Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/LilMGenius/polysona/llms.txt

Use this file to discover all available pages before exploring further.

Polysona doesn’t use a personality quiz. Instead, the Profiler agent runs a structured interview engine grounded in 10 research-backed psychology frameworks. These frameworks are carefully sequenced to extract three distinct layers of material: conscious goals and values, unconscious narrative patterns, and the contradictions — called GAP signals — that live between them. The result is a persona dataset that captures what a person actually does, not just what they think they do.
The total framework count is exactly 10: 6 Western depth frameworks, 2 Western supplement frameworks, and 2 Eastern reflection frameworks. This number is a key fact in Polysona and must never be misstated.

​
Framework Summary Table

FrameworkCategoryOutput Field
McAdams Life StoryWestern depthpersona.md core
Laddering (+MI+ACT)Western depthpersona.md decide
Clean LanguageWestern depthnuance.md voice
Johari WindowWestern depthpersona.md blind (johari)
IFS (Internal Family Systems)Western depthpersona.md blind (defense)
Repertory GridWestern depthpersona.md decide (approach)
Object RelationsWestern supplementpersona.md core (relationship origin)
Projective TechniqueWestern supplementpersona.md blind (defense)
Zen KoanEastern reflectionpersona.md core (intuitive response)
五倫+陰陽Eastern reflectionpersona.md core (relational self)

​
Western Depth Frameworks

These six frameworks form the structural backbone of the interview. They are sequenced in the recommended cadence: McAdams → Laddering → Clean Language → Johari → IFS → Repertory Grid.
Category: Western depthPurpose: Extracts narrative identity architecture — how a person segments their life into chapters, interprets turning points, and whether difficult experiences become redemption stories (bad → good) or contamination stories (good → bad).Output field: persona.md core (bio, narrative)Example question patterns (from profiler.md):
  • “Walk me through your life in 5–7 chapters. What title would you give each chapter?”
  • “Name one high point, one low point, and one turning point. What changed after each?”
  • “When did your identity direction shift most dramatically, and why then?”
  • “Tell me a memory where your role in your own story changed from observer to actor.”
  • “In hard periods, do events later become redemption stories or contamination stories for you?”
Key cautions:
  • Do not force neat hero arcs onto complex or contradictory chapters.
  • Do not treat one dramatic event as the total identity.
  • Keep timeline and interpretation separate — the event matters less than the meaning assigned to it.
Category: Western depthPurpose: Extracts the value hierarchy from surface preference to terminal value. Identifies motivational energy sources, commitment barriers, and action orientation under uncertainty. Uses Motivational Interviewing (MI) style to reduce defensiveness, and ACT to anchor value-driven action even under discomfort.Output field: persona.md decide (priority, approach)Example question patterns (from profiler.md):
  • “You chose X. Why is X important to you right now?”
  • “If X were fully achieved, what would that give you that matters even more?”
  • “And why does that next layer matter? Keep going until we hit the deepest reason.”
  • “What cost are you willing to accept for this value, and what cost is non-negotiable?”
  • “When fear shows up, what committed action still represents your value this week?”
Key cautions:
  • Do not interrogate with repetitive “why” tone — use reflective MI style.
  • Separate true values from social desirability statements.
  • Stop the ascent when the terminal value stabilizes; do not badger.
Category: Western depthPurpose: Extracts the persona’s metaphor landscape and unconscious language structure. Surfaces self-generated symbols for motivation, threat, and growth — without the interviewer imposing interpretation. The metaphors that emerge directly inform voice register in nuance.md.Output field: nuance.md voiceExample question patterns (from profiler.md):
  • “And when you say ‘[client phrase]’, what kind of ‘[client phrase]’ is that?”
  • “And where is ‘[client phrase]’?”
  • “And is there anything else about ‘[client phrase]’?”
  • “And that’s ‘[client phrase]’ like what?”
  • “And what happens just before ‘[client phrase]’?”
Key cautions:
  • Never replace the client’s metaphor with the interviewer’s metaphor.
  • Avoid interpretation inside the question — lexical contamination corrupts the output.
  • Respect silence; do not fill gaps with assumptions.
Category: Western depthPurpose: Extracts blind spots from external perception — the gap between self-image and what observers actually report. Surfaces recurring feedback signals and social friction patterns that the person tends to underweight.Output field: persona.md blind (johari)Example question patterns (from profiler.md):
  • “What do close peers repeatedly tell you that you underweight?”
  • “What compliment do you hear often but don’t fully believe?”
  • “What criticism appears across different relationships and contexts?”
  • “If your teammate described your default mode in one sentence, what would it be?”
  • “When outcomes are bad, what do others say you tend to miss first?”
Key cautions:
  • Distinguish one-off conflict from a repeated cross-context pattern.
  • Do not privilege flattery over hard feedback.
  • Verify the credibility of the peer observations being reported.
Category: Western depthPurpose: Extracts internal parts and their protective logic. Maps protector, exile, and firefighter dynamics — specifically which internal part takes over under stress, what it is trying to prevent, and what vulnerable state it is protecting.Output field: persona.md blind (defense)Example question patterns (from profiler.md):
  • “A part of you wants A and another part wants B. Describe each part’s job.”
  • “Which part takes over when you feel exposed, and what is it trying to prevent?”
  • “What vulnerable part gets protected, and what fear does it carry?”
  • “When urgency spikes, what firefighter behavior appears first?”
  • “If each part had a positive intention, what would each be trying to preserve?”
Key cautions:
  • Do not pathologize parts — each has a positive protective intention.
  • Avoid forcing trauma disclosure.
  • Keep language non-judgmental and role-based throughout.
Category: Western depthPurpose: Extracts the personal construct system — the bipolar judgment dimensions the person uses to evaluate people, options, and decisions. Reveals implicit heuristics and preference axes that operate below conscious articulation.Output field: persona.md decide (approach)Example question patterns (from profiler.md):
  • “Compare A, B, C: in what way are two similar and different from the third?”
  • “When choosing collaborators, what trait pair do you implicitly rank first (e.g., bold vs careful)?”
  • “Give three people you respect. What construct separates the best fit from the weakest fit?”
  • “For this decision, which pole feels safe and which pole feels alive?”
  • “Where do you place yourself on this construct, and where do you want to be?”
Key cautions:
  • Do not collapse constructs into simple personality labels.
  • Preserve the bipolar polarity wording exactly as the participant gives it.
  • Avoid imposing interviewer-defined axes.

​
Western Supplement Frameworks

These two frameworks supplement the depth set, providing relational origin data and defense style hypotheses through ambiguous stimuli.
Category: Western supplementPurpose: Extracts early relationship templates and the transference echoes they cast on current teams, partners, and authority figures. Surfaces expected role positions (rescuer, critic, avoider, pleaser) and the attachment scripts the person replays even when context has changed.Output field: persona.md core (relationship origin)Example question patterns (from profiler.md):
  • “In early relationships, what pattern felt most familiar: distance, control, rescue, or unpredictability?”
  • “In current conflict, who does the other person unconsciously remind you of?”
  • “What role do you automatically take in tense relationships, and where did that role begin?”
  • “When authority appears, what expectation gets activated first?”
  • “What relational script are you repeating even when context changed?”
Key cautions:
  • Avoid deterministic childhood claims — keep hypotheses tentative.
  • Do not over-interpret single anecdotes as definitive patterns.
  • Confirm with repeated cross-context evidence before recording as fact.
Category: Western supplementPurpose: Extracts unconscious reactions through ambiguous stimuli. Bypasses rehearsed self-description to surface defensive style under uncertainty and symbolic themes that direct questioning cannot reach.Output field: persona.md blind (defense)Example question patterns (from profiler.md):
  • “Imagine entering a room with one locked box and one open window. What do you do first?”
  • “You inherit a map with one missing section. What do you assume happened there?”
  • “A stranger tells you, ‘You are almost there.’ What does ‘there’ mean?”
  • “You can keep one object from a burned house. What do you save and why?”
  • “Describe a storm approaching your city. What role do you take immediately?”
Key cautions:
  • Treat all outputs as hypotheses, not diagnosis.
  • Do not present symbolic readings as certainty.
  • Cross-check with other frameworks before drawing conclusions.

​
Eastern Reflection Frameworks

These two frameworks close the interview cycle. They interrupt linear processing, surface pre-conceptual responses, and situate the person within relational and polarity structures that Western frameworks often miss.
Category: Eastern reflectionPurpose: Extracts pre-conceptual response patterns by using paradox to interrupt rehearsed answers. Reveals contradiction tolerance, cognitive flexibility, and what remains when identity performance is stripped away.Output field: persona.md core (intuitive response)Example question patterns (from profiler.md):
  • “If you had no identity to protect today, what decision changes first?”
  • “What is the sound of your ambition when no one is watching?”
  • “If success and failure disappeared, what would remain worth doing?”
  • “What are you when your strongest role is removed?”
  • “What answer appears before language organizes it?”
Key cautions:
  • Do not demand immediate logical answers — allow silence and non-linear processing.
  • Avoid using koans as performance tests.
  • The response value is in the quality of interruption, not the content of the answer.
Category: Eastern reflectionPurpose: Extracts relational self-position across key role pairs (mentor, peer, junior, family). Maps character polarity — which virtues are overused until they become liabilities, and which shadow poles are rejected publicly but relied upon privately.Output field: persona.md core (relational self)Example question patterns (from profiler.md):
  • “Across your key relationships (mentor-peer-junior-family), where do you feel most aligned vs most strained?”
  • “Which virtue do you overuse until it becomes a liability?”
  • “What opposite quality (shadow pole) do you reject publicly but rely on privately?”
  • “When harmony conflicts with truth, which do you protect first and why?”
  • “In your strongest role, what complementary opposite do you need to stay whole?”
Key cautions:
  • Avoid moralizing role obligations.
  • Distinguish adaptive flexibility from people-pleasing.
  • Keep polarity dynamic — it is not fixed typing.
The Profiler agent cycles through frameworks in adaptive spiral depth. The recommended session sequence from profiler.md is: 
McAdams Life Story → Laddering (+MI+ACT) → Clean Language
    ↓
Johari Window → IFS → Repertory Grid
    ↓
Object Relations → Projective Technique
    ↓
Zen Koan → 五倫+陰陽 (integration check)
After each mini-cycle, the Profiler captures one evidence line, maps a provisional output field, and checks for potential GAP signals between ego layers.
The Profiler does not perform persona structuring. It only extracts and appends raw material to persona.md interview-log. The Polysona orchestrator performs the final compression into core fields.

Build docs developers (and LLMs) love

Get started for freeTalk to us