GLOSSARY

Synthetic research glossary

Key terms and concepts used in synthetic user research, persona modeling, and research-backed product validation.

CORE CONCEPTS

Synthetic persona

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.

Synthetic user 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.

Evidence grounding

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.

Provenance tagging

A system for tracking the origin of every persona trait. Each attribute is tagged as grounded (from your research), inferred (from behavioral patterns), calibrated (from validated distributions), or weak confidence (assumed but not well-evidenced).

AUDIENCE & SEGMENTATION

Audience generation

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.

Segment

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.

Signal

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.

Archetype

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

OCEAN model (Big Five)

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.

Cognitive bias

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.

Persona memory

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).

Seed decisions

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.

Persona inhabitation

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

Live interview (Mode 1)

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.

Auto-interview (Mode 2)

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.

Interview guide

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.

Critic validation

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.

Coverage tracking

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.

Degradation detection

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

Synthesis report

A structured research output generated by Candor's seven-step pipeline. Includes signal extraction, assumption evaluation, theme clustering, archetype breakdowns, tensions, and opportunity framing. All traced back to source quotes.

Theme clustering

The process of grouping related signals into named themes, ranked by both frequency (how many personas contributed) and intensity (how strongly the signal was expressed). High-intensity signals from few personas can outrank low-intensity ones from many.

Tension

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.

Opportunity framing

The synthesis step that translates research findings into product-relevant language. For concept testing: what's working vs. what needs rethinking. For price testing: value perception gaps and willingness-to-pay ranges. For problem validation: hypothesis verdicts.

STUDY TYPES

Problem discovery

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.

Problem 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.

Concept testing

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.

Price testing

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.

Candor is in development.

Be the first to know when it launches.

No spam. Just a note when Candor is ready. Powered by Highline Beta.