Please note: Some features are forward-looking and may or may not be included in the final release; treat them as intended. This is not exhaustive – it all depends on paying customers and practicality.
Please add a comment if there is a feature you want most, or is missing from the list.
1. Retrieval agent – core tree & fact questions
These are “command-only, no guessing” bread and butter.
1.1 Basic identity & life facts
– Who is X?
– Who is X’s mother/father/parents?
– Is X the son/daughter/child of Y (or Y and Z)?
– Who are X’s children?
– Who are the children of X (or X and Y)?
– Who is the oldest/youngest child of X (or X and Y)?
– Who did X marry? How many times?
– When and where was X born?
– When and where did X pass/die?
– Is X still alive? If not, how old were they when they died?
– Has X passed?
– How old is X?
– How old would X be if still alive?
– What is X’s sex?
– What events are recorded in X’s life? (birth, marriage, death, census, immigration, etc.)
– Which of X’s children were born before/after 1944?
– Which of X’s daughters/sons were born/after/in 1944?
1.2 Ancestry & descent
– Who are X’s grandparents/great-grandparents up to N generations?
– Who are X’s 1st great grandparents?
– Who are X’s 2nd great grandparents?
– Who are X’s great great grandparents?
– Who are X’s great great great grandparents?
– List all descendants of X.
– Show the direct line from X to Y.
– Who is the earliest known ancestor in X’s direct paternal line?
– Who is the earliest known ancestor in X’s direct maternal line?
1.3 Siblings & birth order
– Who are X’s brothers/sisters/siblings?
– What is the birth order of X among their siblings?
– How many sons/daughters/children did X have?
– Which of X’s children were born before/after 1944?
– Which of X’s daughters/sons were born before/after 1944?
– Which of X’s children/sons/daughters was born closest to year Y?
1.4 Relationship lookup
– What is the relationship between X and Y?
– How am I related to X?
– Is X a cousin of Y? If so, what degree?
– Is X an aunt/uncle/niece/nephew of Y?
– Who are X’s aunts/uncles?
– Who are X’s cousins? (optionally filtered by degree)
– Who are X’s in-laws?
– Does X have a father/mother called Y?
– Is X the father/mother/parent of Y?
1.5 Counts & summaries
– How many children did X have?
– How many marriages did X have?
– How many brothers/sisters/siblings does/did X have?
– How many descendants does X have in generation N?
– How many people in X’s tree were born in [place] or [year range]?
1.6 Place & geography
– Where did X live throughout their life?
– Which of my relatives lived in X?
– Which of my relatives lived close to X?
– In which county/country was X born/married/buried?
– Which county is closest to [place]?
– Who in the tree is associated with [place]?
– Who emigrated to [country] from [origin country]?
– Who moved from [place A] to [place B]?
– Which counties border where X was born/died/married/lived?
1.7 DNA & match-oriented
– Is X a DNA match to Y?
– Is X a common DNA ancestor? (of me)
– Who are the common ancestors of X and Y based on DNA?
– Which people are shared DNA matches between X and Y?
– Which ancestors are most likely responsible for the shared DNA between X and Y? (borderline inference)
2. Inference agent – puzzles, hypotheses, constraints
These are the “genealogist brain” questions—where the system must reason, not just retrieve.
2.1 Relationship puzzles
– Given that A is described as a “half-sister” of B and C is an “aunt” of D, how might they all be related?
– If X is my great-grandfather and Y is my DNA match at ~200 cM, what are the possible relationships?
– Could X and Y be the same person given these dates and places?
– Is it possible that A is the father of B given their birth years and locations?
2.2 Slot-filling / where-do-they-fit questions
– I have an unnamed child born around 1885 in this family—where might they fit among these siblings?
– Could this “Mary Smith” be the same as the “Mary Ann Smith” in this other record?
– Which branch of the tree is the most likely place for this mystery person to belong?
– Given these constraints (age, place, surname), who are the candidate parents for X?
2.3 Conflict resolution
– Two records give different birth years for X—what is the most likely year?
– One source says X was born in County A, another in County B—how can this be reconciled?
– Could these two conflicting trees both be partially correct? If so, how?
2.4 Pattern & anomaly detection
– Are there any suspicious gaps in births in this family that might indicate missing children?
– Are there any improbable ages at marriage or childbirth that suggest an error?
– Does this tree show any repeated naming patterns that might hint at missing relatives?
3. Research agent – external records & discovery
These questions assume the system can reach out to Ancestry, FreeBMD, MyHeritage, etc.
3.1 Record search
– Find all birth registrations for a “John Smith” born around 1870 in Lancashire.
– Find census records for X in the 1901 and 1911 censuses.
– Search for a marriage between X and Y between 1890 and 1900 in England.
– Find immigration records for X travelling to Canada between 1920 and 1930.
3.2 Record ranking & suggestion
– Which of these three birth records is the most likely match for X?
– Given X’s parents and location, which of these census entries is the best fit?
– Suggest possible candidates for X’s parents from available records.
3.3 Gap-filling suggestions
– What records should I look for next to confirm X’s parents?
– Which sources might help resolve this conflict between two possible birthplaces?
– Are there parish records that might contain X’s baptism?
4. Normalisation agent – data quality, cleaning, and structure
These are the “make the data sane” questions.
4.1 Name normalisation & variants
– Are “Eliza Smith” and “Elizabeth Smith” likely to be the same person?
– List all variant spellings of the surname “Macdonald” in this tree.
– Group people whose names differ only by common nicknames (e.g., “Bill” vs “William”).
4.2 Date & place normalisation
– Normalise all dates to ISO format.
– Standardise place names to modern county boundaries.
– Identify records with incomplete or ambiguous dates (e.g., “about 1850”, “before 1871”).
4.3 Duplicate detection
– Identify possible duplicate individuals in this tree.
– Are these two records for “John Smith” likely to be the same person?
– Merge these two candidate profiles and highlight conflicts.
4.4 Structural sanity checks
– Flag any cases where a parent is younger than their child.
– Flag any births where the mother would have been under 13 or over 55.
– Flag overlapping marriages that suggest bigamy or data errors.
5. Analytical / overview questions (cross-agent)
– These can be answered by combining retrieval + light inference.
– Which branch of my tree has the most descendants?
– Which ancestors had the most children?
– Which families experienced the highest child mortality?
– Which ancestors emigrated, and where did they go?
– Show a timeline of major events for X’s direct ancestors.
– Which surnames appear most frequently in my tree?
– Which places are most common in my family history?
6. UX / assistant-style questions (meta)
These are not genealogy facts, but they matter for the product.
– What kinds of questions can you answer about my tree?
– Show me examples of interesting questions I could ask.
– Explain how you calculated the relationship between X and Y.
– Why do you think these two people might be the same?
– What data is missing that would help answer this question better?