Synthesis Matrix Builder
Compare sources side by side.
The Open buttons send the prompt text as currently shown below to that site only when you click. Fill in the placeholders first.
[ADD SOURCE] is an editorial flag, not a blank to fill. Replace or resolve each flag before you use the result.
Help me build a synthesis matrix. My research question: [RESEARCH_QUESTION]. Sources with citations and notes: [SOURCE_NOTES]. Themes I have noticed: [THEMES]. Create a matrix with sources down the side and columns for aim, method, sample, key findings, limitations, and how each source relates to each theme. Fill the cells only from my notes and mark gaps [ADD SOURCE]. Then identify patterns: where sources agree, disagree, or leave gaps. Suggest a structure for a literature review section organised by theme rather than by source, with a topic sentence for each paragraph. Warn against summarising sources one after another. Do not add studies I have not provided. Also add a worked example row for an invented study on remote work and productivity, labelled as an illustration, and a short procedure for reading the finished matrix by column to spot patterns across sources. Include a reminder to record page numbers for any direct quotation I may use later.
Fill in before use
Optional: type your details and the prompt above updates. Nothing is saved or sent.
Replace each bracketed placeholder with your own details, then paste into Any AI or another assistant.
See an example result (fictional data)
Matrix extract (invented studies on remote work) Source | Method | Sample | Finding | Theme: productivity | Theme: wellbeing Study A | Survey | 400 staff | Self-reported productivity higher | Supports | Mixed Study B | Field experiment | 250 call-centre staff | Productivity 13 percent higher [figure from study] | Supports | Not measured Study C | Interviews | 20 managers | Concerns about visibility | Contradicts | Not measured Pattern: evidence on productivity mostly positive; wellbeing under-studied. Gap: small firms.
Illustrative only, made-up data. Your results will differ and must be reviewed.