Key terms and concepts used in synthetic user research, persona modeling, and research-backed product validation.
CORE CONCEPTS
An AI-generated representation of a person within a target audience, built from real evidence rather than imagination. Synthetic personas have personality traits, cognitive biases, memory, and behavioral patterns grounded in market data and research.
A research methodology that uses AI-generated personas to simulate customer interviews, concept tests, and market validation studies. Designed to complement traditional research by providing fast, research-backed signal before committing to building.
The practice of building persona attributes from verifiable sources (uploaded research documents, web evidence, and validated behavioral distributions) rather than generating them from a prompt alone. Every trait traces back to a source.
The customer-facing read on how well-grounded something is, shown on segments, personas, and findings. It summarises the provenance underneath: a persona whose traits are mostly grounded and inferred reads as well-evidenced, while one leaning on sampled and weak-confidence values reads as thin.
A system for tracking the origin of every persona trait. Each attribute carries one of five tags: grounded (cited to one specific source), inferred (synthesised across two or more), calibrated (derived from validated distributions), sampled (drawn from one of those distributions, which is how OCEAN values and bias intensities are set), or weak confidence (assumed but not well-evidenced).
AUDIENCE & SEGMENTATION
The process of analyzing a target audience description and evidence to produce behavioral segments, signals, and calibration data. Candor segments by psychographic and behavioral dimensions rather than demographics alone.
A meaningful subgroup within a target audience, defined by a primary differentiating dimension: the behavioral or psychographic criterion that explains why members make different choices from other segments.
A discrete research finding extracted from evidence: a behavior, pain point, attitude, constraint, goal, belief, preference, or decision rule. Signals are tagged with type, sentiment, provenance, and intensity.
A distinct behavioral cluster within an audience, defined by specific values across selected dimensions. Archetypes represent different ways people in the audience approach decisions, with OCEAN ranges and primary cognitive biases.
PERSONA MODELING
The five-factor personality model: Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. Candor samples each trait from peer-reviewed population distributions calibrated by region and occupation, not randomly.
A systematic pattern in how people process information and make decisions. In Candor, biases are first-class traits with intensity values from 0 to 1, assigned based on archetype context and research-backed prevalence data.
The narrative knowledge that defines a persona's inner world. Includes four types: identity memory (background, role), behavioral memory (goals, habits, constraints), belief memory (opinions, preferences, decision rules), and language memory (vocabulary, tone, communication style).
Formative decisions pre-generated for each persona that establish their decision-making patterns. Each includes the choice scenario, factors weighed, outcome chosen, reasoning, and which cognitive biases were activated.
The process by which an AI model embodies a persona during an interview, drawing on the full persona profile (personality, memory, biases, prior decisions, and conversation history) to generate responses that stay in character.
INTERVIEW & RESEARCH
An interview mode where you type questions in real time and the persona responds conversationally. Each response is validated by a critic agent before delivery. Personas remember everything across multiple live interview sessions.
An automated interview mode where Candor conducts the interview based on a configured guide. It generates questions, tracks learning goal coverage, adapts probes based on responses, and detects when a persona is going off-profile.
A structured configuration for auto-interviews that defines sections, learning goals, and question variants. Candor uses the guide to drive the conversation, ensure coverage of all research objectives, and decide when to move between topics.
A quality control step where a separate AI model reviews every persona response for consistency. Hard contradictions (direct conflicts with established beliefs) are caught and regenerated. Soft tensions (mood shifts) are flagged but delivered.
The auto-interview system's method of monitoring which learning goals have been substantively addressed. It ensures every section of the interview guide receives adequate coverage before the interview concludes.
A mechanism in auto-interviews that identifies when a persona's responses are going off-profile or becoming repetitive. When detected, the system re-anchors the conversation or moves to the next topic to protect transcript quality.
ANALYSIS & OUTPUT
The structured output of an interview run, generated automatically once the last session finishes. Every report has four sections: what matters most, the findings, the next steps, and an evidence appendix. What sits inside the findings depends on the interview type, because a hypothesis verdict and a willingness-to-pay range are built differently. Every claim traces back to source quotes.
Grouping related signals into named themes. In a problem-discovery report the themes are merged with the problems that surfaced on their own into a single findings list, ranked by how broadly each one showed up across personas. Other interview types order their findings differently: concept testing leads with the strongest verdicts.
A genuine disagreement surfaced in synthesis: different archetypes or personas expressing directly opposing views on the same topic. Tensions highlight real product decisions where you can't satisfy all segments simultaneously.
How much weight the evidence behind a finding can carry, shown as High, Medium-High, Medium, or Low. It is not a quality score: a Medium finding can be the most important thing in a report. When something pulled the level down, an info icon lists the specific caps that fired and why.
An explicit call attached to a tested item, shown as a coloured pill. Each interview type uses its own vocabulary: problem validation returns validated, partially validated, not supported, not applicable, or inconclusive; concept testing returns pursue, iterate, inconclusive, drop, or rewrite-and-retest.
An internal synthesis step that turns findings into product-relevant language. You will not see it as a heading in a report. Its output lands in the findings and next steps: what is working versus what needs rethinking for concept testing, value gaps and willingness-to-pay ranges for price testing, hypothesis verdicts for problem validation.
STUDY TYPES
A study type for exploring unknown problems in a market. You know who you want to serve but not what problems matter most. Synthesis highlights themes and tensions without opportunity framing. The goal is understanding, not solution validation.
A study type for testing specific hypotheses about customer problems. State assumptions explicitly, then interview personas to see if evidence supports, contests, or contradicts each one. Synthesis delivers explicit verdicts with supporting quotes.
A study type for evaluating a specific product concept. Synthesis frames what's working, what needs rethinking, and who the concept is actually for. Structured to drive build-or-pivot decisions, not just generate themes.
A study type for understanding how customers perceive value and what they're willing to pay. Synthesis extracts value perception gaps, price anchoring effects, and willingness-to-pay ranges segmented by archetype.
The second choice you make inside concept testing. A standard test shows whole concepts cold and compares them against each other. A name test, a value proposition test, and a messaging test each expose one anchor concept first, then present the candidate options inside that context, so nobody judges a name or a headline in a vacuum.
A concept test that evaluates candidate names for one concept. Personas meet the concept first, then react to each name: whether it fits, whether it resonates, and whether it connects to what the product actually does.
A concept test that evaluates candidate benefits for one concept. Personas see them one at a time in the concept's context and say which is most compelling and most believable.
A concept test that evaluates candidate messages or headlines for one concept: which is clearest, which is most persuasive, and which makes a persona want to learn more.
A methodology the guide switches to automatically when you give it enough items to compare. Personas sort the items into buckets and rank them, and the interviewer then deep-dives the top-ranked ones rather than treating all of them equally.
Be the first to know when it launches.
No spam. Just a note when Candor is ready. Powered by Highline Beta.