Case Study
Finding Aunt Maisie
Colonial archive research, AI-assisted genealogy.
Problem
A retired professional had spent years trying to trace a family marriage record. His great-aunt, an Irish Montessori teacher, had emigrated to Ceylon in the 1920s and married an English telephone engineer. As far as the official record was concerned, both simply vanished into the colonial archive. Years of conventional searching had produced nothing.
What happened
Rather than another database search, he tried something different: he opened an AI and described the problem conversationally, with all the context he had accumulated over years of searching.
The AI did not produce the marriage certificate. What it did was subtler. It identified something he had overlooked: his relative’s husband had worked for a telecommunications company in Liverpool in 1921, a company with contracts across the British Empire including Ceylon. The colonial posting was not random; it was traceable through employment records.
From there it produced five actionable leads: the Kabristan Archives, sixteen thousand colonial birth, marriage and death records, free to search; a direct approach to the Catholic Diocese of Colombo; a prioritised action list; and reusable session notes so the next conversation could build on the first rather than starting again.
Outcome
One conversation. No marriage record yet, but a map where there had been blank space before. The research has a shape and a direction it did not have before.
Why it matters
The bottleneck was not the database. Years of searching the obvious sources had produced nothing. The bottleneck was the question: specifically, the failure to connect the employment history to the colonial posting. The AI found the connection because it was given the full context and asked to think about what was missing.
This is not a research tool that finds things you would have found anyway. Used well, it finds the shape of what you do not yet know.
A detailed write-up of this case — including the action list, the archives identified, and the reusable session notes — is available as a PDF.