A research workflow with prompts

PhD Dissertation Workflow

From a broad idea to a complete dissertation in 12 linked steps, each step building on the outputs of the one before.

  • Steps: 12
  • Difficulty level: Expert
  • Estimated time: It spans the period of study; the first six steps usually fall in the first year.
  • Target audience: PhD students and their supervisors; it also suits master's students with some steps shortened.

This workflow brings the library's prompts together in a logical sequence for the stages of a dissertation: choosing the topic, the gap, the problem, the questions, the proposal, the literature, the method, the experiments, the analysis, the writing, the proofreading and then the abstract. Carry the outputs of each step into the next step as input, and review every output with your supervisor.

You can copy the prompt of any step and use it on its own without completing the workflow. The “I finished this step” mark is saved in your browser only.

  1. Step 1: Generating research ideas

    1 week

    Start from a broad interest and realistic constraints to get feasible ideas.

    Required inputs

    • The broad interest
    • Time, resources and skills

    Expected output

    • 6 rated ideas
    • 2 recommended ideas

    Step prompt

    Show the prompt text here
    You are an expert research advisor in [Specific field] who supervises [Stage or type of work] students.
    
    I want research ideas within this broad interest:
    [Broad research interest]
    
    What I have available:
    - Time available for the research: [Time available]
    - Available data or resources: [Available data or resources]
    - My current skills: [Your current skills]
    - [Additional information]
    
    Required:
    1. Propose 6 specific research ideas (not generic titles). For each idea:
    - A clear working title.
    - The main research question in one sentence.
    - Why it may matter now (give the reasoning; do not cite figures or studies you have not verified).
    - The likely data or method.
    - The main risks (data, time, ethics, topic saturation).
    2. Rate the ideas in a table with the columns: feasibility, likely originality, fit with the time available, fit with my skills (low/medium/high), with a brief justification.
    3. Recommend two ideas to start with and give the first three steps to check the originality of each in academic databases.
    
    Academic integrity rules (mandatory):
    - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed].
    - Do not claim to have read a study or file whose text I have not given you.
    - Clearly separate what comes from the material I provided from your own conclusions and suggestions.
    - If you are missing essential information, ask me for it before continuing instead of assuming it.
    - Originality here is only a preliminary estimate and must be tested by searching the literature; tell me this explicitly.
    
    Write the answer in [Answer language].
    Customise the variables on the prompt page

    Research tools for this step

    Next step
  2. Step 2: Research gap analysis

    2 to 3 weeks

    Collect the abstracts of the closest studies and analyse the gaps with their evidence.

    Required inputs

    • 10 to 30 abstracts

    Expected output

    • Classified gaps with their evidence
    • 2 proposed questions

    Step prompt

    Show the prompt text here
    You are a senior researcher in [Specific field] specialising in critical literature reviews.
    
    My topic: [Research topic]
    
    Below I will give you abstracts or excerpts (limitations and future work) from studies I collected myself. Each study is preceded by a number.
    
    <studies>
    [Study abstracts or excerpts]
    </studies>
    
    Required:
    1. A table of the studies: number, aim, method, data or sample, main findings as reported, stated limitations.
    2. Extract the research gaps and classify them: (methodological, data, geographic or linguistic context, theoretical, applied, evaluation). For each gap:
    - A precise description in two sentences.
    - The numbers of the studies that support it, with a short quote from the text provided.
    - Strength of the evidence that the gap exists: strong / moderate / weak, and why.
    3. Clearly distinguish between a gap "explicitly stated in the studies" and a gap "inferred by you".
    4. Propose two research questions for the two strongest gaps, and what to search for to confirm nobody has closed them yet.
    
    Academic integrity rules (mandatory):
    - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed].
    - Do not claim to have read a study or file whose text I have not given you.
    - Clearly separate what comes from the material I provided from your own conclusions and suggestions.
    - If you are missing essential information, ask me for it before continuing instead of assuming it.
    - Rely only on the texts inside <studies>. Do not add studies from your memory.
    
    Write the answer in [Answer language].
    Customise the variables on the prompt page

    Research tools for this step

    Next step
  3. Step 3: Formulating the research problem

    3 days

    Turn the strongest gap into a convincing research problem.

    Required inputs

    • The chosen gap
    • Documented evidence

    Expected output

    • A research problem in two versions

    Step prompt

    Writing a Research Problem Statement

    Builds a coherent research problem from five elements: context, the ideal situation, the reality, the gap and the impact, flagging the places that need sources.

    Preparing the plan and proposalIntermediate
    Show the prompt text here
    You are an academic supervisor in [Specific field] who reviews the research proposals of [Stage or type of work] students.
    
    Help me formulate the research problem for this topic:
    [Research topic]
    
    The research gap I identified:
    [Research gap]
    
    [Documented evidence or figures you have]
    
    Required:
    1. Formulate the research problem using the structure: (a) general context, (b) desired situation, (c) current reality and what is missing, (d) the specific gap, (e) the impact of not addressing it, (f) what this research will contribute.
    2. Give two versions: a short one (120 to 150 words) and a detailed one (300 to 400 words).
    3. Put [source needed] after every factual or numerical claim for which I have not provided evidence.
    4. End with a list of 5 critical questions a defence committee member might ask about this wording.
    
    Academic integrity rules (mandatory):
    - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed].
    - Do not claim to have read a study or file whose text I have not given you.
    - Clearly separate what comes from the material I provided from your own conclusions and suggestions.
    - If you are missing essential information, ask me for it before continuing instead of assuming it.
    
    Write the answer in [Answer language].
    Customise the variables on the prompt page

    Research tools for this step

    Tools linked to this step's prompt.

    Next step
  4. Step 4: Questions, objectives and hypotheses

    3 days

    Derive the questions and objectives and check their consistency.

    Required inputs

    • Research problem

    Expected output

    • Questions, objectives and hypotheses
    • A consistency matrix

    Step prompt

    Show the prompt text here
    You are an expert in research methodology in [Specific field].
    
    Research problem:
    [Research problem]
    
    Expected type of research: [Type of research]
    
    Required:
    1. One main research question, precisely worded.
    2. Three to five sub-questions that cover the main question without overlapping.
    3. An objective for each sub-question in SMART form (measurable verb, scope, output).
    4. Null and alternative hypotheses [Do you need hypotheses?], with the independent, dependent and control variables.
    5. A consistency matrix: question → objective → data required → measurement tool or method → analysis method.
    6. Warn me about any question that cannot be answered with the stated resources or method.
    
    Academic integrity rules (mandatory):
    - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed].
    - Do not claim to have read a study or file whose text I have not given you.
    - Clearly separate what comes from the material I provided from your own conclusions and suggestions.
    - If you are missing essential information, ask me for it before continuing instead of assuming it.
    
    Write the answer in [Answer language].
    Customise the variables on the prompt page

    Research tools for this step

    Tools linked to this step's prompt.

    Next step
  5. Step 5: Research proposal

    2 weeks

    Combine the above into a research proposal with your university's sections.

    Required inputs

    • The problem, questions and initial method

    Expected output

    • Draft research proposal
    • A timeline

    Step prompt

    Writing a Thesis Research Proposal

    Builds a complete draft research proposal following your university's requirements, and identifies what is missing before you submit it to the seminar or graduate committee.

    Preparing the plan and proposalAdvanced
    Show the prompt text here
    You are an expert academic supervisor in [Specific field] who has supervised dozens of [Stage or type of work] proposals.
    
    What I have prepared so far:
    - Working title: [Working title]
    - Research problem: [Research problem]
    - Questions and objectives: [Questions and objectives]
    - Proposed method: [Proposed method]
    
    Sections required at my university:
    [Required proposal sections]
    
    Required:
    1. A complete draft proposal with these sections, in coherent academic language.
    2. In the literature review section, give only a structure of themes with [sources needed] and do not write references.
    3. A timeline (text Gantt chart) over [Duration in months] months.
    4. An "expected contribution" section with modest, defensible claims.
    5. A final checklist: what the proposal is missing, and any inconsistency between sections.
    
    Academic integrity rules (mandatory):
    - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed].
    - Do not claim to have read a study or file whose text I have not given you.
    - Clearly separate what comes from the material I provided from your own conclusions and suggestions.
    - If you are missing essential information, ask me for it before continuing instead of assuming it.
    
    Write the answer in [Answer language].
    Customise the variables on the prompt page

    Research tools for this step

    Next step
  6. Step 6: Literature review

    4 to 8 weeks

    Write the review from a literature matrix you prepared.

    Required inputs

    • Literature matrix
    • Themes
    • The gap

    Expected output

    • Draft literature review chapter

    Step prompt

    Show the prompt text here
    You are an expert academic writer in [Specific field].
    
    Write a draft "Literature Review" section on the topic: [Research topic]
    
    The only material you may rely on is the following matrix and references:
    <matrix>
    [Literature matrix]
    </matrix>
    
    Required structure (themes):
    [Themes]
    
    Writing rules:
    1. Organise by theme, not by study. Each paragraph starts with a synthesising idea and is then supported by the studies.
    2. Cite in (author, year) form exactly as it appears in the matrix only.
    3. Compare the studies explicitly: who agrees, who disagrees, and why.
    4. End each theme with a critical sentence, and end the review with a paragraph showing the gap my research addresses: [The gap your research addresses]
    5. Approximate length: [Approximate length] words.
    6. After the draft, add a list of the claims that need an additional reference.
    
    Academic integrity rules (mandatory):
    - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed].
    - Do not claim to have read a study or file whose text I have not given you.
    - Clearly separate what comes from the material I provided from your own conclusions and suggestions.
    - If you are missing essential information, ask me for it before continuing instead of assuming it.
    
    Write the answer in [Answer language].
    Customise the variables on the prompt page

    Research tools for this step

    Next step
  7. Step 7: Choosing and justifying the methodology

    1 week

    Compare the possible methods and choose the most suitable one with a justification.

    Required inputs

    • The questions
    • Practical constraints

    Expected output

    • A justified method
    • Threats to validity

    Step prompt

    Selecting and Justifying a Research Methodology

    Compares the possible methods for your research questions, recommends the most suitable one with a scientific justification, and reveals the weak points a committee may ask about.

    Preparing the plan and proposalAdvanced
    Show the prompt text here
    You are a professor of research methods in [Specific field] and a member of [Stage or type of work] defence committees.
    
    My research questions:
    [Research questions]
    
    Practical constraints: [Practical constraints]
    The method I lean towards (if any): [Preferred method]
    
    Required:
    1. Identify 2 to 3 possible methods or designs for these questions.
    2. Compare them in a table: fit with the questions, type of data, sample or data size required, time, skills, main threats to validity.
    3. Recommend one method and justify the choice in an academic paragraph (about 250 words) that can go into the thesis, with [source needed] where a methodological reference is required.
    4. List the threats to internal and external validity (or credibility and transferability in qualitative research) and how to mitigate each one.
    5. Five difficult questions the committee may ask about the method, with the key points of an answer.
    
    Academic integrity rules (mandatory):
    - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed].
    - Do not claim to have read a study or file whose text I have not given you.
    - Clearly separate what comes from the material I provided from your own conclusions and suggestions.
    - If you are missing essential information, ask me for it before continuing instead of assuming it.
    
    Write the answer in [Answer language].
    Customise the variables on the prompt page

    Research tools for this step

    Tools linked to this step's prompt.

    Next step
  8. Step 8: Designing the experiments

    2 weeks

    Design the experiment and the pre-specified analysis plan.

    Required inputs

    • The hypotheses
    • The resources

    Expected output

    • An experimental design
    • A pre-specified analysis plan

    Step prompt

    Designing a Rigorous Experiment

    Designs a complete experiment: variables, groups, randomisation, controls, sample size (methodologically), procedures and a pre-specified analysis plan.

    Methodology and designAdvanced
    Show the prompt text here
    You are an expert in experimental design and statistics in [Specific field].
    
    Hypothesis or experimental question: [Hypothesis or question]
    Type of experiment: [Type of experiment]
    Resources and constraints: [Resources and constraints]
    
    Design the experiment, including:
    1. The independent variable and its levels, the dependent variable and how it is measured, and the possible control and confounding variables.
    2. The design (between-groups, within-groups, factorial, ...) with justification.
    3. Randomisation and blinding where they apply.
    4. Sample size: the method (statistical power analysis) and the inputs needed (expected effect size, α, power), without inventing an effect size; suggest where I can obtain it.
    5. The procedures step by step.
    6. The pre-specified analysis plan: the main test, handling missing values and outliers, correction for multiple comparisons.
    7. Threats to validity and how to control them.
    8. Ethical considerations.
    9. In computational experiments: random seeds, data splitting, number of repetitions and baselines.
    
    Academic integrity rules (mandatory):
    - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed].
    - Do not claim to have read a study or file whose text I have not given you.
    - Clearly separate what comes from the material I provided from your own conclusions and suggestions.
    - If you are missing essential information, ask me for it before continuing instead of assuming it.
    
    Write the answer in [Answer language].
    Customise the variables on the prompt page

    Research tools for this step

    Tools linked to this step's prompt.

    Next step
  9. Step 9: Choosing the statistical tests

    3 days

    Identify the appropriate tests and their assumptions before the analysis.

    Required inputs

    • The variables and design

    Expected output

    • The tests and their assumptions

    Step prompt

    Choosing the Right Statistical Test

    Identifies the right statistical test for your question, variable types and design, with its assumptions, how to check them, the non-parametric alternative and how to report it.

    Analysis and experimentsIntermediate
    Show the prompt text here
    You are a biostatistician and data analysis consultant in [Specific field].
    
    Research question or hypothesis: [Research question or hypothesis]
    Variables:
    [Variables and the type of each]
    Design: [Design]
    Sample size per group: [Sample size]
    
    Required:
    1. The decision tree you followed step by step to reach the test.
    2. The recommended test, the non-parametric or robust alternative, and when to use each.
    3. The assumptions and how to check each one (a test and a plot), and what to do if they are not met.
    4. The appropriate effect size and how to interpret it, and correction for multiple comparisons if needed.
    5. The steps to run it in [Software].
    6. A template for reporting the result in APA style with blanks for the figures, without invented figures.
    
    Academic integrity rules (mandatory):
    - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed].
    - Do not claim to have read a study or file whose text I have not given you.
    - Clearly separate what comes from the material I provided from your own conclusions and suggestions.
    - If you are missing essential information, ask me for it before continuing instead of assuming it.
    
    Write the answer in [Answer language].
    Customise the variables on the prompt page

    Research tools for this step

    Next step
  10. Step 10: Writing the dissertation chapters

    3 to 6 months

    Write each chapter from your notes and results, one chapter at a time.

    Required inputs

    • Notes and results for each chapter

    Expected output

    • Chapter drafts

    Step prompt

    Show the prompt text here
    You are an expert academic editor in [Specific field].
    
    Write a draft of the "[Required section]" section of a [Document type].
    
    The raw material (my notes and results, the only source of content):
    <notes>
    [Your notes and results]
    </notes>
    
    The required structure of the section (if any):
    [Section structure]
    
    Writing rules:
    1. Do not add any information, figure or result that is not in <notes>.
    2. Where a reference is needed write [source needed], and where information is missing write [missing information: ...].
    3. Keep to academic style: paragraphs that start with a topic sentence, clear transitions, and verb tenses suited to the section.
    4. Approximate length: [Approximate length] words.
    5. After the draft: a list of the marked places, and three suggestions to strengthen the section.
    
    Academic integrity rules (mandatory):
    - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed].
    - Do not claim to have read a study or file whose text I have not given you.
    - Clearly separate what comes from the material I provided from your own conclusions and suggestions.
    - If you are missing essential information, ask me for it before continuing instead of assuming it.
    
    Write the answer in [Answer language].
    Customise the variables on the prompt page

    Research tools for this step

    Tools linked to this step's prompt.

    Next step
  11. Step 11: Proofreading and style editing

    2 to 4 weeks

    Proofread the chapters in parts and approve the changes yourself.

    Required inputs

    • Chapter drafts

    Expected output

    • Proofread text
    • A table of changes

    Step prompt

    Show the prompt text here
    You are a proofreader and academic editor specialising in [Specific field] texts written in [Text language].
    
    Level of intervention: [Level of intervention]
    
    Text:
    <text>
    [Text]
    </text>
    
    Required:
    1. The text after proofreading.
    2. A table of changes: the original, the change, the type (grammar, spelling, punctuation, style, terminology, clarity) and the reason in one sentence.
    3. General notes: recurring mistakes in my writing and how to avoid them.
    4. Any sentence with an unclear meaning that you did not change because changing it might alter the meaning; ask me about it.
    
    Constraints:
    - Do not change the scientific meaning, do not add information or references, and do not delete content.
    - Keep technical terms as they are unless they are wrong, and make them consistent across the whole text.
    - Do not turn the style into overly ornate prose.
    Customise the variables on the prompt page

    Research tools for this step

    Tools linked to this step's prompt.

    Next step
  12. Step 12: Abstract in Arabic and English

    2 days

    Write the two equivalent abstracts after the results are complete.

    Required inputs

    • The title, results and conclusion

    Expected output

    • Two abstracts and keywords

    Step prompt

    Show the prompt text here
    You are a bilingual (Arabic and English) academic editor specialising in [Specific field].
    
    Thesis material:
    - Title: [Thesis title]
    - Problem and aim: [Problem and aim]
    - Method and data: [Method and data]
    - Main results (figures exactly as they are): [Main results]
    - Conclusion and the most important recommendation: [Conclusion and recommendation]
    
    Required:
    1. An Arabic abstract of up to [Maximum number of words] words, in the order: background, aim, method, results, conclusion.
    2. An English abstract equivalent in content (not a literal translation) with the same limit.
    3. 5 to 6 keywords in each language.
    4. A table of the terms used in both abstracts (Arabic ↔ English) to make sure they are used consistently in the thesis.
    5. Check: the word count of each abstract, and any information that appears in one but not the other.
    
    Academic integrity rules (mandatory):
    - Do not invent references, author names, DOIs, links, experimental results or statistics. Where a source is needed, write [source needed].
    - Do not claim to have read a study or file whose text I have not given you.
    - Clearly separate what comes from the material I provided from your own conclusions and suggestions.
    - If you are missing essential information, ask me for it before continuing instead of assuming it.
    - Use the figures exactly as I provided them.
    Customise the variables on the prompt page

    Research tools for this step

    Tools linked to this step's prompt.