods to evaluate evidence, cross-check information, and assess possible connections. For example, it treats information from other users’ family trees as less reliable clues to investigate rather than as established facts. GAIA presents the supporting evidence, distinguishes between well-supported findings and uncertain possibilities, and indicates its confidence in the results.

Now let's look at what it can do with a challenging end-of-line problem that has been around for a number of years. 

This screenshot shows one of my direct line, remote ancestors on my MyHeritage family tree. Garrard Morgan born in 1755 has a son and a grandson, both named Garrard Morgan. This has been an entry in the FamilySearch.org Family Tree, since the Family Tree went online. Until recently, there were many more generations of speculative and inaccurate ancestry attached to this person. Some time ago, I detached all the inaccurate individuals to clean up the entries. 

On MyHeritage, I already have a long list of Smart Matches (the green dots on the individual's colored accent on my MyHeritage family tree). Smart Matches are connections to other users' family trees who are related to me on MyHeritage. The brown dots indicate a possible source record. However, a quick search shows that the source cited is a user-contributed entry in another family tree which was the reason for cutting off the false lineage on FamilySearch.org. So, FamilySearch.org and MyHeritage.org cannot automatically find any additional sources for Garrard Morgan b. 1755. 

I opened Garrard's profile page on MyHeritage. MyHeritage already has seven sources listed. Now let's see what GAIA can do. 

I clicked the Research this person at the top edge of this screenshot and then clicked on the Research Agent Suggestions to Start Research.

GAIA begins to analyze the existing information. 

I got an extremely detailed analysis of what has already been done. It is apparent that GAIA is not only familiar with the details from MyHeritage, but also the records and tree data available on FamilySearch. The initial research begins by focusing on Elizabeth Milton, Garrard Morgan's wife. 

I could go on with the results of the research, but at this point, it becomes extremely lengthy. The conclusion is that although there are a lot of mentions on other family trees and in copied records about this family, there is very little documentary evidence. 

GAIA immediately starts suggesting looking at original records in Goochland County marriage bonds and begins the process of searching the records. The conclusions and information provided by GAIA are extremely pertinent to doing any further research. 

To avoid making this blog post much longer, I suggest that you try using GAIA for yourselves.

Looking at Record Hints between the Big Three Genealogy Family Tree Websites

 

FamilySearch.org, Ancestry.com, and MyHeritage.com all provide record hints. Over the past few years, these matching systems have increasingly incorporated artificial intelligence. I use all three websites daily for genealogical research, and I have definite opinions regarding the accuracy, availability, and overall usefulness of their hints. These observations are not based on a formal study; they reflect my personal experience and methodology.

Each of these massive websites hosts its own unique collections, and hint generation naturally depends on the records each platform holds. These collection differences are among the most influential factors when judging utility. Because I am familiar with all three, I rely on each for its specific strengths. This diversity makes direct, 1-to-1 comparisons tricky—each platform is uniquely valuable in its own right.

Both Ancestry and MyHeritage offer an abundance of immediately actionable record hints (Record Matches on MyHeritage). When working on either platform, one could spend nearly full-time simply evaluating and attaching quality matches. FamilySearch.org remains the outlier. When adding a new person to the FamilySearch Family Tree, you might receive a trickle of hints, but more often the system seems to wait for you to build out the profile before suggesting relevant records. Because of this lag, I typically do the heavy lifting on Ancestry or MyHeritage first. Once I transfer that verified data over to FamilySearch, hints finally begin to populate—though they often simply mirror the records I just added from the other sites.

Ancestry and MyHeritage deliver hints seamlessly. On Ancestry, AI increasingly surfaces potential tree extensions and leaf hints that are generally well-supported and helpful, though complex or conflicting lines can still trip them up. MyHeritage’s Record Matches have consistently been among the most dependable, often capable of driving an entire line's research on their own.

FamilySearch has placed its AI-assisted research tools front and center. However, these AI-generated hints and suggestions can be deceptively tricky, frequently leading researchers into messy genealogical quagmires. Unwary users risk accepting these suggestions without proper source verification, quickly injecting errors into a shared tree.

I encountered a clear example of this recently with a FamilySearch AI-assisted suggestion. The tool suggested a spouse for an individual in England whose existing profile showed siblings born across five widely scattered locations—a classic red flag that the family grouping was already suspect. Accepting the AI recommendation at face value would have compiled bad data on top of bad data.

AI can and does make mistakes. Evaluating historical context, geographic plausibility, and family structure should never be left entirely to an algorithm. Future iterations of these tools will undoubtedly improve, but for now, everyday researchers need to approach AI-generated suggestions with healthy skepticism and rigorous verification.

Can AI Fix the FamilySearch Family Tree -- Part Two Concerns and Challenges

 

The first big question is whether AI can actually improve the quality of the massive FamilySearch.org Family Tree, and whether it can consolidate and search the scattered record collections across the website. FamilySearch currently maintains eight distinct record collections that are either searched individually or, at best, appear together in only one or two combined queries.

Here are the eight primary search areas under the "Search" tab:

• Records -- The core portal for searching traditional indexed records, currently supplemented by computer-indexed records that are increasingly AI-assisted.

• Full Text -- An AI-powered search (currently in FamilySearch Labs) that indexes every word in processed documents and generates transcriptions alongside the digital images.

• Images -- A vast archive of browse-only digital images, largely unindexed and gathered by FamilySearch camera crews around the world.

• Genealogies -- A diverse aggregate of unrelated databases, lineage collections, oral genealogies, and contributed family trees.

• Catalog -- The comprehensive bibliographic guide to the Family History Library's collection, indexed using traditional library methods at the collection or roll level rather than the individual record level.

• Books -- A collection of digitized family histories, local histories, and periodicals that are searchable full-text, word-for-word.

• Cemeteries -- A dedicated database of burial grounds and individual headstones searchable via the Cemeteries interface.

• Newspapers -- A historical newspaper database indexed for full-text search, provided through a partnership with NewspaperArchive.com.

It is obvious that AI can perform remarkable feats—particularly in automated transcription, paleographic deciphering, translation, and surrogate search. A key question, however, is whether AI is reliable enough to replace FamilySearch's traditional catalog and query systems, tools built on decades of painstaking volunteer indexing.

Full-text search can surface ancestral records that never made it into traditional field-indexed collections. However, it currently covers only a small percentage of total holdings, and there is no simple way to track its overall impact across the other major collections. While icon badges in the Catalog indicate certain microfilms or DGS folders that have been processed by Full Text, the remaining collections offer few clear indicators of inclusion.

If FamilySearch eventually applies full-text AI search across the vast majority of its holdings, will traditional searches—such as the Historical Records Collection and the Catalog—become obsolete? Furthermore, could full-text retrieval be paired with specialized AI agents capable of actively evaluating and contextualizing search results against existing Family Tree profiles? Ultimately, will AI agents assist in researching all the records on the FamilySearch website?

The AI technology answer all three questions with a "yes" is available today. The biggest challenge is processing the billions of records on the FamilySearch website and then redesigning the website to take advantage of the complete Full-text search capabilities. 

The results would then be similar to what is currently done on the Ancestry.com and MyHeritage.com websites. For example, MyHeritage.com has for years provided highly accurate Record Matches that search virtually all the pertinent records on the website in 42 languages. Also, Ancestry.com has AI assisted searches that suggest the next individuals on many of the end of lines. 

I guess the last question is how fast can FamilySearch start implementing the programming to solve the questions?