As genealogists, we often get excited about diving into records and searching for clues about our ancestors. However, taking the time to create a solid research plan can make our efforts much more productive. In this post, we’ll explore the elements of effective research planning and how artificial intelligence (AI) tools can assist in the process.

Why Research Planning Matters

Research planning helps us:

• Stay focused on our research objective
•  Pick up where we left off if our work is interrupted
• Approach problems systematically, like experts do

 

Elements of a Research Plan

A thorough research plan typically includes:

1. Objective
2. Summary of Known Facts
3. Working Hypothesis
4. Identified Sources
5. Prioritized Research Strategy

Let’s examine each of these elements in more detail using my case study to research Isabella Weatherford in Texas in the mid-1800s.

Example: Isabella Weatherford Research Plan

1. Research Objective

Your objective should clearly state what you aim to discover. In part one of this series, I discussed how I used AI to write the following objective for my project on Isabella Weatherford.

The objective of this research phase is to examine the economic and social conditions in Dallas County, Texas, in the early 1870s and their influence on Isabella D Weatherford’s life and marriage prospects. Isabella was born on 4 Mar 1858 in Missouri; she first married John H. Carpenter on 16 Jan 1874 in Dallas County, Texas, then later married Robert Cisnie Royston on 16 Jan 1877 in Van Zandt County, Texas, and died on 9 May 1942 in Tucumcari, Quay County, New Mexico.

2. Summary of Known Facts

This section outlines what you already know about your research subject based on previous research. AI tools can help summarize timeline data into a concise list of facts. In part 2 of this series, I show how I used AI to transcribe and organize a 57-page widow’s pension file for Isabella. I added the relevant details to my Airtable timeline and then saved the timeline as a .csv file. I uploaded that file to Claude 3.5 Sonnet and prompted the AI model to create a summary of known facts for me in a table with four columns.

Prompt for Claude 3.5 Sonnet

Claude did a great job creating the summary table, making it easy for me to fact-check the dates and places. I next prompted the model to give me the data in a .csv file, which I imported into a spreadsheet. However, I like to use a bulleted list in my project document, so I asked Claude to create the same information in a bulleted list with source citations, and it complied.

Finally, I copied the bullets into my project document and put the citations into footnotes.

3. Working Hypothesis

A working hypothesis is an educated guess about what might have happened based on the known facts. AI can help generate hypotheses by analyzing the available data and historical context.

I was curious to compare my hypothesis with what AI would create. I wrote:

Isabella’s family moved from Springfield, Missouri, where she was born on 4 March 1858, to Dallas County, Texas, by 3 September 1860, the date of the census enumeration. The Civil War broke out the next year, and Texas joined the Confederacy. This would have affected her family life, with her older brother, John, possibly serving in the military. Reconstruction and the post-Civil War era would have also influenced life in Dallas County. 

The research will need to center on Isabella’s father, Henderson Weatherford, as the records will be in his name. The family has not been located on the 1870 census, so tax records could perhaps lend clarity to the family situation. There is no listing for precinct 6, so the broad Dallas County tax list could be searched.  Henderson worked as a blacksmith in 1860 and perhaps continued the trade. Locating the Weatherford family in 1870 would be helpful.

Isabella married John H. Carpenter on 2 January 1874 in Dallas County, Texas, at the age of 15. He may have traveled to Dallas County on the railroad that arrived in 1872. He may have been a Confederate veteran from any southern state. Their daughter, Mary Clem Carpenter, was born on 3 October 1875. John either died or deserted Isabella by 1877 when she married Robert Cisnie Royston.

I provided Claude with my research objective and the summary of known facts then prompted it to create a hypothesis using sound genealogical methodology. The response was fairly good and included research possibilities I hadn’t considered. I particularly like the ideas highlighted in the response below.

In comparing my hypothesis with the AI-generated one, I noticed the following.

• Diana’s hypothesis
• Used specific names, dates, and places
• Used past research experiences and knowledge that research in this era generally means finding records for the men in a woman’s life
• Focused on the most likely scenario for the people involved
  Isabella, her husband, her father

 

• Claude’s hypothesis
• Provided new ideas such as economic conditions (from the objective)
• Gave broader searches, such as looking for patterns in other marriages and divorces
• Used no specifics although they were in the summary of known facts.

 

4. Identified Sources

In this step of research planning, you list potential sources that may contain information relevant to your objective. This could include census records, marriage records, tax lists, newspapers, and more. AI can suggest sources based on your locality guide and research objective. I wrote about using AI in locality research in part 3 of this series.

I decided to set up a project in Claude for this research planning stage. Note that you need a Pro account to create a project, but I have found it extremely valuable to have this capability in my research. You can read more about projects here: How can I create and manage Projects?

For a project, you create a knowledge base that Claude will draw on for your chat prompts. I copied and pasted my Dallas County, Texas, locality guide as text, then copied the objective, background information, summary of known facts, and my hypothesis into another text box.

Next, I prompted Claude to create a list of sources that could be used in the research. The starred sections in the image below show those that I agreed with. Notice that links were added and reasoning.

5. Prioritized Research Strategy

The final step in research planning is to organize your identified sources into a logical order for research. Consider factors like:

• Likelihood of finding relevant information
• Ease of access to the records
• Time periods covered

 

AI tools can help prioritize sources based on these factors and your specific research goals.

Claude chose the following sources and priority:

1. 1870 Census
2. Dallas County Tax Records
3. Newspapers from Dallas County, Texas
4. Dallas County Deed Records
5. Dallas City directories

 

Using Chat GPT 4o

You may be wondering if I used Chat GPT in this process. I was curious about what ideas it would provide and used the principle of prompt chaining with this strategy:

• Uploaded Isabella’s timeline
• Provided the objective
• Gave a sample hypothesis
• Pasted in the historical information from the timeline
• Asked for a hypothesis
• Uploaded a PDF of the locality guide
• Asked for a research strategy
• Asked for a prioritized research strategy

 

I was pleased with the final results and agreed with the sources highlighted below.

Of course, I also created my own research priority according to time, record accessibility, and relevance. I used my years of experience researching in Texas, my hypothesis, and my intuition. In comparing my strategy to Claude and ChatGPT, each model had three of the same sources I chose and two different ones.

Using AI in Research Planning

While AI can be a powerful assistant in the research planning process, it’s important to remember:

• AI does not replace your research experience or intuition
• Always verify AI-generated information against reliable sources
• Provide the AI with thorough context (objective, timeline, locality guide) for best results
• Use AI to generate new ideas and perspectives you may not have considered

 

Taking the time to create a thorough research plan can greatly enhance the effectiveness of your genealogy research. I found that involving AI in appropriate ways gave me a new perspective. If we’ve been researching for many years, we may use the same strategy for each type of problem, and AI can help us see a different way of solving our challenge.

Best of luck in all your genealogical endeavors!

Research Like a Pro with AI Series

Using AI to Find Research Questions and Write Objectives: Isabella Weatherford Project Part 1

Using AI in Timeline Creation and Source Analysis: Isabella Weatherford Project Part 2

Using AI in Locality Research: Isabella Weatherford Project Part 3

Using AI in Research Planning: Isabella Weatherford Project Part 4

Learn more about using AI tools in our hands-on workshop, Research Like a Pro with AI.