Every family historian eventually inherits a cold case.

Mine begins with Martha Elizabeth Savage née Evans, a woman whose life ended in tragedy and whose story now asks to be handled with care, evidence, and compassion. This is not a case of crime in the usual sense. There is no villain to expose, no neat solution to deliver, no dramatic confession waiting in the archive.

Instead, this is a quieter kind of investigation.

It is the search for a woman behind a record of death. It is the attempt to understand what can be known, what remains unknown, and how a genealogist can investigate a painful family history without turning suffering into spectacle.

This first entry in my new AI Case Notes series opens the file.

Case File 1: Remembering Martha Elizabeth Savage

Person of Interest: Martha Elizabeth Savage née Evans
Known events under investigation: Marriage in 1899, birth of son in 1904, admission to Carmarthenshire Lunatic Asylum in 1907, death by suicide in 1918.
Research focus: To investigate Martha’s life, death, family circumstances, and historical context using genealogical evidence, careful source analysis, and AI-assisted research methods.
Case status: Open
Emotional classification: Sensitive family history

At this stage, I am treating every detail as evidence to be tested, not a story to be embellished. Where a record confirms a fact, I will say so. Where a detail is uncertain, I will mark it as unknown. Where the evidence is incomplete, I will resist the temptation to fill the silence with imagination.

That is the first rule of this investigation: Martha deserves truth, not invention.

The Central Mystery

The central question is not simply “How did Martha die?”

A death record answers that in a formal sense. But family history asks wider, more human questions:

• Who was Martha before the final record?

• What family, social, economic, and emotional pressures surrounded her?

• What do the surviving records say?

• What do they refuse to say?

• Where are the newspaper reports, inquest records, burial records, institutional records, or family documents that might add context?

• How can I write about her life and death with dignity?

This case is not about reducing Martha to the manner of her death. It is about restoring her place in the family story.

The Case Lead: Carole McCulloch

As the AI-skilled genealogist, I aim to keep the investigation focused – to hold the central research question in view and prevent the story from wandering into speculation. This case study will be referenced in my online courseware as an example of the AI Squad approach.

Case Lead prompt:
“Act as a genealogical case manager. Help me define the research question, separate known facts from assumptions, and identify the next best research steps.”

The AI Squad

For this investigation, I will be working with what I call my AI Squad — not as a replacement for genealogical methods, but as a set of research assistants, each with a clearly defined role.

1. The Timeline Analyst: Gemini

The Timeline Analyst builds a chronological reconstruction of Martha’s life from the records. This helps identify gaps, contradictions, and turning points. The output can be structured as a data table.

Timeline analyst prompt:
“Using only the facts I provide, create a chronological timeline. Include columns for date, event, place, source, evidence value, and unresolved questions.”

2. The Source Critic and Evidence Locker: NotebookLM

The source critic interrogates each record as a witness. Who created it? Why? Who supplied the information? How reliable is it? The output can be structured as a Report.

Source critic prompt:
“Analyse this record as genealogical evidence. Identify the informant where known, assess reliability, and explain what the record proves, suggests, or does not prove.”

3. The Social Historian: Perplexity

The social historian helps place Martha in her historical setting. This may include women’s lives, marriage, motherhood, health, bereavement, housing, religion, work, and social expectations. The output can be structured as a Locality Guide.

Social historian prompt:
“Provide historical context for this place and period, but do not infer Martha’s personal motives unless supported by evidence.”

4. The Illustrators: Gemini or ChatGPT

Gemini can create illustrations for scenes to be incorporated into the written story. I will prompt the creation of images from the context of the story using engineered prompts. Prompt Cowboy helps structure strong descriptive prompts for these.

Illustrator prompt:

“Create an infographic that illustrates this first scene in my story. [paste description] Use a detective genealogist style with appropriate icons and photo realistic imagery related to the early 1900s in Pembrokeshire, Wales.”

Note: Chat GPT creates the opening images for each of my posts in this series.

5. The Writing Editors: Claude Chat or Cowork

The writing editor helps shape the final story so it reads like a detective case study while remaining accurate and respectful.

Writing editor prompt:
“Revise this genealogy case study in the style of thoughtful historical non-fiction with a light detective structure. Do not add facts.”

6. The Prompt Engineer: Prompt Cowboy

Prompt Cowboy enables the creation of strong, meaningful prompts from your initial input. These can be stored in the folders of the Prompt Cowboy Library.

The Evidence Locker: NotebookLM

The next task is to gather the evidence already known and place it into a structured case file. I have set up the Pembrokeshire: A Savage Family History Hunt Notebook as the evidence locker.

The evidence locker may include the following items and more as the research continues.

Birth or baptism record, marriage record, census records, death certificate, burial record, newspaper reports, coroner or inquest records, probate or administration, family stories or notes, and family group sheets.

These are uploaded as ‘Sources’ see the left-hand panel of the ‘Notebook’.

The Rules of the Investigation

Before I begin, I need rules.

Rule 1: No guessing: If the evidence does not tell me something, I will say unknown.

Rule 2: No single-record conclusions: One record may provide a clue, but the case will rest on a pattern of evidence.

Rule 3: No sensational language: Martha’s death will not be treated as drama. The detective structure is a storytelling device, not an excuse to turn grief into entertainment.

Rule 4: Context is not motive. Historical context may help me understand the world around Martha, but it cannot tell me exactly what she felt unless a source says so.

Rule 5: The woman comes before the mystery: Martha was not a “suicide case”. She was a daughter, a wife, a mother, a neighbour, a worker, a churchgoer, a friend, or a member of a community. Some of those roles may be documented. Some may remain unknown.

Opening Questions

These are the questions I will carry into the next stage of the investigation:

1. What are the earliest confirmed records for Martha Elizabeth Evans?

2. When and where did she become Martha Elizabeth Savage?

3. Who was present at key life events as witnesses, informants, neighbours, or household members?

4. What does the death certificate actually say?

5. Was there an inquest?

6. Did newspapers report the death?

7. Where was Martha buried?

8. What family members were nearby at the time?

9. What was happening socially, economically, and locally around her?

10. Which parts of her story can be proved, and which must remain unknown?

Case Note: Why AI Belongs in This Investigation

AI will not solve this case for me.

It cannot replace original records. It cannot decide truth from imagination. It cannot know Martha’s mind. It cannot turn an unsourced family story into evidence.

But it can help me think.

It can help me organise a timeline, test a hypothesis, generate search strategies, compare conflicting records, ask better questions, and write with more care. It can act as a research assistant, a sceptical colleague, a social historian, and an editor—provided I remain the genealogist in charge.

That is the heart of this series.

Not “AI tells the story.” But rather:

AI helps me investigate. Evidence helps me decide. Ethics helps me write.

Where the Case Goes Next

In the next instalment of The Savage Family Mysteries, Part 2 of 5, I will begin calling the witnesses.

The first witnesses will be the records themselves: civil registrations, census returns, marriage evidence, death documentation, and any surviving newspaper or inquest material. I will ask what each source proves, what it merely suggests, and where it may mislead me.

For now, the case file is open.

Martha Elizabeth Savage, née Evans, has stepped out of the shadows of a single tragic record and into the fuller work of family history investigation.

The trail begins here.

Lisa Rex of Ancestor Audit is exploring her own research challenge case across the same five weeks. You can follow along at Lisa’s AI Case Notes.

Ancestor Audit

We will be posting on Tuesdays and Thursdays throughout July, and we’re both excited to explore where our Substack Exchange will take us.

Share NextGenGenealogy

There is something quietly thrilling about a One Place Study. Unlike traditional ancestor-focused research, which follows a surname across time and geography, a One Place Study says: "I will stay here." I will get to know this street, this village, this parish — and let the people find me.

My current obsession is South Molton Street in Mayfair, London. It runs barely 400 metres between Oxford Street and Brook Street. Yet, across the two census years of 1881 and 1891, it was home to dressmakers from Paris, tailors from Germany, a family of professional nurses, a circus actress, the librarian of King’s College, and more than a few women quietly running small empires from the floors above fashionable shopfronts.

To research all of this, I did something that I suspect will become increasingly normal in genealogy: I used two AI tools — Google Gemini and Anthropic’s Claude —, and I gave each of them a different job. The results surprised me, delighted me, and absolutely reshaped how I think about AI-assisted research.

So let me pull up a chair and walk you through exactly what I did, what worked beautifully, and what I’d do differently next time.

* * *

What is a One Place Study, and why does it need AI?

A One Place Study (OPS) is a systematic investigation of all the records relating to a specific geographic place over time — every birth, death, marriage, census return, trade directory, map, and newspaper story you can find. The Society for One-Place Studies has a wonderful community around this, and if you’ve never explored their work, it’s well worth a look.

The challenge is the sheer volume of data. South Molton Street alone contains over 400 named individuals across the two census years I’ve examined so far, spread across 63 properties. There are occupations to categorise, birthplaces to map, family patterns to identify, and narratives to weave between the dry columns of Victorian bureaucracy.

This is exactly the kind of work where AI becomes not a shortcut, but a genuine research partner.

“The census gives us the bones. The AI helps us find the flesh — the patterns, the stories, the questions we didn’t even know to ask.”

— Personal research notes, South Molton Street OPS

Why two AI tools, not one?

I came to this arrangement quite naturally. I had been using Google Gemini for a while as a broad thinking partner — it’s brilliant at brainstorming, generating frameworks, and producing structured output like tables and templates. Then I began working with Claude for more intensive document analysis and narrative work, particularly when I started uploading census images directly. Plus, my most used AI tool this year, NotebookLM, has inspired me to generate infographics and slide decks to illustrate my narratives.

What I discovered is that they have genuinely different strengths. Rather than choosing one and being frustrated by its gaps, I’ve learned to use them the way I’d use three specialist colleagues: I brief one, then the others, and compare what comes back.

Gemini’s Strengths (the 'Big Picture' planner)

• Generating project frameworks and CSV templates

• Brainstorming narrative angles and themes

• Producing structured research summaries

• Helping design WeAre.xyz article structures

• Drafting social media captions and descriptions

• Broad historical context (e.g. Charles Booth maps)

Claude’s Strengths (the 'Deep Dive' archivist)

• Reading and transcribing census images directly

• Cross-referencing data within a project

• Identifying puzzles and discrepancies in records

• Crafting layered, emotionally resonant narratives

• Handling ambiguous or partially legible handwriting

• Maintaining context across long research conversations

NotebookLM’s Strengths (the ‘Fine Tune’ artisan)

• focussed only on the data you give it for analysis

• talented in generating relevant infographics and slide decks eg hero images, story images, and teaching slides

• crafting a meaningful in-depth conversation about your sources

Think of Gemini as the researcher who’s brilliant at setting up systems and big-picture context, and Claude as the one you call when you’re deep in the archive with a magnifying glass, trying to figure out whether that name really is “Pitman” or “Pateman.” Consider NotebookLM as your artist with specific design skills to create the visuals to illustrate your story.

* * *

How I structured the workflow: a step-by-step guide

Here is the approach I followed for South Molton Street — and that you can adapt for your own One Place Study, whatever the location or era.

Start with Gemini: build your framework

Before touching a single census image, I asked Gemini to help me design a consistent article structure for each property on WeAre.xyz, my chosen platform for spatial storytelling. We also created a CSV template with columns for House Number, Schedule, Resident Names, Occupation, Birthplace, Booth Classification, and Trade Category. Getting this scaffold right at the start saved enormous amounts of time later. Gemini is particularly good at this kind of structured design work.

Use Gemini for historical context

I asked Gemini to help me identify and interpret the Charles Booth Poverty Map classification for South Molton Street (it was “Red” — well-to-do, middle class) and to locate the relevant Police Notebook walk (B354, Inspector Hunt, 17 May 1898). Gemini helped me understand what the Booth data meant in context, and what questions to carry into the census analysis. The handwritten ‘notes’ in the Police Notebook walks revealed a vivid picture of the street, including sights, smells and sound. This contextual layer made every subsequent record feel richer and more grounded.

Move to Claude: upload your images

With the framework in place, I began uploading the actual census folio images directly to Claude — the 1881 returns (RG 11/91) and the 1891 returns (RG 12/67). Claude can read Victorian handwriting with impressive accuracy. For any word it can’t make out with confidence, I asked it to use [unknown] or [?] notation rather than guess — a discipline that keeps your transcript honest. Always work through the images methodically, page by page, confirming transcriptions as you go.

Note: I trialled the new Claude Opus 4.7 to analyse and extract data from the census data in two batches. Each batch contained about 10 census records. The processing time was lengthy and Opus 4.7 limited it two batches on the one day.

Ask Claude to build comparative tables

Once I had both census years transcribed, I asked Claude to produce a house-by-house comparison across 1881 and 1891. This revealed something I hadn’t anticipated: while actual resident persistence was very low (under 10% of the same people appeared in both censuses), trade persistence was remarkably high. The street kept its identity — luxury fashion, tailoring, millinery — even as its people moved on. That kind of insight is hard to spot when you’re reading records line by line. AI makes it visible.

Ask both AIs for narrative interpretations

This is where the two-AI approach really earns its keep. After Claude had identified key patterns, I took those findings back to Gemini and asked: “What narrative themes emerge from this data?” Gemini gave me broad thematic frameworks — The Widow’s Economy, The Feminisation of Trade, The Persistence of Place. I then brought those themes back to Claude and asked it to find specific individuals who embodied each one. The combination is powerful: big-picture framing from one, human-scale stories from the other.

Solve the puzzles together

Every census has its mysteries. For South Molton Street, one of the most satisfying was what I came to call “The Pateman/Pitman Puzzle” at No. 9. The family appeared under one surname in 1881, and a different surname in 1891, but Claude’s cross-referencing of the children’s given names, ages, and birthplaces proved it was the same family. Having an AI partner who can hold all the variables in mind simultaneously — across multiple uploaded images — makes this kind of detective work genuinely tractable.

Export your data and pin your stories

With a clean, compared dataset, I exported the CSV (formatted during Step 1) and began uploading to Google Drive. Each property becomes an interactive pin on the map, linking the shopfront business to the residents above, and the residents to their broader story — where they came from, what they did, who they lived with. Gemini helped me draft the copy for each pin; Claude helped me sense-check the details against the primary records.

* * *

The discoveries that stopped me in my tracks

Let me be honest with you: I started this project expecting a tidy exercise in data management. What I got was something far more alive.

The women who held everything together

Perhaps the most striking pattern to emerge from both census years was the quiet economic power of women — particularly widows. At No. 4, Mary Ann Harrison managed a lodging house after her husband’s death, and by 1891 she had shifted her boarders upmarket, attracting a better class of professional tenant. At No. 55, Harriet Adams ran a lodge house for a community of trained nurses. At No. 62, Ellen Warren headed a household of dressmakers, saleswomen, and milliners from across the country and beyond.

These women don’t appear in the history books. They’re not mentioned in the Booth notebooks or the trade directories. But there they are, in column 7 of the census folio, listed as “Head” — one of the smallest words that carries the largest weight.

Research Discovery

By 1891, No. 26 South Molton Street had become home to 10 trained nurses — the most densely occupied house on the street. This represented a significant institutional shift in a building that a decade earlier had housed a printing family. Neither Gemini nor Claude invented this: the census says it plainly. But AI made it visible by surfacing it within a comparative analysis across 63 properties.

The missing school

In 1881, No. 53 South Molton Street was home to Nathaniel Denton, School Master, and the Hanover District National School. By 1891, the building was recorded as “Uninhabited.” An institution that had served the community for years had simply... closed. Or moved. The census doesn’t say why. That’s where the next phase of research begins — and where the narrative questions become as important as the data.

The international community is hiding in plain sight

When Claude compiled the birthplace data across both census years, a vivid picture of Victorian cosmopolitanism emerged. Residents on South Molton Street had been born in France, Germany, Italy, Greece, Russia, Sweden, Switzerland, Australia, the United States, and British Guiana, alongside the expected range of English, Scottish, Welsh, and Irish birthplaces. This was not an isolated street; it was woven into a global economy of fashion, trade, and service.

* * *

Key findings at a glance: 1881 vs 1891

* * *

Practical tips for your own AI-assisted One Place Study

🗂 Build the scaffold first

Before you upload a single document, use an AI to help you design your data columns, article structure, and filing system. Changing your schema halfway through 63 properties is not a good afternoon.

📜 Use [unknown] notation honestly

When uploading handwritten images, instruct your AI to use [unknown] or [?] for any word it is uncertain about. Never let the AI guess a name or occupation and present it as fact. Accuracy is everything in genealogical research.

🔁 Cross-brief your AIs

Don’t silo your tools. Take Claude’s micro-discoveries back to Gemini for big-picture framing. Take Gemini’s thematic frameworks back to Claude for human-scale illustration. The conversation between them — mediated by you — is where the richest insights live.

🗺 Always anchor data to a place

A One Place Study is, at its heart, a spatial story. Use a platform like WeAre.xyz that lets you pin records to a map. The physical street is not just a backdrop — it is the argument. Every data point should be tethered to its address.

Note: consider joining us for the next course in Preserving Family History Archives with WeAre.xyz

📅 Plan your time layers from the start

I began with 1881 and 1891. But from the very first session, I asked both AIs to flag anything that would support a 1901 follow-up analysis. Building temporal continuity into your research from the beginning means you’re never starting from scratch as you move forward decade by decade.

* * *

What comes next for South Molton Street

I am not done with this street. Not by a long shot. Come and see what I am building for the South Molton Street OPS. This is the start of a large project that will take some time, but with my AI assistants I can speed up the process.

My aim is to build this OPS out by spotlighting some of the most interesting residences and how their households changed between 1881 and 1901.

The next phase will be the 1901 census — and I’m genuinely curious whether any of the anchor families survive into the Edwardian era. Did the Hanover National School reopen somewhere else? Did the nurses at No. 26 stay together as a community? And what happened to the dressmaking trade as the century turned and fashion began its long acceleration toward the modern?

These are not questions that AI can answer on its own. But AI can help me hold all the threads simultaneously, see patterns I’d miss alone, and shape what I discover into stories worth reading.

That feels like a genuinely new kind of partnership in genealogy — and one I think we’re only just beginning to understand.

Is there a street, a village, a parish in your research that deserves this kind of sustained attention? What would it look like to stay in one place long enough to really know it?

I’d love to hear what your place is. Drop it in the comments, or find me in the Ancestry in the Age of AI community. Let’s figure out together what AI can help us see.

Try it for your own research

Whether your place is a London street, a Yorkshire village, or a rural Irish parish — the workflow above adapts. Start with Gemini to build your framework. Move to Claude to read your documents. Let the stories find you.

#OnePlaceStudy #AIGenealogy #EssentialGenealogy #SouthMoltonStreet

How I Stopped Losing 4 Hours a Day (And Found My Ancestors) Instead)

A 4-step “Operating System” to turn Gemini into a precision research tool without the distraction.

Share NextGenGenealogy

The 60-Second Recovery: Reclaim Your Research Time

If you only have a minute, here is how to stop drifting and start finding:

• The Anchor: Never open an AI tool without a one-sentence “Scope Anchor” in place. Write it on a Post-it note and stick it to the screen. Or add it in print on your desktop diary. (e.g., “Extract dates from the 1880 Census for Jacob Miller”). If the AI suggests a tangent, ignore it.

• The Guardrails: Prime your AI with a “Forensic Genealogist” persona. Force it to use tables or dot points and the Genealogical Proof Standard. Give it clear instructions about the format of the output.

• The Split-Screen Setup: Keep your research log on the left and the Gemini side panel on the right. Use the @Google Drive command to query files so you never have to leave the tab.

• The 5-Turn Rule: If the task isn’t solved in 5 prompts, stop. You are either over-complicating it or using the wrong tool. Start a new chat!

• The Hard Exit: Once your scope anchor is met, close the tab. Record your “Next Step” in your log and walk away.

Split Screen View You Tube Video
Split Screen Workflow You Tube Video

Closing Tip

I would love to hear about your ‘anti-rabbit-hole strategies’!

“What is your biggest ‘rabbit hole’ trigger when using AI for family history? Share your distraction stories—and how you fought back—in the comments below.”

Leave a comment

For many genealogists, the sudden rise of AI tools feels like a double-edged sword. On one hand, the potential to analyse records faster is exhilarating. On the other hand, the sheer number of tools—and the fear of “hallucinations” or unethical research practices—can be paralysing.

Is it possible to use AI without losing the integrity of your family history research?

In my latest video, AI Workflow Mastery: From Data to Ancestral Profile, I demonstrate that the answer isn’t just “yes”—it’s that AI, when used correctly, is the key to becoming a truly “Future-Proof Historian.”

Moving Beyond Casual Chatting

Most people treat AI like a search engine—asking a quick question and taking the first answer they get. But in genealogy, “casual chatting” with AI is where mistakes happen.

The secret to success is moving from ad-hoc queries to strategic, repeatable workflows.

In the video, I walk through the process of building a comprehensive ancestor profile—using the example of “Henry Hall”—by integrating specific tools like Perplexity and Notebook LM. By treating the AI as an assistant rather than an oracle, we can synthesise vast amounts of data into a professional-grade ancestral profile, complete with business history, descendant trees, and narratives, all while maintaining rigorous source citations

You can view the profile in progress here.

You can view the biography in progress here.

The Four Pillars of AI Genealogy

To master this workflow, you need a system. My approach is built on four core pillars:

1. The Research Brief: It’s all about prompt engineering. Instead of asking the AI to “write a history,” you provide a structured brief that acts as the parameters for your research, keeping the AI focused on the facts.

2. Workflow Mastery: We dive into repeatable systems—specifically how to handle British records and other archives—to ensure that your process is consistent, no matter which ancestor you are researching.

3. The Golden Rule (Ethics & Integrity): AI is a tool, not a substitute for verification. We cover how to maintain source-based genealogy and ensure that your family stories are grounded in archival evidence.

4. The Horizon: As archives and AI continue to integrate, the possibilities for research are expanding. Understanding how to use these tools now prepares you to leverage the sophisticated archival tools of the future.

Transforming Data into Story

One of the most rewarding parts of the workflow I demonstrate is how to move beyond raw data. We don’t just dump information; we take the research and

• Integrate infographics and visuals into a profile.

• Build a detailed slide deck (using a custom prompt workflow).

• Export and organise these elements into a final, polished media album.

The result is a comprehensive article or presentation that you can actually share with your family, turning dusty census records into a compelling narrative of a life lived.

Ready to Build Your Own Workflow?

AI doesn’t have to be intimidating. Whether you are struggling to understand British record sets or you’re just looking for a more organised way to store your findings, I have resources to help you bridge the gap.

• [Enrol in my free AI Genealogy Starter Campus]: This is designed to help you overcome tech fear and build your first baseline workflow.

• [Join the Essential Genealogy Membership]: Get on-demand training, quarterly masterclasses, and a community of researchers dedicated to doing genealogy the right way.

Don’t let your research sit in a folder. Start building a system that turns your data into a legacy.

Latest workflow: I have become obsessed with infographics and slide decks on NotebookLM.

Subscribe now

1. January: AI Genealogy Starter Campus

- A free course released on January 1 - now has over 50 enrolments. coachcaroleonline.thinkific.com/courses/take/AI-Genealogy-Campus

Note: The bulk of this course was built with assistance from NotebookLM.

2. February: YouTube Playlists

AI Workflows for Genealogy - a Playlist at my YouTube channel - includes 10 short videos.

https://youtube.com/playlist?list=PLjgMLij9U0O1OHuOzZwV3wnekYa7zsN8l&si=VCnwLANudcqDcIiL

Stories for the Ancestral Vault - includes 15 stories of my family research

https://youtube.com/playlist?list=PLjgMLij9U0O0IR6e7-sSQxL4FpXbI4MI1&si=VrZ8shEi7HrqDcs_

The AI Genealogy Revolution - includes 15 video tutorials -

https://youtube.com/playlist?list=PLjgMLij9U0O1ltabkCRHg4WO5S2ofrRs_&si=jhJoIeLBrUWzcGa-

3. March: RootsTech 2026

Preparing - adding online sessions to My Schedule

Experiencing - watching webinars and summarising with Gemini

Reflecting - unpacking new learning from presentations via summaries, syllabus and slides downloads.

Hosting an ‘After RootsTech’ event on Zoom on March 14. Details here: https://www.facebook.com/groups/ancestryintheageofai

4. Latest Project: Tech Tips for Genealogists

I have also been focussed on building a set of Tech Tips for Genealogists that help set them up for success with their browsers, dashboards, tabs, screens and files.

You can access this free 30 Day Challenge here:

https://coachcaroleonline.thinkific.com/products/digital_downloads/tech-tips-30-day-challenge

A new playlist of Tech Tips is beginning here:

Tech Tips for Genealogists 30 Day Challenge

https://youtube.com/playlist?list=PLjgMLij9U0O0NQNW9XS-rOZ8id3owa85A&si=yr0U8G7lkbjPaIUI

Listen to a synopsis of this post created in the NotebookLM Studio.

And now for the AI Workflow!

For many family historians, the “Family Group Sheet” is the backbone of our research. It’s filled with names, dates, and locations—the “who, when, and where.” But the “how” and “why” of our ancestors’ lives often remain trapped behind the dry, tabular data of census returns and certificates.

How do we bridge the gap between a spreadsheet and a story? The answer lies in a new, collaborative workflow using Artificial Intelligence.

By using AI as a research partner rather than a ghostwriter, you can transform fragmented records into a meaningful narrative. Here is the step-by-step method to bring your ancestors into the light.

The Workflow: A Three-Stage Process

Lesson 1. The Harvest (Data Gathering)

Start with your primary database, such as Ancestry. Focus on one individual and gather every scrap of evidence: census records, birth/marriage/death certificates, and burial records.

Data Harvesting & Curation

Before engaging with AI, you must provide the “ground truth” from your research.

• Select Your Subject: Open your family tree (e.g., Ancestry) and focus on a single individual.

• Gather Primary Sources: Download high-quality copies of essential records:

  • Census Records: These provide the “timeline” of their life.

  • Vital Records: Birth, Marriage, Death, and Burial (BMDB) certificates.

Optional AI Data Boost: If using Ancestry, utilize the Listen and Explore AI feature to uncover nuanced details within your records. Save these insights to your ancestor’s focus folder.

Lesson 2. The Analysis (Perplexity)

Upload your .jpg and .pdf records to Perplexity. This AI is excellent at “reading” documents and extracting pertinent facts.

• The Goal: Have a conversation. Ask the AI to identify patterns—like a sudden change in occupation or a family living in separate lodgings. This turns “data points” into “life events.”

Extraction & Analysis (The “Research Assistant” Phase)

We use Perplexity here because of its strength in analyzing uploaded documents and providing citations.

• The Upload: Upload your .jpg or .pdf records (Censuses, Certificates) directly into the chat.

• The Prompt: Start a conversation to extract the “meat” of the records.

  • Example: “Analyze these three census records for Alfred Wright. Identify his occupation changes and residential moves between 1871 and 1911.”

• The Transformation: Ask Perplexity to turn those facts into a rough narrative draft that highlights specific themes, such as “working life” or “social mobility.”

Lesson 3. The Synthesis (Gemini)

Finally, bring your raw narrative draft and your Family Group Sheet into Gemini. This is where the polish happens. Ask Gemini to combine the hard dates of the family sheet with the contextual story from your analysis to create a concise, professional “Life Sketch.”

Synthesis & Polishing (The “Editor” Phase)

Now, move to Gemini to refine the story and ensure it aligns perfectly with your family group data.

• The Context Cloud: Upload two specific items:

  • The Family Group Sheet (PDF) from your database (containing exact dates, parents, and children).

  • The Narrative Draft you generated in Perplexity.

• The Final Prompt: Use a direct, creative prompt to shape the tone.

  • Example: “Combine this Family Group Sheet with the narrative draft. Transform it into a concise, professional ‘Life Sketch’ for a public article. Focus on the transition from artisan to laborer.”

---

The Artist (NotebookLM)

Creating the “Source of Truth” with NotebookLM

Once you have your final narrative and facts, you can use Google’s NotebookLM to act as a specialised historian for that specific ancestor.

• Create a Notebook: Title it after your ancestor (e.g., “Alfred Thomas Wright (1840–1923)”).

• Upload Sources: Upload your final Gemini narrative, the Family Group Sheet, and any key census transcriptions.

  NextGenGenealogy is a reader-supported publication. To receive new posts and support my work, consider becoming a free or paid subscriber.

Lesson 1: Designing Professional Infographics with NotebookLM

Infographics are perfect for visualising a timeline or a “Life by the Numbers” chart. In the 2026 Studio Panel update, Google added a specialised tool to turn your source-grounded research into a “single, engaging visual summary”. This is ideal for visualising an ancestor’s life timeline, family tree, or career journey.

Step 1: Preparation and Source Selection

• Finalise Your Sources: Ensure your notebook contains the high-quality narrative and Family Group Sheet generated in the previous steps.

• Selective Focusing: In the left sidebar, check only the documents you want included in the infographic.

  • Tip: If you want a career-focused infographic like Alfred’s, select only the census records and the Gemini narrative.

Step 2: Customising the Visual Style

• Open Studio: Navigate to the Studio panel on the right and select Infographic.

• Pencil Icon (Crucial): Click the pencil icon next to the title to unlock customisation.

• Set the Foundations:

  • Orientation: Choose Portrait (best for mobile/web reading), Landscape (best for presentations), or Square (best for social media).

  • Level of Detail: Select Concise for a high-level summary or Detailed for a comprehensive life-story breakdown.

Step 3: Mastering Style Prompts

Because NotebookLM is “Gemini under the hood,” the quality of your infographic depends on your prompt. In the custom instruction box, define the visual metaphor and colour palette.

Prompt Examples for Students:

• The “Journey” Style: “Design a winding path or road timeline that shows the transition from rural Essex to industrial London. Use a vintage, desaturated color scheme with burnt orange highlights”.

• The “Blueprint” Style: “Create a technical blueprint style infographic with a monochromatic blue palette. Focus on the chronological progression of addresses and job titles”.

• The “Sketchnote” Style: “Create a whiteboard-style infographic with marker-style doodles, arrow connectors, and handwritten fonts to represent family branches”.

Step 4: Generation and Export

• Wait for Background Processing: The visual is generated in the background, taking roughly two minutes, allowing you to keep working on your research.

• Download High-Res: Once complete, click the three dots menu (⋮) next to the generated title and select Download to save it as a PNG file.

• Sharing: You can share the infographic directly via a public link if your notebook settings allow “Anyone with a link” access.

Lesson 2: Building a Slide Deck

Use this for classroom presentations or family reunions to tell the ancestor’s story visually.

Step 1: Upload and Select Your Sources

• Create Your Notebook: Open NotebookLM and create a new notebook for your ancestor.

• Upload Records: Upload your primary evidence, such as PDFs of census records, JPGs of certificates, or the polished narrative you created in Gemini.

• Select Specific Sources: In the left-hand source panel, you can check or uncheck specific documents. This allows the AI to focus only on relevant records for your presentation.

Step 2: Configure and Edit the Slide Prompt

• Locate the Tool: Go to the Studio panel and find the Slide Deck option.

• Open Customisation: Click the pencil icon next to “Slide Deck” to open the configuration settings.

• Choose a Format:

  • Presenter Slides: Clean, visual slides with minimal text and speaker notes.

  • Detailed Deck: Comprehensive slides with full text, ideal for standalone reading.

• Edit the Prompt: Use the custom instruction box to define the style and audience.

  • Example Prompt: “Create a 6-slide presentation for a history class. Focus on the transition from skilled shoemaking to industrial labour. Use a professional, historical tone with a clear timeline. ”

Step 3: View and Download the Slides

• Generate and Preview: Click Generate. Once the process is complete, select the deck title in the Studio panel to open the viewer.

• View in Full Screen: Click Start Slideshow to present directly within the app.

• Download as PDF: Click the three dots menu (⋮) next to your slide deck title and select Download.

Review and Publish

AI can occasionally misinterpret handwritten script in old records. Always perform a final “sanity check”:

• Verify Dates: Ensure the AI didn’t confuse a birth year with a baptism year.

• Check Relationships: Confirm all children and spouses are correctly attributed.

• Upload: Once polished, add the story to your article or genealogy profile.

See it in Action!

Alfred Thomas Wright: The Craftsman's Journey

To see exactly what this workflow produces, look at this finished example of Alfred Thomas Wright, my paternal great-grandfather. I have focussed on his transition from one industry to another.

Alfred was born in Halstead, Essex. For years, he was a skilled bootmaker in Stratford, raising nine children with his wife, Eliza Goats. However, the 1901 and 1911 censuses revealed a dramatic shift: as mechanisation killed off the independent cobbler trade, Alfred adapted.

In his 60s and 70s, he transitioned from a craftsman to a gas factory labourer. His story is no longer just a list of dates; it is a narrative of resilience and the grit of the East End working class.

🔗 Read the Full Article on WeAre: Alfred Thomas Wright

Why This Matters

AI doesn’t replace the genealogist; it empowers us. It allows us to process vast amounts of historical context instantly, ensuring that men like Alfred—who might otherwise be forgotten as just another “labourer” on a census page—are remembered for the craftsmen they truly were.

Would you like me to help you draft the first prompt for your next ancestor’s analysis? Find out how you can create the building blocks of your ancestor profile in a few minutes with the help of AI tools!

Come and join me in the Ancestry in the Age of AI community on Facebook.

Transforming Family History with AI and Digital Archives

for members of the Genealogical Society of Victoria

Scheduled for: Tuesday 2 December 2025 1:30 to 3:00 pm

GSV members, please register for the ZOOM SESSION here.

In my latest Essential Genealogy Academy presentation, I explore how artificial intelligence, digital archiving, and next-generation agentic browsers are changing the way we uncover and preserve family histories.

AI in Genealogy: Enhancing Discovery and Storytelling

AI isn’t here to replace genealogists—it’s here to amplify our storytelling power. With tools that instantly transcribe handwritten records, infer relationships and timelines, draft narrative sketches of ancestors, and analyse historical sources for accuracy, genealogists are free to focus on interpreting, connecting, and crafting family stories.

Agentic Browsers: Smarter Research Workflows

Meet the new generation of agentic browsers—tools that act with intention. Browsers such as Comet, Atlas, and Perplexity search and cross-reference records across sources, summarize findings in real time, and suggest next steps. This keeps genealogists in a connected research environment, transitioning from manual searching to AI-assisted discovery.

WeAre.xyz: Building Living Family Archives

Think of archiving as storytelling with permanence. Platforms like WeAre.xyz transform raw research into interactive, story-driven archives. You can create dedicated pages for families, places, and heirlooms; use AI to summarise metadata and polish your text; and present your findings as a living digital legacy for descendants to explore

The Unified Workflow in Action

During the live demo, I showcase a complete research workflow, using my own family lines as examples:

1. Use an agentic browser to gather and verify records.

2. Draft ancestor profiles and stories in ChatGPT Projects.

3. Publish results to WeAre.xyz to preserve and share.

This cycle creates a seamless, creative loop—merging technology with tradition.

Looking Ahead

The future of family history is about integration: human intuition, historical accuracy, and intelligent digital assistants working together. Want to start your transformation?

Explore the Essential Genealogy Academy, and join collaborative communities like “Ancestry in the Age of AI” on Facebook.

Leave a comment

Here is the link to the digital download available at the Essential Genealogy 2.0 Academy, “Family History Writer's AI Toolbox – Complete Setup Guide”

Family History Writers’ toolbox by Canva, August 2025

Summary and overview

The "Family History Writer's AI Toolbox" is a structured system designed to help genealogists and family historians transform dry research into emotionally resonant ancestral stories using artificial intelligence. Rather than being just a list of tools, the guide outlines a complete workflow for integrating research, narrative craft, and creative expression in a manageable, repeatable way. It is now available for free from the link above.

This resource outlines an AI-powered toolkit designed for family history writers. It details a comprehensive browser tab group setup, including categories for AI writing partners, prompt templates, and visual creation tools, alongside genealogy archives. The guide provides specific examples of prompt templates for character development, setting scenes, and crafting dialogue, as well as a narrative tone guide for various historical eras. Furthermore, it introduces AI worksheet templates for story planning and historical context, offering step-by-step setup instructions and strategies for implementing and optimising this system to enhance the quality and efficiency of family storytelling.

Subscribe now

Briefing Document: The Family History Writer's AI Toolbox

This briefing document summarises the "Family History Writer's AI Toolbox" as presented in the provided excerpts. It outlines the core components, key functionalities, and strategic implementation for leveraging AI and digital tools in family history writing.

Main Themes and Most Important Ideas:

The "Family History Writer's AI Toolbox" emphasises a structured and systematic approach to integrating AI and digital resources into family history research and narrative creation. The central idea is to streamline the writing process, enhance creativity, and ensure factual accuracy by organising diverse tools into a cohesive "toolbox".

1. The "Toolbox" as a Structured Digital Workspace:

The core concept is the creation of a "Family History Writer's AI Toolbox" browser tab group designed for efficiency and easy access to all necessary resources. This setup includes:

AI Writing Partners (Tab 1):

Utilising various AI models for specific tasks:

• ChatGPT: "for brainstorming, planning, and drafting"

• Specific GPTs (Family Tree GPT, Historical Context GPT): For genealogy-specific queries

• Claude Sonnet: "for narrative writing, story arcs and social media posts"

• Perplexity: "for fact-checking and research verification"

Prompt Template Library (Tab 2): A collection of pre-designed prompts for various writing stages, including:

• "Profile development prompts"

• "Setting and context builders"

• "Dialogue creation templates"

• "Timeline structuring prompts"

AI Worksheets Collection (Tab 3): Digital templates (e.g., Google Docs) for organising thoughts and research, such as:

• "Story planning templates"

• "Ancestor profile builders"

• "Historical context checklists"

• "Narrative Tone Guides"

• "Narrative arc planners"

Visual Creation Tools (Tab 4): Resources for visual storytelling and organisation:

• "Trello for research planning"

• "Canva for family trees and infographics"

• "Map generators for migration stories"

• "Photo editing for historical documents"

Genealogy and Family History Archives (Tab 5): Direct access to research databases like Ancestry.com and WeAre.xyz

The setup instructions emphasise creating a dedicated browser tab group, customising a prompt library in a shared document, and organising a visual workspace.

2. Ready-to-Use Prompt Templates and Worksheets:

The toolbox provides specific examples of prompts and worksheets to guide the user:

• Character Development Prompts: Example: "Create a detailed character profile for [Ancestor Name]...describe their likely daily routine, personality traits shaped by their era, and the challenges they would have faced. Include sensory details about their world."

• Setting the Scene Prompts: Example: "Paint a vivid picture of [Location] in [Year]. What would my ancestor have seen, heard, and smelled walking down the main street? What were the social dynamics, economic conditions, and cultural atmosphere of this place and time?"

• Dialogue Creation Prompts: Example: "Based on the social class, education level, and regional dialect of [Location] in [Time], write a conversation between [Ancestor 1] and [Ancestor 2] discussing [specific historical event or family situation]."

• Narrative Tone Guides: Examples for different eras (Victorian, early 20th century, and Depression era) demonstrating formal, personal, optimistic, realistic, resilient, and stark tones.

• AI Worksheet Templates: Story Planning Worksheet: Fields for "Ancestor", "Period", "Central Conflict/Challenge", "Historical Context Needed", "Research Gaps to Address", and "Narrative Goal".

• Character Development Worksheet: Sections for "Physical Description", "Personality Traits", "Motivations", "Relationships", and "Legacy".

• Historical Context Checklist: A comprehensive list of elements to consider, including "Major historical events", "Local/regional conditions", "Economic circumstances", "Available technology", "Social norms," "Educational opportunities", and "Religious/cultural influences".

3. Advanced Customisation and Collaboration:

The toolbox encourages advanced features to tailor the experience:

• Family Line Specific Tabs: Creating distinct tab groups for different ancestral lines, each with "Relevant historical context", "Specific research documents", and "Customised prompts".

• Genre-Specific Templates: Utilising AI for different storytelling genres such as "Mystery/Detective", "Romance", "Adventure", "Drama", and "Biography".

• Collaborative Features: Facilitating "Shared family storytelling projects", "Community prompt sharing", "Peer feedback integration", and "Family member contribution workflows"

4. Strategic Implementation and Success Metrics:

The document provides a four-week implementation strategy:

• Week 1: Foundation Building: Setting up the basic tab group and gathering essential tools

• Week 2: Customisation: Adding family-specific resources, developing personal tone guides, and testing workflows.

• Week 3: Optimisation: Refining prompts, streamlining tools, and creating visual templates.

• Week 4: Mastery: Completing the first full ancestor story, sharing the setup, and documenting best practices.

Success is measured by:

• "Time saved: From idea to draft completion"

• "Story quality: Engagement and emotional resonance"

• "Research integration: How well AI helps connect facts to narrative"

• "Creative flow: Reduced writer's block incidents"

• "Output consistency: Regular story completion"

The overarching message is that the "Family History Writer's Toolbox” isn't just about organisation – it's about creating a space where your ancestors' stories can flourish with the perfect blend of research rigour and creative inspiration." The document encourages starting with "just one ancestor story and watching how this systematic approach transforms scattered facts into compelling family narratives."

Leave a comment

Today’s project took a new digital download called AI Image Generators for Family History and transformed it into an explanatory Podcast with help from NotebookLM.

The audio file above is an edited version of the podcast created in NotebookLM by the team of two AI voices. First, I uploaded the AI Image Generators for Family History file to Descript, a favourite media editing tool, and used the wizardry of the Descript Underlord to remove filler words, adjust the tone and edit out unwanted content. Then I asked ChatGPT to create an image to go with this blog post.

Whimsical image by ChatGPT, August 2025

Subscribe now

In today's digital age, preserving and visualising our family history has taken a radical leap forward. If you've ever peered at a faded family photograph or deciphered names on a crumbling census record and wished for more, your time has come. Thanks to AI image generators, we can now connect with the past in ways previously unimaginable. Let's embark on this visual journey and explore how AI tools elevate family history projects.

Discovering the Power of AI

Imagine being able to bring your ancestors to life visually, gaining insight into the nuances of their world through images crafted by intelligent technology. Our mission is to explore why experimenting with various AI tools is paramount to achieving the visuals you desire. The myriad of options might seem overwhelming at first, but each tool comes with distinctive strengths that can tailor your story to perfection.

Navigating the AI Landscape

AI tools like DALL-E 3, which you can access through chat platforms such as GPT, epitomise flexibility and creativity with edits. Its ability to interpret complex prompts makes it ideal for restoring damaged photos or crafting scenes enriched with period-specific detail.

On the other hand, Canva's Magic Media, seamlessly integrated into a design tool familiar to many, offers easy, quick illustrations for family trees or presentation slides.

For those needing character consistency, Leonardo AI stands out. It's perfect for showcasing someone, like a great-grandfather, at varying life stages, offering continuity across multiple historical narratives.

If speed and high-quality output are your goals, Google's Gemini model serves as an invaluable resource for rapid historical illustrations or brainstorming.

For those willing to invest, a platform like Abacus AI provides a spectrum of generators under one roof. This is beneficial for creating diverse characters or developing styles for vast family tales. Experimenting across these offerings underscores a crucial point—it's about matching the tool with your needs.

Strategically Choosing Your Tools

The journey begins by defining your story. Visualise the setting before diving into the technicalities. Is it a scene among Welsh coal miners from 1906 or an 1880s English farm family? Consider the attire, surroundings, and mood.

Once clarity is achieved, select the tool that complements your vision, whether Leonardo for faces or DALL-E for intricate details. Be prepared to adapt and iterate during the refining process, particularly when encountering typical AI anomalies, such as extra fingers or distorted expressions. Switching tools or integrating manual edits via Canva when necessary can resolve these quirks. This strategic flexibility enhances your storytelling.

Bringing the Past to Life

For those venturing into this digital exploration, it's about thinking creatively, akin to directing a film of your family's history. Instead of accepting the first AI-generated image, fine-tune your prompts, document your progress, and maintain context. Annotate your visuals with notes indicating their purpose, such as generating a 1920s style for a great aunt. Incorporating these vivid AI representations alongside actual documents, maps, and photographs enriches the narrative, providing texture and immersion. Visualising an ancestor's village, even without existing photos, becomes reality, connecting past to present intricately.

Next Steps for History Enthusiasts

Now, it's your turn. Consider which tool might help you visualise a cherished family photo or a scene described in an old correspondence. Contemplate how combining different tools might narrate your family’s story more vividly. Embark on this exploration with excitement and refine your family's visual history.

Happy exploring!

Leave a comment

🌟Picture AI as your research assistant—brilliant at gathering threads but needing your vision to weave the tapestry. 🌟

Composite image by Flux-1 Kontext and Canva, July 2025

Subscribe now

When I first encountered AI tools in my genealogical work, I felt that familiar tug between innovation and tradition—the same tension our ancestors must have experienced when embracing new technologies in their time. How do we honour their stories while stepping boldly into tomorrow's possibilities? A question I hear often from the growing community of family historians and genealogists beginning their journey into AI-assisted writing.

✨Remember: Your most powerful tool isn't any algorithm—it's your heart's connection to your family story. ✨

Share

Here's what I've discovered about maintaining my creative edge:

• My voice is irreplaceable. AI might decode historical contexts or suggest narrative structures, but only I carry the emotional inheritance of my family's journey. That catch in my throat when I read my grandmother's letter? That's where my authenticity lives. I needed to preserve my voice through the stories of my ancestors.

• Set sacred boundaries. Use AI as my research assistant—brilliant at gathering threads—but reserve the weaving for my heart. Let technology illuminate the facts; I will provide the soul that transforms information into a legacy. I owe this to my descendants, who will read my stories long after I’ve gone.

• Innovation serves love, never the reverse. Each tool I embrace should amplify my connection to those who came before, not distance me from their truth. I relish the speed at which AI tools enhance and structure my writing, but I want to put the ‘heart’ back in my stories.

• A smart AI workflow is essential. I want to be able to repeat my process with confidence and efficiency while generating profiles, biographies, images, transcriptions, and narrative transformations. At the heart of that workflow is my AI Toolkit and my Prompt Library.

• Maintaining my creative edge is crucial. I need to stay on top of the updates to my AI tools and to participate in communities with others who are doing the same. I need to listen to the voices of thought leaders in the field of ancestry in the age of AI and to learn from my peers. Finally, I need to adapt my workflow to keep a fresh perspective.

Essential AI strategies for the thoughtful genealogist:

• Understand AI as a collaborator, not a replacement

• Cultivate originality through personal interpretation

• Maintain transparency in your research process

• Build workflows that honour your creative rhythm

• Stay adaptive while preserving authenticity

✨Your creative edge lives in the space between information and inspiration! ✨

Leave a comment

Share

A Storytelling Methodology

A comprehensive approach to integrating artificial intelligence into family history narrative crafting.

This framework represents a fundamental shift in family history methodology—from AI as a tool to AI as a thoughtful storytelling companion, helping us craft narratives worthy of the lives they represent.

Understanding the Framework Philosophy

Every family story deserves to be told with the depth and nuance it carries in life. After eighteen months of testing AI tools against real ancestral narratives—from piecing together the daily life stories to understanding the emotional weight behind tragic newspaper records—I've developed a methodology that honors both technological capability and human storytelling tradition.

Take my research into Harriet Allery's world in 1840s Devon. When I discovered she lived through the railway's arrival in Totnes, I didn't just note the date—I asked Claude to help me understand what that thunderous change meant to a young mother whose world had been shaped by market-day rhythms and church bells. The AI painted a vivid picture of how iron horses might have terrified children who'd never seen anything move faster than a galloping mare. Suddenly, Harriet wasn't just a name in a census; she was a woman clutching her shawl as modernity roared past her cottage.

This framework transforms AI from a mere research accelerator into a thoughtful storytelling companion, one that helps us bridge the gap between scattered historical facts and the rich, emotional tapestries of our ancestors’ actual lives.

(Though I must admit, AI occasionally gets a bit too dramatic—apparently every ancestor lived through "tumultuous times." Sometimes a Tuesday was just a Tuesday, even in 1847.)

You can read the stories of Harriett Allery, my three times great-grandmother, in my Memoirs of my Devon Ancestors: “Your Story Matters” series.

Subscribe now

Four Pillars of AI-Enhanced Family Storytelling

Pillar 1: Contextual Research Partnership

AI excels at weaving historical context around the fragments we've uncovered. Rather than simply searching for facts, we engage AI as a research partner that helps us understand the world our ancestors inhabited—the social pressures, daily realities, and historical currents that shaped their choices.

Core Principle: Every ancestor lived within layers of context that influenced their story. AI helps us reconstruct these layers with unprecedented depth.

Practical Tip from Harriet's Story: When I discovered Harriet Allery made weekly trips to Totnes market, I asked ChatGPT: "What would market day have been like for a young mother in 1840s Devon? Include sounds, smells, social dynamics, and economic realities." The response transformed a simple census entry into a vivid scene where I could almost hear the clatter of carts on cobblestones and smell the fresh bread stalls. Try this with your own ancestor's documented activities—ask AI to flesh out their sensory world.

Pillar 2: Character Development Through Empathy

Our ancestors were complex individuals, not merely names in records. AI can help us develop nuanced character profiles by analyzing historical patterns, social conditions, and human psychology of specific eras, allowing us to approach our ancestors with greater empathy and understanding.

Core Principle: Behind every genealogical fact lies a human story worth understanding with compassion.

Practical Tip from Harriet's Story: When researching Harriet's marriage at seventeen to Samuel Goodman (who was "more than twice her age"), I asked Claude to help me understand: "What were the emotional and practical realities for young women in rural Devon entering arranged marriages in the 1830s?" This helped me write about her wedding day with authentic nervousness rather than modern judgment. The key is asking AI to help you inhabit their mindset, not impose yours.

Pillar 3: Narrative Architecture

AI serves as a structural partner in organizing family stories, helping us identify compelling narrative threads, emotional turning points, and thematic connections that might otherwise remain buried in our research notes.

Core Principle: Great family stories require intentional storytelling craft, enhanced by AI's pattern recognition capabilities.

Practical Tip from Harriet's Story: I fed all my research about Harriet into Claude and asked: "What are the major life themes and turning points in this woman's story? How might these connect to universal human experiences?" The AI identified patterns I'd missed—themes of adaptation, quiet resilience, and finding dignity in everyday work. Sometimes you're too close to your research to see the bigger narrative arc. AI can be your external story editor. (Just don't let it convince you every ancestor was "ahead of their time"—some people are perfectly of their time, and that's equally fascinating.)

Pillar 4: Multi-Modal Story Creation

Modern family history transcends written narratives. AI tools help us create visual elements, enhance photographs, and develop multimedia presentations that bring ancestral stories to life across different formats and audiences.

Core Principle: Family stories deserve to be experienced through multiple senses and media.

Practical Tip from Harriet's Story: When I wanted to show what Harriet's cottage might have looked like, I used AI image generators with prompts like: "1840s Devon cottage interior with cast iron pot, herb-drying bundles, simple wooden table, warm firelight." The results helped me describe her "kitchen magic" more vividly. For dialogue, I asked AI to help me craft period-appropriate speech patterns: "How would a working-class Devon woman in the 1840s express affection or give advice?" Remember: AI-generated content should enhance authentic research, not replace it.

The Methodology in Practice

Phase 1: Foundation Setting

Begin each storytelling project by establishing what I call the "ancestral landscape"—the geographical, temporal, and social environment in which your ancestor's story unfolds. AI serves as your research partner, helping you understand not just where and when your ancestor lived, but how those circumstances would have shaped their daily experience.

Phase 2: Character Archeology

Move beyond vital statistics to understand your ancestor as a fully realized person. AI helps analyze period-appropriate psychology, social expectations, and cultural pressures to develop authentic character insights that honor their complexity.

Phase 3: Narrative Weaving

Transform researched insights into compelling story structures. AI assists in identifying emotional arcs, dramatic tension points, and thematic elements that transform genealogical data into engaging narratives.

Phase 4: Story Amplification

Enhance your narratives through visual storytelling, period-appropriate dialogue creation, and multimedia elements that make family stories accessible and memorable for different audiences.

Looking for more? Try the ‘12 Questions Story Scoping Framework’

Leave a comment

This framework represents a fundamental shift in family history methodology—from AI as a tool to AI as a thoughtful storytelling companion, helping us craft narratives worthy of the lives they represent.

For this podcast, I asked the team at NotebookLM to analyse, unpack, and synthesise the messages, ideas, and advice in my latest ‘Beyond the Pen’ newsletter.

This 17.5-minute conversation is the result of that request. The process was simple: I gave the URL of the newsletter posted on Substack and then clicked the generate button. I waited for 5 minutes and then downloaded this audio file. It’s brilliant.

It made me feel like I really had something important and enlightening to say about my favourite topic of AI in Genealogy; another chapter in My Genealogy Journey.

Share

You can read more about this presentation and its content on my blog post:

Discover your family history mysteries easily with AI

Subscribe now

Leave a comment

Subscribe now

My latest blog post contains several new video tutorials. As yet there is no direct link between my WordPress blog and Substack, so I am just posting the link manually.

Videos in this new series include:

1. Analysing Documents

2. Extracting Data

3. Creating Timelines

4. Embedding Historical Context

5. Identifying Patterns and Connections

6. Research Planning and Strategy

7. Analyzing Conflicting Information

8. Creating Family Narratives

9. Creating Visual Assets for Family History

10. Choosing the Right AI for Genealogy Tasks

Note: Stay tuned for more links to YouTube Channel videos as they are created and published on the Genealogy AI Face-off Playlist.

Share

Note: Please let me know if you know how to post directly to Substack from a WordPress blog platform (e.g., using JetPack).