Formulating a Historical Research Question

Switzerland and the Council of Europe

Methods
A guided exercise on the systematic development of an analytical historical research question, with a considered use of generative AI.
Author
Affiliation

Moritz Mähr

University of Bern

Published

December 29, 2025

Modified

August 16, 2026

WarningAutomated Translation

This exercise was translated automatically from the German original and can contain errors. Consult the original version in case of doubt.

Overview and Didactic Goal

This exercise teaches transferable methodological competencies for the development of historical research questions. The goal is not to generate the “right” question. The goal is the controlled and considered interplay between your own historical thinking and an exploration with AI.

One shared case study stands at the centre: Switzerland and the Council of Europe.

The exercise follows a circular understanding of research: you can revise the result of a single step, and you should.

NoteNote on the search online

Digitization advances, but historical research is not possible online alone. Secondary literature that is out of print, and primary sources that no one has catalogued yet, often demand a physical search in libraries and archives. Plan your access (library, interlibrary loan, archive). Note that platforms and catalogues structure visibility through their logic of cataloguing, and that they guarantee no completeness. (Putnam 2016) Digital source criticism demands particular attention to the creation and the curation of online collections. (Fickers and Tatarinov 2022)

At a Glance

Item Value
Duration about 90 minutes
Level Beginner
Core path 1 → 2 → 4 → 5 → 6
Optional deepening 3 (the state of research and the gaps in research)
Hand-in (minimum) One research question. AI log: 5 entries.

The core path leads you to a research question that you can work on in about 90 minutes. Step 3 costs about 60 minutes more. You practise the state of research in detail in the exercise Literature Research.

What You Need

Subject knowledge

  • A basic understanding of historical research methods
  • Basic knowledge of work with generative AI, above all prompting
NotePrompt Engineering

If prompting is new to you, we recommend that you work through the exercise Prompt Engineering first.

Capabilities of the AI system

The system must be able to do the two following things:

  • Search the web and support each finding with an address. You need this in step 2 and in step 4.
  • Deliver an answer in a format that you prescribe, for example as a list of variants.

Other tools and access

  • A file for your AI log.
  • An account for the library catalogue of your university. You use it in step 4 to check which sources exist.

You can do every exercise with AI systems from different makers. What a system can do depends on the product and on your account. Settle the five following points before you start.

Cost

A free account is enough for short text tasks. For some capabilities you need a paid account. This mostly concerns the search on the web, the reading of long files and the built-in reasoning mode. Check first whether your university provides access.

Tools

Check which tools your account unlocks. Can the system search the web? Can it read a file that you upload? Can it call external services? Each exercise names the capabilities that it requires.

The section Check and classify capabilities explains five newer capabilities. It also describes what each capability means for your work with sources.

Memory

Some systems carry over statements from earlier sessions or from a project context. Check the settings for memory, projects and chat history. A new session therefore guarantees no empty context.

Account: institutional or private

Check which account you work with. The rules differ in three points.

Point Account of your institution Private account
Contract Your university concludes it and shares the liability. You conclude it yourself and carry the liability alone.
Training A contract often excludes the use of your inputs. Many providers use inputs for training.
Permitted material The university rules which data you can enter. You have no such rule and carry the risk yourself.

Ask the IT office or the library of your university when you cannot find the rules. Record the answer in your AI log.

CautionCheck every piece of material before you upload it

Do not upload material that you have no right to pass on. An upload leaves your computer and you cannot take it back.

These materials stay outside the AI system:

  • Personal data of living persons, for example from interviews, from private papers or from holdings under a protection period.
  • Digitized items whose terms of use forbid a disclosure.
  • Unpublished texts of other persons, for example manuscripts or reviews.
  • Licensed full texts, when the license of your library forbids a disclosure.

In case of doubt, work with a short excerpt or with an anonymized version. You can also use a local model, because the material then stays on your computer.

Law: data protection and disclosure

Two areas of law concern your work directly. This section gives an orientation and no legal advice.

Data protection. In the EU the General Data Protection Regulation applies. In Switzerland the revised Data Protection Act applies (Verordnung (EU) 2016/679 Zum Schutz Natürlicher Personen Bei Der Verarbeitung Personenbezogener Daten (Datenschutz-Grundverordnung) 2016, Bundesgesetz Über Den Datenschutz (DSG) 2020). Both laws protect personal data of living persons. The text of the law itself is binding. Article 6 GDPR requires a legal basis for every processing operation, and an upload is a processing operation.

The role of the provider decides the classification. A provider can act as a processor and process your data only on your behalf. Article 4 point 10 GDPR expressly excludes a processor from the third parties. This role needs a contract under Article 28 GDPR. Without such a contract, a provider uses your inputs for its own purposes. An upload is therefore not always a disclosure to a third party, but without a contract you must assume that it is. Check the contract that applies to your account.

Research is subject to safeguards, but it gets no exemption. Article 89(1) GDPR requires appropriate safeguards, for example data minimisation and pseudonymisation. Article 89(2) GDPR permits the legislator to derogate from single rights of the data subject. The information of the data subjects can also fall away, namely under Article 14(5)(b) GDPR. That applies only when the information proves impossible or would involve a disproportionate effort. Research therefore does not release you from the information duty in general. Settle your individual case with the data protection office of your university.

The European Data Protection Board presented a guideline on research in 2026 (European Data Protection Board 2026). This guideline was in public consultation until June 2026. It is therefore not applicable law, but an aid to interpretation. For deceased persons, the protection periods and the rules of use of the archive apply.

Disclosure. The AI Act of the EU governs the transparency of generated content (Verordnung (EU) 2024/1689 Zur Festlegung Harmonisierter Vorschriften Für Künstliche Intelligenz (Verordnung Über Künstliche Intelligenz) 2024). Article 50 applies from 2 August 2026. It separates two addressees: the provider of an AI system and the deployer. You are a deployer as soon as you use an AI system professionally. For purely private use you are not a deployer, under Article 3 point 4.

As a deployer you carry two separate duties from Article 50(4).

  1. Deep fake. If an AI system generates or manipulates an image, an audio recording or a video, and the content is a deep fake, then you disclose that. Under Article 3 point 60, a deep fake resembles existing persons, places or events and falsely appears authentic. A generated image without this resemblance to reality does not fall under this duty.
  2. Text on public matters. If you publish generated text to inform the public on a matter of public interest, then you disclose that. The duty falls away when a person reviewed the text and holds the editorial responsibility for the publication.

Article 50(4) therefore requires no disclosure for every generated image and for every generated text. Article 50(2) addresses the provider instead. The provider must mark generated content in a machine-readable format. This duty does not lie with you, and it does not replace your own disclosure.

ImportantThe legal disclosure does not replace the academic one

The legal disclosure and the academic disclosure are two separate duties. Your university requires a declaration even when the law requires no disclosure. The exercise Citing shows how you declare your AI use.

Record your answers to these five points. They belong to the description of your work environment.

Learning Objectives

After the exercise you can:

  • tell a topic, a problem statement and an analytical historical research question apart,
  • formulate a precise historical research question that you can work on,
  • use AI systems critically and under methodological control for literature and context work,
  • judge which sources exist and whether a project is feasible in a considered way.

Structure of the Exercise

The exercise is modular. Each step holds:

  • a clear objective,
  • one or several concrete tasks (prompts),
  • a work assignment and a reflection assignment.
  1. Clarify the terms: what is a historical research question?
  2. Set the topic and build a historical overview
  3. The state of research and the gaps in research
  4. Which sources exist, and is the project feasible?
  5. Delimit and formulate the research question
  6. Iterative revision and reflection on the AI use

1. Clarify the Terms: Historical Research Question

Goal

Understand the differences between a topic, a problem statement and an analytical historical research question.

Task (AI Exploration)

What is a historical research question?
Which elements does a historical research question hold?

If the answer holds no description of the process:

Which steps are necessary to develop a historical research question?

Work Assignment (Critical Comparison)

Compare the AI answer systematically with:

Identify:

  • the agreements,
  • the omissions,
  • the shifts or simplifications of terms.

Put targeted follow-up questions to the AI. Insert the element that you miss in the answer. The example names the state of research.

Why is the element "state of research" missing?
Which scholarly or didactic sources does your definition rest on?

2. Set the Topic and Build a Historical Overview

Goal

Separate the topic from the analytical question, and build a solid base of historical knowledge.

Topic Frame (Given)

Switzerland and the Council of Europe

(Optional: find the topic in a dialogue)

You are a historian and you help me in a dialogue to find a historical topic for a student paper.
TipQuestion for reflection

How does this dialogue with an AI differ from a conversation with a teacher or with a fellow student?

Task (Historical Overview)

Give me a historical overview of the relation between Switzerland and the Council of Europe.

Comparison and Critique

Compare the overview with:

Put targeted follow-up questions. Insert the aspect that you miss. Further examples are the European Convention on Human Rights and its court.

Why is the aspect "neutrality" missing?
Which sources does this account rest on?

3. The State of Research and the Gaps in Research

Goal

Tell a descriptive overview apart from an analytical state of research.

Task (Secondary Literature)

Name the central historical secondary literature on the relation between Switzerland and the Council of Europe.

Task (Gaps in Research)

Which open questions or gaps in research exist in the research so far?

Work Assignment

  1. Check the titles that the AI names at https://swisscovery.slsp.ch.

  2. Compare the results with:

Put targeted follow-up questions. Insert the title that you miss in the answer. The example names the edited volume of Altermatt and Casasus.

Why is the work "50 Jahre Engagement der Schweiz im Europarat 1963–2013" missing?

Insert your own question and your own work in the second follow-up question.

Why do you call the question about the role of neutrality a gap in research,
although "50 Jahre Engagement der Schweiz im Europarat 1963–2013" treats it?

4. Which Sources Exist, and Is the Project Feasible?

Goal

Judge whether you can work on a research question on the basis of sources.

Task (Primary Sources)

Replace the example question in the following prompt with your own working question.

Which primary sources suit the study of the research question
"How did neutrality serve between 1949 and 1963 as an argument against an accession
of Switzerland to the Council of Europe?"

If necessary:

Name concrete archives, collections and document types on Switzerland and the Council of Europe.

Comparison with Real Resources

Compare the answer with these resources, among others:

5. Delimit and Formulate the Research Question

Goal

Turn an open problem statement into a precise analytical historical research question.

Possible Dimensions of the Delimitation

  • Time: for example 1949–1963, the Cold War, after 1971
  • Space: Switzerland in a transnational European context
  • Topic: neutrality, human rights, case law, foreign policy, parliamentarism

Task (Delimitation)

Replace the example question in the following prompt with your own working question.

Suggest possible delimitations in time, space and topic for the research question
"How did neutrality serve between 1949 and 1963 as an argument against an accession
of Switzerland to the Council of Europe?"

Task (Formulation)

Formulate an analytical historical research question on this basis.

Quality Check

The research question should:

  • be open and analytical (“how”, “why”, “to what extent”),
  • carry a historical context,
  • look workable with the sources that you can reach.

6. Iterative Revision and Reflection

Goal

Separate the support from the AI from your own research decision deliberately.

Final Task

Note briefly:

  • What did the AI make easier?
  • Where was it misleading, imprecise or too short?
  • Which decisions could only you make?

AI Log

Close your AI log. It holds at least 5 entries, that is one entry per work step with AI.

Learning Outcome

At the end of the exercise you hold:

  • a clearly formulated analytical historical research question,
  • an AI log with at least 5 entries,
  • a considered understanding of the potential and the limits of AI in a research design,
  • a methodologically reasoned judgement on the feasibility of your project.

Further Resources

  • Ranke.2: Wikipedia as Historical Source – Provenance, revision histories and digital source criticism.
  • AI Pedagogy Project: What is AI? – Conceptual introduction for non-technical audiences.
  • Meadows and Sternfeld (2023) – Introduces a journal forum on what AI changes for the methods and the epistemology of history; useful for judging which research decisions stay with the researcher.

Bibliography

Altermatt, Bernhard, and Gilbert Casasus, eds. 2013. 50 Jahre Engagement Der Schweiz Im Europarat 1963–2013: Die Schweiz Als Akteur Oder Zaungast Der Europäischen Integration? Rüegger.
Bundesgesetz Über Den Datenschutz (DSG) (2020). https://www.fedlex.admin.ch/eli/cc/2022/491/de.
European Data Protection Board. 2026. Guidelines 1/2026 on Processing of Personal Data for Scientific Research Purposes. Version 1.0. European Data Protection Board. https://www.edpb.europa.eu/our-work-tools/documents/public-consultations/2026/guidelines-12026-processing-personal-data_en.
Fickers, Andreas, and Juliane Tatarinov. 2022. “Digital Source Criticism: The Case of the Historian’s Craft in the Digital Age.” Journal of Digital History 2 (1): 1–20. https://doi.org/10.1515/jdh-2022-0001.
Meadows, R. Darrell, and Joshua Sternfeld. 2023. “Artificial Intelligence and the Practice of History.” The American Historical Review 128 (3): 1345–49. https://doi.org/10.1093/ahr/rhad362.
Putnam, Lara. 2016. “The Transnational and the Text-Searchable: Digitized Sources and the Shadows They Cast.” The American Historical Review 121 (2): 377–402. https://doi.org/10.1093/ahr/121.2.377.
Verordnung (EU) 2016/679 Zum Schutz Natürlicher Personen Bei Der Verarbeitung Personenbezogener Daten (Datenschutz-Grundverordnung), Amtsblatt der Europäischen Union 1 (2016). https://eur-lex.europa.eu/eli/reg/2016/679/oj/deu.
Verordnung (EU) 2024/1689 Zur Festlegung Harmonisierter Vorschriften Für Künstliche Intelligenz (Verordnung Über Künstliche Intelligenz), Amtsblatt der Europäischen Union (2024). https://eur-lex.europa.eu/eli/reg/2024/1689/oj/deu.
Back to top

Citation

BibTeX citation:
@inreference{mähr2025,
  author = {Mähr, Moritz},
  title = {Formulating a {Historical} {Research} {Question}},
  booktitle = {Critical AI Literacy for Historians},
  date = {2025-12-29},
  url = {https://maehr.github.io/critical-ai-literacy-for-historians/en/exercises/formulating-historical-research-question-switzerland-council-of-europe.html},
  langid = {en}
}
For attribution, please cite this work as:
Mähr, Moritz. 2025. “Formulating a Historical Research Question.” In Critical AI Literacy for Historians. December 29. https://maehr.github.io/critical-ai-literacy-for-historians/en/exercises/formulating-historical-research-question-switzerland-council-of-europe.html.