A persona profile is dense. It packs a personality, a memory, a set of biases, a way of speaking, and the evidence trail behind every claim into one screen. This guide walks through every section so you know what each field is doing and how to read it.
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.
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.
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:
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.
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.
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.
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.
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.
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.
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.
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.
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.
Every field in the memory sections and the B2C/B2B profile carries a provenance badge. The five values:
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.
At the bottom of the profile, a section titled Evidence & Provenance summarises how well-evidenced the persona is overall. Two main parts:
A Well-evidenced persona is ready to interview with full confidence. Some loose evidencemeans a few traits rest on audience data that’s only loosely related, so weight its responses with a little more skepticism. Thin evidence personas are still interviewable, but best for hypothesis generation rather than standalone validation.
Three minutes is enough for a productive read:
Be the first to know when it launches.
No spam. Just a note when Candor is ready. Powered by Highline Beta.