peopleanalyst

Tools · Marketing

Personas

Turn any research, transcript, or market notes into structured personas.

How it works

Single extraction pass; only what the source evidences (no invented specifics); model self-assesses confidence/completeness; provenance on every record.

You bring

{ text, sourceId?, title? } — raw text is first-class

You get

PersonaCanonical[] (demographics · psychographics · behaviors · goals · pain points · use cases)

Use it for

See it work

example output

Source: 12 customer-interview transcripts for a cloud scheduling tool sold to independent dental practices.

Personas — extracted from dental-practice interview transcripts

2 personas extracted from source: dental-scheduling-interviews-2026. Only what the transcripts evidenced; confidence/completeness self-assessed per record.

Persona 1 — "Front-Desk Dana"

Role: Practice coordinator / front-desk lead · confidence: high · completeness: complete

The person who actually lives in the schedule all day. Owns booking, confirmations, and the no-show fallout. Pragmatic, not technical; judges software by how fast it gets her off the phone.

Demographics: age 30–45 · job title: practice coordinator · industry: dental · company size: 1–3 chairs · years experience: 5–10 Psychographics: values reliability over features; attitudes: skeptical of "all-in-one" promises; interests: anything that reduces phone tag Behaviors: triggers — a morning of back-to-back cancellations; routines: confirms next-day appointments by hand every afternoon Goals: primary — cut no-shows; motivations — stop being the bottleneck the dentist blames Pain points: primary — patients ignore voicemail reminders; frustrations — re-keying the same data into three systems

Use caseuc-1 Reduce next-day no-shows — sends batched SMS confirmations the afternoon before; expected outcome: fewer empty chairs by 8am · frequency: daily · priority: high

Persona 2 — "Owner-Dentist Raj"

Role: Practice owner / clinician · confidence: medium · completeness: partial

Buys the software but doesn't touch it. Cares about chair-utilization and whether the tool pays for itself. Time-poor; delegates the evaluation to Dana but signs the check.

Demographics: age 38–55 · job title: owner-dentist · company size: 1–3 chairs Goals: primary — protect revenue per chair-hour; aspirations — open a second location without adding admin headcount Pain points: primary — can't see utilization across days; concerns — switching cost and staff retraining

Provenance: single extraction pass; no specifics invented beyond the transcript evidence.

Run it on your data

Call it on your own inputs — over the API, or hand it to your AI agent via MCP. Discovery is open; running it is metered.

REST  POST /api/bicycle/personas
MCP   generate_personas

← All tools