A research workflow with prompts

Literature Review Workflow

Eight steps from the review plan to the draft: searching, citation networks, critical reading, the matrix, the gaps, then writing.

  • Steps: 8
  • Difficulty level: Intermediate
  • Estimated time: 4 to 10 weeks.
  • Target audience: Master's and PhD students and researchers.

A workflow for writing the literature review chapter or a narrative review paper in an organised, traceable way, starting with a plan and ending with a draft built on synthesis rather than narration.

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: The review plan

    2 days

    Define the themes, terms, sources and stopping criterion.

    Required inputs

    • The topic and purpose

    Expected output

    • A review plan

    Step prompt

    Show the prompt text here
    You are an academic librarian and an expert researcher in [Specific field].
    
    My topic: [Research topic]
    Purpose of the review: [Purpose of the review]
    Target time period: [Time period]
    
    I need a review plan that includes:
    1. 4 to 6 sub-themes for the review, with a guiding question for each theme.
    2. For each theme: main search terms and their synonyms in English and Arabic, and terms to exclude.
    3. Databases and search engines suited to this field, with the reason for choosing each (without claiming record counts).
    4. Inclusion and exclusion criteria (study type, language, period, venue quality).
    5. How to organise the sources: the fields I will record for each study.
    6. A "saturation" criterion: when to stop searching.
    7. A weekly timeline over [Number of weeks available] weeks.
    
    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
  2. Step 2: Search strategy

    3 days

    Build structured search queries for each database.

    Required inputs

    • The themes and terms

    Expected output

    • Documented queries

    Step prompt

    Building a Boolean Search Strategy

    Turns your research question into concepts, synonyms and Boolean operators, adapts the search string to each database, and plans a sensitivity test.

    Literature reviewAdvanced
    Show the prompt text here
    You are a medical and academic librarian specialising in building search strategies for systematic reviews.
    
    Research question: [Research question]
    Field: [Specific field]
    Target databases: [Databases]
    Limits: [Limitations]
    
    Required:
    1. Break the question into 2 to 4 main concepts.
    2. For each concept: free-text terms and their synonyms, spelling variants (British/American), truncation (*) and phrases in quotation marks, and controlled vocabulary terms (such as MeSH) where they apply, reminding me to check them in the thesaurus.
    3. Write the full query: OR within a concept, AND between concepts.
    4. Adapt the string to each listed database with its fields (such as TITLE-ABS-KEY in Scopus), noting the differences.
    5. Suggest a way to test sensitivity: a list of known reference papers that the query must find.
    6. A search log table (database, date, query, number of results) that I will fill in myself.
    
    [Reference papers you know]
    
    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.
    - Do not state expected numbers of results; I will run the queries myself.
    
    Write the answer in [Answer language].
    Customise the variables on the prompt page

    Research tools for this step

    Next step
  3. Step 3: Exploring citation networks

    1 week

    Expand the search from key papers.

    Required inputs

    • Seed papers

    Expected output

    • Additional papers

    Step prompt

    Show the prompt text here
    You are an expert researcher in bibliometrics and citation network analysis in [Specific field].
    
    My topic: [Research topic]
    
    The seed papers I chose (title, year and, if possible, DOI):
    [Seed papers]
    
    [Your notes on the resulting map]
    
    Required:
    1. Assess the seed papers: do they cover the essential aspects of the topic? Which missing aspect needs an additional seed paper (describe the kind of paper needed without inventing a title)?
    2. A staged exploration plan: backward citations (references), forward citations (who cited them) and similar papers, with a stopping criterion for each stage.
    3. Criteria for screening what the tools suggest: relevance, recency, study type.
    4. If I give notes about the resulting map: interpret the likely clusters, the bridging papers between clusters and the trend over time, based only on what I wrote.
    5. A table template for recording what is found.
    
    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
  4. Step 4: Critical reading

    2 to 4 weeks

    Create a reading card for each important paper.

    Required inputs

    • The papers' texts

    Expected output

    • Reading cards

    Step prompt

    Structured Critical Summary of a Paper

    Summarises a paper whose text you provide into a structured card: problem, method, data, results, limitations, strengths and weaknesses, keeping the authors' claims separate from the model's assessment.

    Literature reviewIntermediate
    Show the prompt text here
    You are an expert reviewer in [Specific field].
    
    I will give you the text of a research paper (or its main parts) inside the <paper> tag.
    
    <paper>
    [Paper text]
    </paper>
    
    My purpose in reading it: [Your purpose in reading]
    
    Create a critical reading card with the following sections:
    1. Bibliographic details exactly as they appear in the text (leave anything missing blank).
    2. The problem and the research question.
    3. Method and design, and the data or sample (size, source, characteristics).
    4. Main results with the figures exactly as reported.
    5. Limitations stated by the authors.
    6. Your critical assessment (separate and clearly headed): internal and external validity, possible data leakage or bias, suitability of the evaluation metrics, and reproducibility.
    7. The paper's relevance to my purpose, and what it can be cited for.
    8. Three open questions the paper raises.
    For every point in sections 2 to 5, add a short quote from the text in quotation marks.
    
    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: Building the matrix

    1 week

    Collect the cards into a single matrix.

    Required inputs

    • The reading cards

    Expected output

    • Literature matrix

    Step prompt

    Show the prompt text here
    You are an expert researcher in [Specific field], experienced in the critical synthesis of literature.
    
    My topic: [Research topic]
    
    The studies (numbered abstracts or reading cards):
    <studies>
    [Studies]
    </studies>
    
    Required:
    1. A literature matrix as a table with the columns: [Matrix columns].
    - Write "not reported" when the information is missing, and do not guess it.
    2. Analysis of the matrix:
    - Patterns of agreement (with the study numbers).
    - Contradictions and their possible explanations (differences in data, method, metrics).
    - Trends over time in methods or results.
    - What all the studies overlook.
    3. Propose a thematic structure (not study by study) for writing the review, based on the matrix.
    
    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
  6. Step 6: Analysing the matrix and the structure

    2 days

    Extract the patterns and contradictions and propose a thematic structure.

    Required inputs

    • The matrix

    Expected output

    • The review structure

    Step prompt

    Show the prompt text here
    You are an expert researcher in [Specific field], experienced in the critical synthesis of literature.
    
    My topic: [Research topic]
    
    The studies (numbered abstracts or reading cards):
    <studies>
    [Studies]
    </studies>
    
    Required:
    1. A literature matrix as a table with the columns: [Matrix columns].
    - Write "not reported" when the information is missing, and do not guess it.
    2. Analysis of the matrix:
    - Patterns of agreement (with the study numbers).
    - Contradictions and their possible explanations (differences in data, method, metrics).
    - Trends over time in methods or results.
    - What all the studies overlook.
    3. Propose a thematic structure (not study by study) for writing the review, based on the matrix.
    
    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
  7. Step 7: Identifying the gap

    2 days

    Extract the gap your research addresses, with its evidence.

    Required inputs

    • Abstracts and limitations

    Expected output

    • An evidence-based gap

    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

    Tools linked to this step's prompt.

    Next step
  8. Step 8: Writing the review

    2 weeks

    Write the review by theme and end with the gap.

    Required inputs

    • The matrix
    • The structure
    • The gap

    Expected output

    • Draft review

    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