Profile Catalog - PrefID Documentation

Overview

PrefID organizes user preferences into profiles — structured collections of preference atoms that define how AI agents should interact with users. Each profile serves a specific purpose and can be selectively exposed to different agents and companies.

Core Behavioral Profiles

These profiles control how AI reasons and interacts with users. They’re the highest-value profiles for AI agents.

thinking_profile

Purpose: Controls how AI structures reasoning and responses

Atom	Description
`prefers_stepwise_reasoning`	Show step-by-step thought process
`prefers_summary_first`	Lead with conclusions, details after
`prefers_decision_recommendation`	Provide clear recommendations

Useful for: OpenAI, Anthropic, IDEs, Enterprise copilots
Consumed by: ChatGPT, Claude, Coding agents, Strategy agents

communication_profile

Purpose: Defines tone, formality, and brevity preferences

Atom	Description
`prefers_direct_tone`	Get to the point quickly
`dislikes_fluff`	Avoid unnecessary pleasantries
`formal_language`	Use professional language

Useful for: Customer support platforms, CRM tools
Consumed by: Support bots, Sales bots, HR assistants

initiative_profile

Purpose: Determines who drives the interaction

Atom	Description
`agent_should_suggest`	AI proactively offers suggestions
`agent_should_wait`	AI waits for explicit prompts

Useful for: Agent platforms, workflow automation
Consumed by: Autonomous agents, Task planners

clarity_profile

Purpose: Precision vs ambiguity tolerance

Atom	Description
`demands_precision`	Requires exact, detailed answers
`tolerates_ambiguity`	Comfortable with uncertainty

Useful for: Legal tech, research platforms
Consumed by: Legal AI, Research assistants

pace_profile

Purpose: Speed vs depth of interaction

Atom	Description
`fast_iterations`	Quick back-and-forth preferred
`deep_deliberation`	Thorough, slower exploration

Useful for: Developer tools, startup tooling
Consumed by: Coding agents, Product managers

decision_profile

Purpose: How decisions should conclude

Atom	Description
`single_recommendation`	Give one clear answer
`wants_tradeoffs`	Present options with pros/cons

Useful for: Consulting AI, finance tools
Consumed by: Advisory agents, Strategy bots

error_tolerance_profile

Purpose: Reaction to AI mistakes

Atom	Description
`zero_tolerance`	Errors are unacceptable
`fail_fast`	Prefer quick failure over slow uncertainty

Useful for: Fintech, infrastructure tools
Consumed by: Infra agents, Finance bots

autonomy_profile

Purpose: Permission levels for AI actions

Atom	Description
`wants_ai_initiative`	AI can act independently
`confirm_before_actions`	Always ask before doing

Useful for: Automation platforms
Consumed by: Action-taking agents

Content & Domain Profiles

These profiles capture preferences within specific life domains. Selectively exposed based on app context.

travel_profile

Purpose: Travel style and constraints

Atom	Description
`adventure_focused`	Prefers unique experiences
`moderate_budget`	Mid-range spending
`prefers_airbnb`	Home rentals over hotels

Useful for: Booking.com, Airbnb, travel startups
Consumed by: Travel planners, Concierge agents

food_profile

Purpose: Diet and food behavior

Atom	Description
`prefers_light_food`	Avoids heavy meals
`vegetarian_friendly`	Plant-based preferences
`spice_tolerance_high`	Enjoys spicy food

Useful for: Food delivery, hospitality
Consumed by: Food recommendation agents

music_preferences

Purpose: Listening patterns

Atom	Description
`cinematic_music`	Epic, orchestral preferences
`low_energy`	Calm, relaxing music
`genre_indian_classical`	Cultural preferences

Useful for: Spotify, Apple Music
Consumed by: Playlist agents

shopping_profile

Purpose: Brands, size, spending style

Atom	Description
`avoids_luxury`	Price-conscious
`brand_loyal`	Sticks to known brands
`size_medium`	Clothing size info

Useful for: Shopify merchants
Consumed by: Commerce agents

entertainment_profile

Purpose: Movies, shows, gaming

Atom	Description
`prefers_slow_burn`	Loves character development
`avoids_horror`	Genre exclusions

Useful for: Streaming platforms
Consumed by: Content discovery agents

fitness_profile

Purpose: Physical activity patterns

Atom	Description
`hiking_focused`	Outdoor activities
`recovery_days`	Rest preferences

Useful for: Health apps, wearables
Consumed by: Fitness coaches

health_profile

Purpose: Wellness preferences (non-medical)

Atom	Description
`avoids_heavy_food`	Dietary wellness
`prefers_low_stress`	Calm environments

Useful for: Wellness startups
Consumed by: Health advisory agents

fashion_profile

Purpose: Style & apparel preferences

Atom	Description
`minimal_style`	Clean, simple aesthetics
`neutral_colors`	Color preferences

Useful for: Fashion brands, Myntra
Consumed by: Styling agents

reading_profile

Purpose: Books & learning content

Atom	Description
`prefers_nonfiction`	Genre preference
`long_form_content`	Article length preference

Useful for: Publishers, EdTech
Consumed by: Reading recommendation agents

Professional / B2B Profiles

These profiles serve enterprise and productivity use cases.

coding_profile

Purpose: Development stack and coding style

Atom	Description
`prefers_typescript`	Language preference
`avoids_prisma`	ORM preference
`functional_style`	Coding paradigm

Useful for: GitHub, IDEs, SaaS dev tools
Consumed by: Coding assistants

career_profile

Purpose: Career goals and skills

Atom	Description
`growth_oriented`	Career motivation
`leadership_track`	Management aspiration

Useful for: LinkedIn, Coursera
Consumed by: Career advisors

learning_profile

Purpose: Learning style preferences

Atom	Description
`prefers_examples_over_theory`	Learning method
`visual_learner`	Content format

Useful for: EdTech platforms
Consumed by: Tutors

productivity_profile

Purpose: Work habits

Atom	Description
`deep_work_blocks`	Focus time preference
`async_communication`	Communication style

Useful for: Enterprise SaaS
Consumed by: Work assistants

collaboration_profile

Purpose: Team vs solo work style

Atom	Description
`solo_operator`	Independent work preference
`consensus_seeker`	Team decision style

Useful for: GitHub, Jira
Consumed by: Team agents

confidence_profile

Purpose: Reliance on AI

Atom	Description
`seeks_validation`	Wants AI confirmation
`independent_thinker`	Uses AI as tool, not authority

Useful for: Coaching platforms
Consumed by: Coaching agents

Meta & Governance Profiles

These profiles define boundaries and constraints for AI behavior. This is PrefID’s competitive moat.

memory_scope_profile

Purpose: What AI can remember

Atom	Description
`explicit_memory_only`	Only remember what user says to
`session_only`	Forget after conversation

Useful for: Privacy-first platforms
Consumed by: All agents

constraint_profile

Purpose: Hard vs soft limits

Atom	Description
`hard_constraints`	Non-negotiable limits
`deadline_driven`	Time-bound decisions

Useful for: Planning software
Consumed by: Scheduling agents

authority_profile

Purpose: How authoritative AI can be

Atom	Description
`accepts_directives`	AI can give commands
`advisory_only`	AI only suggests, never commands

Useful for: Enterprise AI
Consumed by: Executive agents

compliance_profile

Purpose: Regulatory sensitivity

Atom	Description
`requires_citations`	Needs sources for claims
`audit_ready`	Maintains decision trail

Useful for: Banks, Healthcare
Consumed by: Compliance agents

feedback_style_profile

Purpose: How feedback is delivered

Atom	Description
`direct_feedback`	Blunt, honest feedback
`gentle_feedback`	Softened delivery

Useful for: Coaching apps
Consumed by: Mentorship agents

goal_horizon_profile

Purpose: Short vs long term intent

Atom	Description
`long_term_planner`	Strategic thinking
`opportunistic`	Tactical, flexible

Useful for: Strategy platforms
Consumed by: Planning agents

Emerging Profiles

Experimental profiles with high upside. Ship carefully.

exploration_profile

Purpose: Novelty appetite

Atom	Description
`novelty_seeking`	Wants new experiences
`prefers_familiar`	Sticks to known

Useful for: Travel, discovery startups
Consumed by: Discovery agents

environment_profile

Purpose: Physical context sensitivity

Atom	Description
`altitude_sensitive`	Health at altitude
`heat_averse`	Temperature preference

Useful for: Outdoor platforms
Consumed by: Context-aware agents

resource_profile

Purpose: Available resources

Atom	Description
`low_bandwidth`	Limited connectivity
`offline_mode`	Works without internet

Useful for: Emerging markets apps
Consumed by: Offline agents

taste_maturity_profile

Purpose: Sophistication level

Atom	Description
`refined_preferences`	Discerning taste
`trend_fatigue`	Avoids hype

Useful for: Luxury & culture brands
Consumed by: Curation agents

initiative_boundary_profile

Purpose: Agent boundary limits

Atom	Description
`do_not_assume_intent`	Never infer user intent

Useful for: Enterprise
Consumed by: Guardrail agents

Accessing Profiles

// Get a specific profile
const thinkingProfile = await prefid.getPreferences('thinking_profile', {
  accessToken: userToken
});

// Get multiple profiles
const profiles = await prefid.getPreferences([
  'thinking_profile',
  'communication_profile',
  'autonomy_profile'
], {
  accessToken: userToken
});

// Get agent hints (summarized for context injection)
const hints = await prefid.getAgentHints({
  accessToken: userToken,
  domains: ['thinking_profile', 'communication_profile'],
  maxTokens: 100
});

Scope Requirements

Each profile requires its corresponding scope:

thinking_profile → thinking:read
communication_profile → communication:read
travel_profile → travel:read
// etc.

Request only the scopes you need.

​Overview

​Core Behavioral Profiles

​Content & Domain Profiles

​Professional / B2B Profiles

​Meta & Governance Profiles

​Emerging Profiles

​Accessing Profiles

​Scope Requirements