A codebook, defined.
A named list of questions. Each with its own instructions.
##analyzing_data
Is this manuscript actively analyzing empirical data?
Answer "Yes" if authors gathered or analyzed data. "No" for protocols, editorials, commentaries.
"Yes" — The abstract reports results from 500 patients.
"Yes"
##patient_level_health_outcomes
Does the analysis involve individual patient-level data to evaluate health outcomes?
Isolates clinical research from economic modeling. "No" for HEOR or cluster-level.
"Yes" — Patients assessed for depressive symptoms via PHQ-9.
"Yes"
##intervention_randomized
Was the intervention individually randomised? Answer "Yes", "No", or "Unclear".
"Yes" if individual participants were randomly assigned. "No" for cluster, single-arm, or pseudo-randomisation.
"Unclear"
· · · more fields below · · ·
A codebook is a list of fields. Each field has a name like ##intervention_type and its own slots: Question, Description, Examples, Default. Descriptions grow as needed — rules, edge cases, references to other fields.
The AI reader reads the whole thing, top to bottom.