Building Your Family Tree with AI (2026)
How to rebuild a 5-generation family tree with AI assistance. The step-by-step method: from family interviews to animating ancestor portraits.
AI & Technology Writer, Incarn
In short
AI doesn't search archives for you, but it speeds up deciphering them. Method: family interviews first, then FamilySearch + Geneanet for records, ChatGPT or Claude to transcribe manuscripts, regional archives for gaps, and finally the ancestor portraits worth animating.
TL;DR: 5 steps, from family interviews to ancestor portraits
AI doesn't search archives for you. What it does: transcribe in seconds a record that could take you hours to decipher, analyze historical context, and formulate the right archive search queries. The method: interviews first, FamilySearch + Geneanet for records, ChatGPT or Claude for difficult manuscripts, regional archives for gaps. Then look for portraits among the ancestors you find, and animate one with Incarn.
Take a typical starting point. Say your great-grandfather was a blacksmith in a village of 600 people in the Corrèze region of France. You know that, and nothing else. Not his own father, not his wife's maiden name, not where the family came from before the 19th century.
When the records are well preserved, a case like this can realistically be traced back five generations over a few weeks of evenings: dozens of named ancestors, perhaps a portrait or two recovered from digitized archives or family boxes.
AI helps. Not by searching on your behalf: AI can't do that yet. But by deciphering what you find, explaining what you don't understand, and speeding up the slowest steps.
Here's how.
What AI can (and cannot) do for your genealogy
A clarification before you invest your time.
AI cannot: access archive databases (Ancestry, FamilySearch, and Geneanet have their own interfaces), find your ancestors by name, or guarantee the accuracy of what it says about proper names or dates.
AI does well: transcribing 19th-century handwritten records into readable text, interpreting historical context ("what did 'cultivateur' mean on a French marriage certificate in 1870?"), formulating adapted queries for archive search engines, translating old French or ecclesiastical Latin, and connecting information when you're stuck.
AI is an analysis assistant, not a genealogy search engine. With that distinction clear, it's genuinely worth the effort.
Step 1: Interview the elders before it's too late
This is the most urgent step, and the least technological.
Your grandparents, great-grandparents still living, aunts and uncles over 70: they are human archives with no digital version and no backup system. Every death without a recorded interview means an entire branch of the tree disappears.
Before any search engine, pick up the phone. Ask for parents' first names, home villages, occupations, and the stories told at Christmas dinner. Take notes or record with their permission.
In the Corrèze example, an 84-year-old great-aunt might give you the full name of the blacksmith's father, his village, and the fact that the family moved during the Occupation (which would explain why the Corrèze records go silent after 1942). One hour of conversation that nobody will be able to give you later.
ChatGPT can then structure these notes into a table: individuals, approximate dates, places, known sources. Not magic, but useful for not losing anything at the start.
Step 2: FamilySearch and Geneanet for the first records
FamilySearch is free, with no mandatory registration for basic consultation, and indexes tens of billions of civil records. It's the logical starting point for 19th-century France, as well as for US, UK, and European genealogy more broadly.
The method with AI:
- Search for the record on FamilySearch or on a regional archive portal
- Download the record image
- Send the image to ChatGPT or Claude with the prompt: "Transcribe this handwritten record into modern language. Mark uncertain passages with brackets."
- Verify the flagged passages before adding them to your tree
The time savings are real: instead of deciphering a 19th-century marriage certificate word by word, you spend your time checking the proposed transcription.
Geneanet complements FamilySearch for France in particular, especially for trees shared by other genealogists. Useful for finding branches a distant cousin has already traced. One essential caution: shared trees contain errors. Always verify the source record, never a copy from another tree.
Step 3: Deciphering old records with AI
This is where AI helps the most.
Records from before 1800 are in old French or Latin, with abbreviations, variable spellings, and legal formulas that have long since disappeared. A baptism record from 1743, in a provincial parish register, can remain illegible for hours if you're not familiar with the handwriting style.
The method: send the image to Claude or ChatGPT. Ask for a transcription and an explanation of the structure: "Who is the father? The mother? The witnesses? What exactly is the event being recorded?"
Ask it to identify roles and names even in ambiguous formulas, and to explain what terms meant in the context of an 18th-century record, which can sometimes change the interpretation of an entire branch.
Atypical regional handwriting or heavily damaged records remain difficult. For complex cases, a guide on deciphering old handwriting with AI covers the advanced techniques.
Step 4: Regional and national archives to fill the gaps
FamilySearch and Geneanet have gaps. Some parish registers haven't been digitized; others are only accessible through regional archive portals. In France, each department runs its own portal. For UK researchers, The National Archives and county record offices play a similar role. For US researchers, state archives and the National Archives hold equivalent collections.
AI is useful here for formulating the right queries.
An example: say you know an ancestor was born around 1820 in a village in the Haute-Loire region. Ask ChatGPT: "How do I search for the birth record of someone born around 1820 in Haute-Loire, France? What registers exist, and where are they available online?" A useful answer points you to the civil registers on the departmental archive portal, the corresponding FamilySearch collections, and checks such as whether the commune changed its name, a classic reason why earlier searches find nothing.
Step 5: Finding and animating ancestor portraits
This is the step people tend to underestimate.
Among the ancestors you find, a few may have photos in digitized archives or in family boxes. Conscription photos from the early 20th century are a goldmine in France: military enlistment registers sometimes include front-facing portraits alongside physical descriptions. Similar resources exist in many countries through military records and census photographs.
Picture a great-great-grandfather in his conscript uniform, 1908, on cracked sepia. With Incarn, which we make, that portrait becomes a few seconds of video where he turns his head slightly.
Now imagine showing it to a relative who has only known this man through a family anecdote (he refused to flee during the war and stayed to work his forge). The first question will probably be who in the family he looks like.
More than 12,000 photos have already been animated on Incarn: grandparents, soldiers, wedding portraits. The animation is powered by Seedance 2.0 (a video AI model by BytePlus), rendered in under 2 minutes. The trial is free (1 credit offered at sign-up), then €1.99 per animation.
AI tool comparison for each step
| Step | Recommended tool | Free? | Best for |
|---|---|---|---|
| Structuring interview notes | ChatGPT | Yes (basic version) | Organization and clarity |
| Finding civil records | FamilySearch | Yes | 19th century, France and beyond |
| Transcribing a handwritten record | ChatGPT | Yes | 19th-century cursive |
| Transcribing a record in Latin | Claude | Yes (usage limits) | Complex documents, old French |
| Cross-referencing existing trees | Geneanet | Free (consultation) | Already-traced branches |
| Animating an ancestor portrait | Incarn | 1 free credit, then €1.99 | Portraits, family photos |
How long does this method take?
Honestly, it depends on the complexity of your tree and the archives available.
For a case like the Corrèze example (19th century, well-documented records), a rough budget might look like this:
- Interviews and initial notes: around 4 hours
- Searching and transcribing records with AI: 8 to 10 hours, in one-hour sessions over a few weeks
- Verifying and documenting sources: around 3 hours
That's an estimate, not a promise: damaged registers, a name change or a missing parish can double it.
AI doesn't do the work for you. It reduces the time spent deciphering manuscripts and figuring out where to look, which is often a large share of the time in active research.
If you have an old photo in a drawer and want to start there, Incarn is accessible without prior registration for the first trial.
Frequently asked questions
Can AI build my family tree automatically?
No. Current AI tools (ChatGPT, Claude, Gemini) do not connect to archive databases. They analyze what you bring to them. The research remains human; the transcription and analysis, less so.
Which AI tool should I start with?
ChatGPT (free version) covers most common needs. Claude is a useful second opinion for Latin texts and complex documents.
Is FamilySearch really free?
Yes. Basic consultation is free without a subscription. Some advanced features require an account, which is also free. It's the logical starting point for 19th-century archives, and a strong resource for many other countries as well.
I have records in Latin. Can AI translate them?
Yes, with caveats. Claude and ChatGPT generally handle standard ecclesiastical Latin from baptism, marriage, and burial records. Very specific abbreviations or atypical regional handwriting cause more problems. Always verify uncertain passages with a secondary source or a professional genealogist.
AI & Technology Writer, Incarn
Thomas covers AI and machine learning applications for creative tools. Former research engineer with a focus on computer vision and video generation.