Break a six-year family history brick wall with help from ChatGPT
Copy the prompt below and paste it into the AI tool named on this page.
Prompt Recreated prompt
The source didn't share its exact prompt, so we wrote this from what it describes.
I'm stuck on a family history brick wall. Here is everything we know about this ancestor, with dates, places and documents. What patterns do you see, what records should we check next, and could we be following the wrong person?
Try this in:
Sends the Recreated prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini opens empty, so we copy the prompt for you to paste. Every button also copies it.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google or xAI, and your results may not match the source.
Optional stronger version
Our rewrite with extra checks. The poster didn't test it.
Before you start, ask me 1–3 short questions about the details below and wait for my answers. Once I've answered, confirm the plan in one line and run the whole task start to finish. Goal: Find new leads on an ancestor I can't trace, without treating guesses as facts. Questions to ask me first: - Who is the ancestor, and what do we know for certain (with the documents that prove it)? - What family story are we trying to prove or disprove? - Which records and archives have we already searched? Inputs (fill in or confirm): - Known facts and sources: [FACTS / SOURCES] - Family story or theory: [THEORY] - Places and years: [PLACES / YEARS] - Records already searched: [RECORDS SEARCHED] Rules: - Separate what's proven, what's likely and what's only a guess, and label each one. - Never invent a name, date, record or archive; if you mention a collection, tell me where to find it so I can check. - Suggest other people with the same name we might be mixing up. - List the next records to check, with why each one could help. Checkpoint: Show me your proven/likely/guess table first and wait for me to correct it before suggesting leads. If you get stuck: If the trail goes cold, suggest a different angle (siblings, neighbors, land, court or church records) rather than forcing a link. Verify before you finish: Check every suggested lead is tied to a fact I gave you, and mark anything you couldn't confirm. Output: A short facts table, a list of possible mix-ups, and five next research steps. Done when: We have concrete new records to check and know which links are still unproven.
AI tool
Outcome
Two cousins spent six years trying to prove a family story that the Jacksons descended from the Reade family of colonial Virginia. ChatGPT couldn't hand them the answer, but it helped them spot patterns in their documents, surfaced lesser-known resources and suggested they might be 'chasing the wrong Francis'. A ChatGPT-assisted search led them to Library of Virginia records on a Captain Francis Read whose ship was captured by privateers, and a Reade family Bible at the library listed the children of Gwyn and Dorothy Reade. The next morning, cousin Kelly had pieced it together: 'I've been up since 4 a.m. I figured it out.'
Evidence: Described by posterThe person describes what happened in words, without screenshots or video.
Source
- Posted
- by The People Before Us
- Last checked
- Method:
- How we verify
https://www.thepeoplebeforeus.com/2025/07/the-oral-tradition-passed-down-through.html
Context: The breakthrough came from the cousins' own work in the archives; ChatGPT helped point them in a new direction.
Related cases
Separate land descriptions in an 1836 dower record with ChatGPT
Working from an 1836 Jefferson County, Indiana, probate record, the Heartland Genealogy blogger asked ChatGPT to pull out the land description. It separated Thomas D. Crawford's 113-acre tract from the 43¾ acres set aside as the dower of Crawford's widow, Jane. While drafting a blog post from the record, ChatGPT also found that this Jane appeared to be Jane Todd Crawford, remembered in medical history for surviving an operation performed by Dr. Ephraim McDowell. The writer treats it as a lead to keep researching: 'AI found the connection. It didn't finish the research.'
ResearchChatGPTWorkedRecreated promptEvidence: Described by posterView CaseTrace a family tree from half-remembered details with ChatGPT (partial)
Ryan Aubrey didn't know where the family came from, or even the grandparents' middle names. Aubrey turned ChatGPT's effort level up as high as it would go and shared everything known, mistakes included. On the father's side it quickly found a grandfather's obituary (a high school state championship and a basketball scholarship to the University of Tampa) and went through FamilySearch and Find a Grave to suggest a colonial Virginia line of 'Awbrey's' with a possible, unconfirmed Welsh origin. On the mother's side the line got lost after the grandparents in West Virginia, so Aubrey says the next step is to 'go analog'.
ResearchChatGPTPartialRecreated promptEvidence: Described by posterView CaseReport global NAND market share with Gemini Deep Research
Asked for a simple report on global NAND market share, Gemini Deep Research returned figures the poster called an incredible failure when compared with Sandisk's investor-day slide and Claude's answer to the same query.
ResearchGemini Deep ResearchFailureImproved promptEvidence: Screenshots or logsView Case
