Research a Victorian-born grandfather's life with Claude, ChatGPT and Gemini deep research (partial)

Posted

Oct 21, 2026 by Dan Taylor-Watt (Substack)

·

Last checked

Oct 22, 2026

·

Method:

How we verify

Evidence: Article or interviewA newsletter, journalist or interview account of what happened.

Context: In a comparison test: from a head-to-head chatbot review, not a standalone agent test.

Outcome

Dan Taylor-Watt gave Claude, ChatGPT and Gemini the same brief, with deep research turned on, to research a paternal grandfather, Cecil, who died in 1960, starting from a Word document written by Taylor-Watt's father. Claude took about 6 minutes, used 340 sources and wrote an 11-page, 4,219-word report; it found no significant new information but flagged inaccurate dates, and it later made a 3-minute-30-second narrated video using code and an open-source voice model. ChatGPT took 9 minutes, ran 714 searches and wrote 14 pages (4,659 words); it caught an error about the year of the fire that destroyed service records, noted that the LNER railway wasn't created until 1923, found information on the first wife's family, and spotted a Lance-Corporal's chevron in a photo, but its video attempt fell short. Gemini wrote the longest and most visual report (5,347 words), but its maps were wrong (Osmotherley is east, not south, of Northallerton), it missed the date problems, and it said it couldn't make a video.

AI tools

Claude, ChatGPT, Gemini

The source didn't share its exact prompt, so we wrote this from what it describes.

What the prompt labels mean

Let's work this out together. I'll tell you what I know, you suggest options and ask what you need, and we'll narrow it down step by step. Nothing gets booked, bought or sent until I say so.

Goal: Research a relative's life from the family notes I have, checking what's right and finding what's new.

What I'll share as we go:
- The family notes or document I have: [NOTES]
- The person's name, rough dates and places: [PERSON]
- Photos or records I can share: [PHOTOS OR RECORDS]

Rules:
- Separate three things clearly: what my notes say, what records confirm, and what's new.
- Check every date and place in my notes against historical facts (when organisations existed, when records were lost) and flag anything that can't be right.
- Cite a source for every new fact, and mark anything that's only likely, not proven.
- If you draw a map, check each place's direction and distance from the others.
- Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify.

Output: A short life story with sources, a list of corrections to my notes, and open questions.

You'll know it worked when: I know which family details hold up, which don't, and what to look up next.

Let's work this out together. I'll tell you what I know, you suggest options and ask what you need, and we'll narrow it down step by step. Nothing gets booked, bought or sent until I say so.

Goal: Research a relative's life from the family notes I have, checking what's right and finding what's new.

What I'll share as we go:
- The family notes or document I have: [NOTES]
- The person's name, rough dates and places: [PERSON]
- Photos or records I can share: [PHOTOS OR RECORDS]

Rules:
- Separate three things clearly: what my notes say, what records confirm, and what's new.
- Check every date and place in my notes against historical facts (when organisations existed, when records were lost) and flag anything that can't be right.
- Cite a source for every new fact, and mark anything that's only likely, not proven.
- If you draw a map, check each place's direction and distance from the others.
- Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify.

Output: A short life story with sources, a list of corrections to my notes, and open questions.

You'll know it worked when: I know which family details hold up, which don't, and what to look up next.

Let's work this out together. I'll tell you what I know, you suggest options and ask what you need, and we'll narrow it down step by step. Nothing gets booked, bought or sent until I say so.

Goal: Research a relative's life from the family notes I have, checking what's right and finding what's new.

What I'll share as we go:
- The family notes or document I have: [NOTES]
- The person's name, rough dates and places: [PERSON]
- Photos or records I can share: [PHOTOS OR RECORDS]

Rules:
- Separate three things clearly: what my notes say, what records confirm, and what's new.
- Check every date and place in my notes against historical facts (when organisations existed, when records were lost) and flag anything that can't be right.
- Cite a source for every new fact, and mark anything that's only likely, not proven.
- If you draw a map, check each place's direction and distance from the others.
- Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify.
- End with the three records most worth ordering or searching next, and where to find them.

Output: A short life story with sources, a list of corrections to my notes, and open questions.

You'll know it worked when: I know which family details hold up, which don't, and what to look up next.

Before you finish: re-read my goal and constraints, check your answer against each one, and list anything you assumed or couldn't confirm.

Source

https://dantaylorwatt.substack.com/p/using-ai-to-research-my-victorian