Reading a persona profile

The two tabs

Persona detail opens on the Profile tab. The second tab, Interview, is where you have a live conversation with this persona and where session history lives. Everything below describes the Profile tab.

Demographics

A two-column grid at the top with the persona’s identity anchors. Axes vary by audience type. B2C personas typically show age, location, occupation, household, and education. B2B personas show role, seniority, function, company size, industry, and decision authority. If a heritage profile was generated (cultural, regional, or ethnic context that shapes language and decision style), it appears here too.

OCEAN personality

Two views of the same data: a radar chart and five horizontal bars labeled with values from 0.00 to 1.00. The five traits are:

Openness — curiosity, willingness to try new things, abstract thinking.
Conscientiousness — organisation, reliability, planning vs. spontaneity.
Extraversion — social energy, assertiveness, talkativeness.
Agreeableness — cooperation, empathy, willingness to defer.
Neuroticism — emotional reactivity, anxiety, stress response.

These aren’t random. Each value is sampled from peer-reviewed population distributions calibrated by region and, where applicable, occupation. Two personas in the same archetype will sit at different points within the archetype’s OCEAN ranges, which is why they sound different in interviews even when they share a worldview.

Cognitive biases

A list of every bias active in this persona, sorted by intensity (highest first), each rendered as a horizontal bar from 0.00 to 1.00. Biases aren’t labels; they’re calibrated intensities. A persona with loss_aversion 0.78 reacts to potential losses far more strongly than one at 0.32, and that difference shows up consistently across interview turns.

Bias selection and intensity are grounded in research on which biases tend to coexist and which contexts amplify them. They’re not assigned for color. Treat the list as a prediction: this is what you should expect to see in this persona’s reasoning.

Interview behavior

A short collapsible section describing how this persona behaves in conversation: their tendency to elaborate, push back, ask clarifying questions, or get specific. Useful to skim before starting a live interview so you know what to expect.

B2C or B2B profile

A collapsible section with audience-type-specific attributes. B2C personas have fields like life stage, financial pressure, digital fluency, brand sensitivity. B2B personas have fields like buying-center role, internal stakeholders, procurement constraints, evaluation criteria. Each field carries a provenance badge so you can tell where the value came from at a glance.

The four memory types

This is the heart of the profile. Personas have four memory types, each capturing a different aspect of how the person thinks. They persist across interview sessions inside the same project, so the persona genuinely remembers what you’ve discussed.

Identity memory: who they are

Background, role context, environment, and demographic anchors. The narrative version of who this person is and the situation they’re embedded in. Short paragraphs and bullets, not CVs.

Behavioral memory: what they do

Goals (what they’re trying to achieve), habits (recurring behaviors), constraints (what they can’t change), tradeoffs (the choices they’ve actively made), and usage patterns (how they engage with relevant tools or services). This is where the day-to-day texture lives.

Belief memory: what they think

Opinions (positions on specific topics, with the stance noted), objections (what would make them push back), preferences (specific aspect-by-aspect leanings), and decision heuristics (the rules they apply when choosing). Belief memory is what makes a persona disagree with you in interview rather than nodding along.

Language memory: how they talk

Vocabulary register, typical phrases, preferred tone, communication style, interview behavior, and verbosity target (terse, conversational, expansive, or narrative). This is what makes a persona sound like a specific person rather than generic AI prose. It also tells the model how long to make answers and which words to reach for.

Provenance badges

Every field in the memory sections and the B2C/B2B profile carries a provenance badge. The five values:

Grounded (green) — the field cites exactly one specific source. Strongest evidence.
Inferred (gray) — the field synthesises across two or more sources. Still well-evidenced.
Calibrated (blue) — derived from validated behavioral or population distributions rather than a specific source.
Sampled (violet) — drawn from a calibrated distribution. OCEAN values and bias intensities are sampled.
Weak confidence (amber) — an explicit hypothesis with no evidence backing. Treat carefully.

The point of provenance tagging is so you never confuse a confident claim with a guess. If a critical decision rule is tagged weak confidence, you know to test it explicitly in interview rather than treating it as established.

Evidence and provenance section

At the bottom of the profile, a section titled Evidence & Provenance summarises how well-grounded the persona is overall. Two main parts:

Audience quality — a single percentage, like 83%. This is what feeds the colored quality badge on the persona card. It rolls up the proportion of fields with strong provenance, the breadth of supporting evidence, and the synthesis depth.
Composition bars — a breakdown of the persona’s claims into cited evidence claims, uncited evidence claims, and constraint-derived claims. Plus a synthesis depth metric: average evidence references per cited field, and the count of distinct signals cited.

A persona with 90% audience quality and 4+ refs per cited field is well-supported and ready to interview. One under 50% is a persona Candor flagged as speculative, often because the underlying segment had thin evidence. Use those for hypothesis generation, not as standalone validation.

How to actually read a profile

Three minutes is enough for a productive read:

Glance at audience quality and provenance composition first. That tells you how much to trust what follows.
Read identity memory and the top three biases. That gives you the person + the cognitive levers they pull.
Skim belief memory’s opinions and objections. These are what you’ll likely poke at in interview.
If you’re running an auto-interview, also skim language memory’s verbosity target and interview behavior. That’s what shapes how the persona will sound across the run.