Interviews that compose into findings.
Follow Dev, a UX researcher, running a study on onboarding friction. Themes emerge, hypotheses get tested, contradictions surface across participants.
Dev starts a research study.
Dev, a UX researcher, opens a new Research project: onboarding friction. Interview one with P1 lands on the timeline.
Branches fan out.
Analytical branches: interview summary, pull quotes, signals, surprising moments. Reference material tied to P1.
The research canvas proposes itself.
Dev reviews the AI's proposed Study Canvas: initial themes (just 1-2), one hypothesis, interview subjects list, next steps. He edits a theme, applies. Study v1.
A prior study lands. A persistent branch looks for patterns.
Three more interviews — and Dev drops in a prior onboarding study PDF from Q4 last year so the canvas has historical context. Then he pins an Emerging themes persistent branch: it accumulates patterns across interviews and documents alike, ranking by frequency and flagging early contradictions.
A contradiction surfaces.
Seven interviews in, the Emerging themes branch flags a split: P3 loved the long signup ("felt serious"); P5 called it "corporate." Its parallel canvas shows the quotes side by side.
Dev promotes a research action.
He opens the branch and merges a next-step into the study canvas: "A/B test shorter-signup copy with non-tech users (P9, P10)." The next wave of interviews has a clear hypothesis to probe.
Transcribr is in early access
We're opening up to a small group first. Drop your email and we'll reach out when your spot is ready.
No spam. One email when your access is ready.