Am I Chasing Rabbit Trails or Following the Records?

Asking ChatGPT to Critique My Research Style

I imagine every family historian knows the feeling. You sit down determined to finally focus on one ancestor…just one…and within twenty minutes you’re knee-deep in a different surname, chasing a witness on a deed, a neighbor in a census, or an in-law mentioned once in a probate file. Your browser has fifteen tabs open, your notes are branching in four directions, and you start to wonder whether you’re actually making progress or just indulging in well-documented procrastination.

Am I actually making progress…or am I just bad at staying on task?

That question has been nagging at me lately. Not because I lack ideas or records, but because I worry about discipline. About sticking with one line long enough to resolve it. About knowing when a tangent is necessary and when it’s just…interesting.

I suspect I’m not alone in this. Many researchers quietly worry that jumping between families means they aren’t serious enough, focused enough, or methodical enough. We hear phrases like “stay in your lane” or “finish one line before starting another,” and they sound right…until the records refuse to cooperate.

So I decided to do something a little unusual. I asked my AI research assistant to critique me. Not to tell me how great my work is. Not to smooth things over. But to be honest.

For context, I don’t treat AI as gospel. I correct it regularly. I reject conclusions that don’t hold up. I use it as a thinking partner, a sounding board, and sometimes a mirror. This time, I wanted the mirror.

I first asked my AI assistant to give me a one-sentence summary of the last 10 surnames I had been

researching in my family tree and to include the big idea/question I was researching. The AI response:

• Peterson (paternal): Determining whether later generations of Petersons are correctly attached to John and Ruth Peterson or whether DNA and documents point to a different relationship entirely.
• Morehead (maternal): Testing whether Alexander Morehead’s family connections, especially Thomas and Calvin Morehead, represent sibling relationships or part of a broader FAN (friends, associates, neighbors) network in Fairfield and surrounding counties.
• Thurman (paternal): Reconciling records that alternately name Daniel Thurman and John Thurman to determine whether they are the same man or closely related individuals across Tennessee, Alabama, and Arkansas.
• Alexander (maternal): Establishing the children and lineage of James Alexander and Jerusha through pension records and indirect evidence in a period with sparse civil documentation.
• Thompson (paternal): Using agricultural and census records to understand Rodden (Roden/Rodden) Thompson’s economic standing and confirm identity consistency across Arkansas records.
• Oglesby (paternal): Clarifying the identity, age, landholdings, and family structure of Constant Oglesby amid variant spellings and early tax and land records.
• Mezo (paternal): Tracing Moses Mezo and Molly (Mary) Oglesby to confirm marriage, migration patterns, and correct surname usage amid repeated misattributions.
• Hancock (maternal): Reconstructing family relationships and land associations through deeds and neighbor analysis to separate documented facts from later assumptions.
• Lawson (paternal): Testing land and tax records to confirm whether similarly named Lawsons represent one individual over time or multiple related men in the same locality.
• Gooding (paternal): Sorting out sibling and in-law relationships among the Gooding family to understand how marriage ties explain beneficiary and witness patterns in early probate documents.

I asked this because I am concerned that I veer off too much and don’t stick to one line long enough. 

Since I have been using AI for about a year now to really help me organize, analyze, and plan research questions, I wanted to know what the AI bot thought of my research and to be honest.

The following is its response: 

I’ll be straight with you, but fair. You do not come across as unfocused or scattershot. What you’re doing looks messy on the surface, but methodologically it actually makes sense for the time periods and problems you’re working in.

Here’s the honest tension I see.

On the risk side:
Yes, there are moments where you pivot quickly…from Peterson to Thurman to Alexander to Morehead…and if someone only skimmed your work, they might think you’re chasing too many threads at once. That can dilute momentum if you’re not careful, especially emotionally, because none of these lines resolve quickly.

On the strength side:
Your pivots are not random. They are triggered by evidence. A probate file points sideways, a census conflict forces a detour, a DNA match drags another surname into the room. That’s not veering…that’s following the record set where it actually leads. Early 19th-century research is inherently collateral.

The deeper truth:
You’re not researching surnames. You’re researching problems. Each surname is a different angle on a single question…who belonged to whom, and how can we prove it without modern records. When you frame it that way, your work is actually disciplined, not scattered.

Where I think a small correction would help:
You might benefit from declaring “primary” and “supporting” lines at any given time. For example, Peterson is the primary problem; Gooding, Thurman, or Alexander are supporting investigations that exist only to resolve that core question. That doesn’t change your research…it changes how you mentally file it.

One practical suggestion that fits your style:
Before starting a new deep dive, write a one-sentence gatekeeping question like: “If I solve this, will it directly confirm, weaken, or eliminate a parentage hypothesis I already have?”
If the answer is yes, you’re on track. If not, park it.

Bottom line, honestly:
You are not drifting. You are working at the edge of what the records allow, and that edge forces lateral movement. The danger for you isn’t lack of focus…it’s burnout from juggling too many unresolved but legitimate questions at once.

End of the AI response.

Reading that response didn’t magically make my research simpler, but it did clarify something important. The problem isn’t that I explore too much. It’s that early records demand exploration. The danger comes when I forget to name which question is central and which paths exist only to serve it.

For me, using AI this way isn’t about outsourcing thinking. It’s about sharpening it. When I argue with it, correct it, or ask it to critique me, I’m forced to slow down and articulate why I’m doing what I’m doing.

And that, in the end, might be the most valuable research habit of all.

When DNA Finds a Cousin but the Trees Guess the Parents

Using Ancestry ThruLines wisely without letting it rewrite my Peterson family history

Why This Post?

I want to share a small but important lesson from my own Peterson research. DNA can be a powerful tool for breaking brick walls, but it can also create false confidence when DNA evidence gets blended with unproven online trees.^1,5

Suggested Family Connections

What ThruLines Is Actually Showing

Ancestry’s ThruLines feature works by combining two things: your DNA matches and the family trees connected to those matches. When Ancestry sees that you share DNA with people who descend from a particular individual, and when enough public trees connect that individual to someone in your own tree, ThruLines suggests a relationship. What it does not do is evaluate whether the parent-child links inside those trees are actually supported by records. In practice, this means ThruLines reflects consensus, not proof.²

My Peterson Example With One Proven Link and One Unproven One

In my own research, Robert Peterson is a documented son of John Peterson and Ruth Pyle. That relationship is supported by records and serves as a solid anchor in my tree. The difficulty arises when ThruLines suggests that Tobias Peterson is also the son of John and Ruth. The DNA matches connected to Tobias are real, but the sources attached to Tobias in public trees do not name John and Ruth as his parents. Instead, the suggested relationship relies on Tobias’s approximate birth year and geographic proximity to John and Ruth. Plausible, yes. Proven, no.

Why the DNA Can Be Right Even If the Trees Are Wrong

At the distance involved here, small amounts of shared DNA are exactly what we expect. Matches in the range of roughly 10 to 25 centimorgans often represent distant cousins who share a common ancestor several generations back. At that level, DNA can reliably tell us that two people are related, but it usually cannot tell us exactly how. A shared DNA segment supports shared ancestry somewhere on the Peterson line, but it does not, by itself, establish a specific parent-child relationship.^3,4

Where Tree-Based Assumptions Take Over

Many of the trees that attach Tobias to John and Ruth rely on census records, indexes, or burial databases. These sources confirm Tobias as a real person in a real place at a plausible time, but they do not identify his parents. Once one tree makes the leap to assign Tobias as a son, that assumption gets copied into other trees. ThruLines then treats repetition as reinforcement, even though the underlying claim remains undocumented.

The Key Takeaway

Ancestry is showing what many people believe, not what has been proven. ThruLines can be a helpful tool for identifying DNA clusters and possible family connections, but it is not a proof engine. The discipline to pause, evaluate the sources, and refuse to elevate a guess into a fact is at the heart of careful genealogical work. Even when Ancestry’s interface makes it feel otherwise, the evidence still needs to stand on its own..^1,5

Reframing the Tobias Question

Instead of asking whether Tobias is the son of John and Ruth, a better question is how Tobias fits into the broader Peterson family network. Tobias could be a nephew, a cousin, a grandson through an undocumented child, or part of a related Peterson line that shares an earlier, unidentified ancestor. The DNA supports shared ancestry, but it does not force a single explanation. Leaving Tobias “related but unplaced” is not a weakness. It is responsible research.

How I’m Using ThruLines Without Letting It Rewrite My Tree

I’m not rejecting ThruLines. I’m using it for what it does well: identifying clusters of related people and pointing me toward the right surname and community. At the same time, I keep documented relationships, like Robert Peterson’s connection to John and Ruth, clearly separated from unproven ones. DNA guides my research. Records determine what earns a place in my tree.

Why this matters

DNA is not the problem. Assumptions are. When we let DNA point us toward the right families and places, then slow down and demand documentation before assigning parentage, we end up with conclusions that can stand up over time. ThruLines can be a helpful road sign, but it is not the destination.

---

Footnotes

1. Ancestry Support, “AncestryDNA ThruLines,” Ancestry.com.
2. Ancestry Support, “How ThruLines Works,” Ancestry.com.
3. Ancestry Support, “Understanding AncestryDNA Match Categories,” Ancestry.com.
4. DNA Painter, “Shared cM Tool,” https://dnapainter.com/tools/sharedcm.
5. Roberta Estes, “Ancestry’s ThruLines Dissected: How to Use ThruLines and Not Get Bit by the Gators,” DNAeXplained – Genetic Genealogy, March 11, 2019.
   https://dna-explained.com/2019/03/11/ancestrys-thrulines-dissected-how-to-use-and-not-get-bit-by-the-gators/

 

When to Stop Extending a Family Tree: Records, DNA, and the Limits of Evidence

Why careful genealogy sometimes means leaving branches unfinished

Why This Post

The purpose of this post is to explain a research dilemma I’ve encountered while studying my Peterson ancestry: how DNA evidence, early church records, and modern indexing can push family trees further back than the surviving documentation can reliably support, and why I’ve chosen to stop where the records stop.

When DNA Goes Further Than the Records

One of the hardest decisions in genealogy is not how to extend a family line, but when to stop extending it.

As I’ve continued working on my Peterson research, I’ve run into a dilemma that many family historians face today. DNA evidence suggests connections that stretch several generations beyond what the surviving records clearly support. Online trees reflect those connections with confidence, often presenting long ancestral lines that appear tidy and complete. Yet when I slow down and look for the documents that should anchor those relationships, the trail becomes much less certain.

What the Records Clearly Support

My direct ancestor in this line is Robert Peterson (1774–1834). The documentary evidence supporting Robert and his immediate family is solid enough to work with carefully. His father, John Peterson, who married Ruth Pyles, is supported by records that can be evaluated and cross-checked.

Beyond John, however, the evidence changes in character. Instead of clear statements of parentage, I encounter repeated names, church entries with descriptive terms, and DNA connections that point in a general direction but do not confirm a specific relationship.

When Repetition Starts to Look Like Proof

In several trees, John Peterson’s parents are confidently named, sometimes with detailed ancestral lines reaching back into Europe. These same names also appear across multiple DNA-connected trees, which can give the impression of confirmation.

But repetition is not proof. DNA can tell us that people are related; it does not, by itself, tell us exactly how they are related. Without records that explicitly connect a parent to a child, the relationship remains a hypothesis, no matter how often it appears online.

A Delaware Baptism Record as an Example

Ancestry.com. Delaware, U.S., Baptisms,
1697-1886 [database on-line]

A Delaware baptism record illustrates how this problem can take shape. Indexed versions of the record list:

Peter Peterson Cauponi
Spouse: Magdalena
Child: Johan Peterson Cauponi

At first glance, it is easy to read this as a family with a compound surname, or to assume that “Cauponi” is part of the Peterson name. Some researchers have carried this forward by inserting “Caupany” or similar spellings into modern family trees as a middle name or additional surname. The record itself does not support that conclusion.

What “Cauponi” Likely Means

The term cauponi comes from Latin and is associated with caupo, meaning an innkeeper, tavern keeper, or merchant (see sources below.) In early church records, especially those written or indexed using Latin conventions, it was common to include descriptive terms alongside a person’s name. These descriptors helped distinguish individuals with common names, much like an occupation or place might be used today.

In this case, the record identifies a man named Peter Peterson, his wife Magdalena, and their child Johan. The word cauponi appears to function as a descriptor attached to the name, not a surname. It describes something about Peter, not who his ancestors were.

The safest way to read this record is NOT “Peter Peterson Cauponi” as a full name, but rather “Peter Peterson, an innkeeper.”

How Descriptors Turn Into Ancestors

Example from Ancestry Tree

Problems arise when descriptive terms like cauponi are lifted out of their original context and placed into family trees. Once entered as a surname or middle name, the descriptor begins to look like evidence of ancestry. 

Over time, repetition across multiple trees can give the appearance that a conclusion is well established, when in fact it rests on a misunderstanding of how the record functions.

Why I Chose to Stop

This is the point where I have chosen to stop extending my own tree. Where records clearly state relationships, I use them. Where records introduce descriptive language that later becomes treated as a surname or proof of ancestry, I document the record itself but stop short of turning that descriptor into an ancestor.

This means my tree looks less complete than many others. It has fewer names filled in and more notes explaining uncertainty. That is intentional. I would rather leave a branch unfinished than attach it to the wrong family.

Genealogy is not just about how far back a tree can go. It is about understanding what records actually say, how they were created, and where their limits lie. Knowing when to stop is not a failure of research. It is part of doing the work responsibly.

Sources

1. “Delaware, U.S., Baptisms, 1697–1886,” database, Ancestry.com (https://www.ancestry.com : accessed 13 January 2026); original data from FamilySearch, “Delaware Baptisms, 1697–1886,” Salt Lake City, Utah.

2. FamilySearch Wiki, “Latin Genealogical Word List,” explaining Latin usage and descriptive terms in church records,
   https://www.familysearch.org/en/wiki/Latin_Genealogical_Word_List
   (accessed 13 January 2026).

3. Steve Peterson, profile for John Peterson (father of Robert Peterson), “Peterson and Hay Ancestry,” Ancestry.com,
   https://www.ancestry.com/family-tree/person/tree/10236187/person/-674227071/facts
   (accessed 13 January 2026; subscription required).