Systematic literature search strategy with Boolean search strings
Plan the search for a systematic or scoping review: concept blocks, synonyms, subject headings, database-specific Boolean strings, inclusion criteria and a PRISMA log. Designed for ChatGPT, Claude, Gemini and Perplexity. It includes 5 customizable variables and you can copy it for free in one click.
Advanced · Text · Pending editorial review
Prompt
Act as an information specialist for systematic reviews, experienced with PubMed, Scopus, Web of Science and subject databases.
Context:
- Review question: {{question}}
- Discipline: {{discipline}}
- Available databases: {{databases}}
- Date range and languages: {{date_range}}
- Review type: {{review_type}}
Deliverables:
1. Concept blocks: split the question into 2-4 key concepts (for example, by PICO) and explain which concept is better left out of the search so sensitivity is not lost.
2. For each concept: free-text terms, synonyms, spelling variants, acronyms, truncation and, where relevant, controlled vocabulary (MeSH, Emtree, ERIC Thesaurus or another suitable one).
3. A full search string for each database listed, with the correct syntax for each one (field tags, proximity operators, truncation) and properly nested parentheses.
4. Justified filters and limits (dates, languages, study types) and the risks of applying them.
5. Inclusion and exclusion criteria in a table, ready for title and abstract screening.
6. Supplementary sources: grey literature, trial registries, repositories, hand-searching reference lists and citation chasing.
7. Quality check: how to test the search's sensitivity against a set of key articles I provide (if I do not provide them, ask me for them) and how to adjust the string if any are missed.
8. A search log template (database, date, string, hits) and a PRISMA flow diagram template to document the process.
Constraints:
- Do not cite specific articles or hit counts: you cannot run the search. Leave results as [FILL IN].
- Warn that every subject heading must be checked in the official thesaurus before use; if you are not sure a heading exists, mark it [FILL IN: verify in thesaurus].
- If the question is too broad or ambiguous, suggest how to narrow it before building the strings.
Format: a table of concepts and terms, code blocks with each database string, a criteria table and the final templates.How to use it
Have your review question defined first. Paste each string into its database, check the subject headings in that database's thesaurus and record the hits in the log. For a thesis or publication, have your university librarian review the strategy.
Usage example
Question: effectiveness of online CBT for adults with insomnia · Databases: PubMed, Scopus, PsycINFO · Range: 2010-2025, English and Spanish · Type: systematic.
Sample output
1. Concept blocks
| Concept | Include in search |
|---|---|
| Insomnia | Yes |
| CBT | Yes |
| Online delivery | Yes |
| Face-to-face comparator | No: handle it at screening; adding it to the string lowers sensitivity |
2. Terms
- Insomnia: insomnia*, "sleep initiation and maintenance disorders" [FILL IN: verify in MeSH]
- CBT: "cognitive behavio*", CBT-I, CBTI
- Online: internet*, online, web-based, digital, app, smartphone
3. PubMed string
("Sleep Initiation and Maintenance Disorders"[Mesh] OR insomnia*[tiab])
AND ("Cognitive Behavioral Therapy"[Mesh] OR "cognitive behavio*"[tiab] OR CBT-I[tiab])
AND (internet[tiab] OR online[tiab] OR web-based[tiab] OR digital[tiab] OR smartphone[tiab])
AND 2010:2025[dp] AND (english[la] OR spanish[la])
Check every MeSH heading in the official thesaurus before use. Translate the syntax for Scopus (TITLE-ABS-KEY) and PsycINFO (APA Thesaurus descriptors).
5. Eligibility criteria
| Criterion | Include | Exclude |
|---|---|---|
| Population | Adults (≥ 18) with insomnia | Insomnia secondary to [FILL IN] |
| Design | Controlled trials | Case series, opinion pieces |
8. Search log
| Database | Date | String | Hits |
|---|---|---|---|
| PubMed | [FILL IN] | String 1 | [FILL IN] |
…
Key facts
- Category
- Research · Literature review
- Output type
- Text
- Level
- Advanced
- Designed for
- ChatGPT, Claude, Gemini and Perplexity
- Verified in
- Pending editorial verification
- Variables
- Review question, Discipline, Available databases, Date range and languages and Review type
- Language
- English
- Price
- Free, no sign-up
- Updated
- Nov 7, 2026
Frequently asked questions
Why not put every concept of the question into the search?
Each block joined with AND cuts results. Some concepts, such as study design or outcome, are better handled at screening so you do not lose relevant but poorly indexed articles.
Can I reuse one string across all databases?
No. Each database has its own syntax and controlled vocabulary: MeSH in PubMed, Emtree in Embase and so on. The prompt adapts the string to each one.
What is the key-article test?
You check that the search retrieves a set of studies you already know are relevant. If one is missing, you look for the term that would have caught it.
What is this prompt for?
Plan the search for a systematic or scoping review: concept blocks, synonyms, subject headings, database-specific Boolean strings, inclusion criteria and a PRISMA log.
Which AI tools does it work with?
It is designed for ChatGPT, Claude, Gemini and Perplexity. We have not verified it in these tools yet, so results may vary between them.
How do I customize the prompt?
Click “Customize” and fill in the variables (Review question, Discipline, Available databases, Date range and languages and Review type). The text updates instantly and you can then copy it in one click. Values are stored only in your browser.
Do I need experience to use it?
It is advanced: it is meant for people with experience in the topic who can evaluate and adjust the result.
Is this prompt free?
Yes. Every HomeCasa Prompts prompt is free, with no sign-up or subscription. You can also use them in professional projects.
Can I trust the AI output?
Treat it as a high-quality draft: always check data, figures and important claims before publishing or making decisions.