Research Playbooks
Choose a research task, weigh the routes, and decide what a trustworthy result would look like before you use a tool.
Editorial suggestion — not end-to-end tested. These workflows combine documented capabilities with our suggested research checks. Source review is not independent reproduction, a tool endorsement or a promise of time savings.
4 guides · Human judgment throughout
Literature screening
Move from a search export to a defensible screening ledger, using AI to prioritize attention rather than decide what counts as evidence.
Produce a traceable set of records ready for full-text assessment. This guide covers title-and-abstract screening, not a complete systematic review or an automated synthesis.
Read playbook: Literature screeningQualitative interview analysis
Keep participant meaning, interpretive decisions and disconfirming cases visible while experimenting with coding and summary assistance.
Develop a researcher-owned analytic memo and an evidence-linked set of candidate themes. AI suggestions are provisional readings, not findings or substitutes for qualitative judgment.
Read playbook: Qualitative interview analysisHistorical document transcription
Preserve the link from every reading back to the page, and keep recognition, correction and historical interpretation separate.
Create a corrected, image-linked transcription of a bounded archival sample, with uncertainty and editorial interventions preserved. Searchable text is a working artifact, not proof of an accurate edition.
Read playbook: Historical document transcriptionCausal data analysis
Use causal machine-learning tools only after stating what effect you want to estimate and why your data can identify it.
Produce a reproducible causal-analysis notebook and an assumptions memo, with effect estimates conditional on a defensible design. This is not a recipe for converting predictive accuracy into causality.
Read playbook: Causal data analysisThese guides connect documented resource capabilities with editorial advice. They do not rank tools, certify privacy or reproduce research outcomes. Check each guide’s source scope and decide whether its assumptions fit your project.