Yila
All use cases
Literature

Constructs set? Find and adapt validated scales

Settled constructs do not make a survey ready. Yila checks each construct’s definition and boundaries, retrieves the original scale literature — Davis, Jian, Bhattacherjee and more — organizes an evidence matrix separating classic sources from generative-AI studies, then adapts items into your questionnaire with source, rewrite, and rationale logged. Anything not verified against the original text is marked pending — never invented.

These are the constructs I plan to study. First check each one’s definition and boundaries for conceptual overlap — do not write questionnaire items yet.

Boundary check complete: PU, PEOU, trust, and continuance intention are clearly defined with no overlap. One caution flagged: the object of trust should be scoped to students who have actually used generative AI.

Find the established scales for these constructs. Prioritize the original scales and studies from the last five years on students using generative AI. List paper, year, and DOI or link — do not invent sources.

Search complete: 18 sources, all 18 DOIs verified — classic originals include Davis (1989) for PU/PEOU, Jian et al. (2000) for trust, and Bhattacherjee (2001) for continuance intention, plus recent generative-AI studies. Nothing invented.

Search complete: 18 sources, all 18 DOIs verified — classic originals include Davis (1989) for PU/PEOU, Jian et al. (2000) for trust, and Bhattacherjee (2001) for continuance intention, plus recent generative-AI studies. Nothing invented.
Organize these papers into a scale evidence matrix. Separate classic originals, later adaptations, and generative-AI context studies, and tell me which original paper each construct should trace back to first.

The evidence matrix is ready: 21 sources classified as classic originals, follow-up reviews, or generative-AI context studies, with the priority original paper and reason for each construct.

The evidence matrix is ready: 21 sources classified as classic originals, follow-up reviews, or generative-AI context studies, with the priority original paper and reason for each construct.
Draw a simple concept map from these sources: PU, PEOU, and trust pointing to continuance intention. Note the theoretical basis beside each link — do not claim causation.

The concept map is done: the three paths are labeled with their TAM/ECM, TAM-extension, and trust–adoption theoretical links, all marked “to be tested”, with a note that arrows are theoretical paths, not proven causation.

The concept map is done: the three paths are labeled with their TAM/ECM, TAM-extension, and trust–adoption theoretical links, all marked “to be tested”, with a note that arrows are theoretical paths, not proven causation.
Design the item-adaptation workflow. List the source item, construct meaning, contextual rewrite, and rationale. Mark anything not checked against the original text as pending — do not invent a validated scale for me.

The adaptation worksheet is ready: every item lists its source, construct meaning, contextual rewrite, and rationale, and anything not verified against the original is marked “pending verification” — never presented as a validated scale.

Give me a pre-launch validation checklist — back-translation, expert review, cognitive interviews, pilot test, item analysis, reliability, and validity — with what each step solves.

The checklist is ready: back-translation secures semantic equivalence, expert review covers content validity, cognitive interviews catch misreadings, the pilot plus item analysis filter weak items, and reliability and validity testing close the loop — each step maps to a concrete risk.

evidence-matrix.xlsxEvidence matrix · Excel
claim-evidence-map.mdClaim–source map · Markdown
openalex-search-results.csvSearch results · CSV
scale-adaptation-worksheet.csvAdaptation worksheet · CSV
validation-checklist.mdValidation checklist · Markdown
Task completed

Yila task replay complete.

Start with this method