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
thinking_profile
Purpose: Controls how AI structures reasoning and responses
Useful for: OpenAI, Anthropic, IDEs, Enterprise copilots
Consumed by: ChatGPT, Claude, Coding agents, Strategy agents
| 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 |
Consumed by: ChatGPT, Claude, Coding agents, Strategy agents
communication_profile
communication_profile
Purpose: Defines tone, formality, and brevity preferences
Useful for: Customer support platforms, CRM tools
Consumed by: Support bots, Sales bots, HR assistants
| Atom | Description |
|---|---|
prefers_direct_tone | Get to the point quickly |
dislikes_fluff | Avoid unnecessary pleasantries |
formal_language | Use professional language |
Consumed by: Support bots, Sales bots, HR assistants
initiative_profile
initiative_profile
Purpose: Determines who drives the interaction
Useful for: Agent platforms, workflow automation
Consumed by: Autonomous agents, Task planners
| Atom | Description |
|---|---|
agent_should_suggest | AI proactively offers suggestions |
agent_should_wait | AI waits for explicit prompts |
Consumed by: Autonomous agents, Task planners
clarity_profile
clarity_profile
Purpose: Precision vs ambiguity tolerance
Useful for: Legal tech, research platforms
Consumed by: Legal AI, Research assistants
| Atom | Description |
|---|---|
demands_precision | Requires exact, detailed answers |
tolerates_ambiguity | Comfortable with uncertainty |
Consumed by: Legal AI, Research assistants
pace_profile
pace_profile
Purpose: Speed vs depth of interaction
Useful for: Developer tools, startup tooling
Consumed by: Coding agents, Product managers
| Atom | Description |
|---|---|
fast_iterations | Quick back-and-forth preferred |
deep_deliberation | Thorough, slower exploration |
Consumed by: Coding agents, Product managers
decision_profile
decision_profile
Purpose: How decisions should conclude
Useful for: Consulting AI, finance tools
Consumed by: Advisory agents, Strategy bots
| Atom | Description |
|---|---|
single_recommendation | Give one clear answer |
wants_tradeoffs | Present options with pros/cons |
Consumed by: Advisory agents, Strategy bots
error_tolerance_profile
error_tolerance_profile
Purpose: Reaction to AI mistakes
Useful for: Fintech, infrastructure tools
Consumed by: Infra agents, Finance bots
| Atom | Description |
|---|---|
zero_tolerance | Errors are unacceptable |
fail_fast | Prefer quick failure over slow uncertainty |
Consumed by: Infra agents, Finance bots
autonomy_profile
autonomy_profile
Purpose: Permission levels for AI actions
Useful for: Automation platforms
Consumed by: Action-taking agents
| Atom | Description |
|---|---|
wants_ai_initiative | AI can act independently |
confirm_before_actions | Always ask before doing |
Consumed by: Action-taking agents
Content & Domain Profiles
These profiles capture preferences within specific life domains. Selectively exposed based on app context.travel_profile
travel_profile
Purpose: Travel style and constraints
Useful for: Booking.com, Airbnb, travel startups
Consumed by: Travel planners, Concierge agents
| Atom | Description |
|---|---|
adventure_focused | Prefers unique experiences |
moderate_budget | Mid-range spending |
prefers_airbnb | Home rentals over hotels |
Consumed by: Travel planners, Concierge agents
food_profile
food_profile
Purpose: Diet and food behavior
Useful for: Food delivery, hospitality
Consumed by: Food recommendation agents
| Atom | Description |
|---|---|
prefers_light_food | Avoids heavy meals |
vegetarian_friendly | Plant-based preferences |
spice_tolerance_high | Enjoys spicy food |
Consumed by: Food recommendation agents
music_preferences
music_preferences
Purpose: Listening patterns
Useful for: Spotify, Apple Music
Consumed by: Playlist agents
| Atom | Description |
|---|---|
cinematic_music | Epic, orchestral preferences |
low_energy | Calm, relaxing music |
genre_indian_classical | Cultural preferences |
Consumed by: Playlist agents
shopping_profile
shopping_profile
Purpose: Brands, size, spending style
Useful for: Shopify merchants
Consumed by: Commerce agents
| Atom | Description |
|---|---|
avoids_luxury | Price-conscious |
brand_loyal | Sticks to known brands |
size_medium | Clothing size info |
Consumed by: Commerce agents
entertainment_profile
entertainment_profile
Purpose: Movies, shows, gaming
Useful for: Streaming platforms
Consumed by: Content discovery agents
| Atom | Description |
|---|---|
prefers_slow_burn | Loves character development |
avoids_horror | Genre exclusions |
Consumed by: Content discovery agents
fitness_profile
fitness_profile
Purpose: Physical activity patterns
Useful for: Health apps, wearables
Consumed by: Fitness coaches
| Atom | Description |
|---|---|
hiking_focused | Outdoor activities |
recovery_days | Rest preferences |
Consumed by: Fitness coaches
health_profile
health_profile
Purpose: Wellness preferences (non-medical)
Useful for: Wellness startups
Consumed by: Health advisory agents
| Atom | Description |
|---|---|
avoids_heavy_food | Dietary wellness |
prefers_low_stress | Calm environments |
Consumed by: Health advisory agents
fashion_profile
fashion_profile
Purpose: Style & apparel preferences
Useful for: Fashion brands, Myntra
Consumed by: Styling agents
| Atom | Description |
|---|---|
minimal_style | Clean, simple aesthetics |
neutral_colors | Color preferences |
Consumed by: Styling agents
reading_profile
reading_profile
Purpose: Books & learning content
Useful for: Publishers, EdTech
Consumed by: Reading recommendation agents
| Atom | Description |
|---|---|
prefers_nonfiction | Genre preference |
long_form_content | Article length preference |
Consumed by: Reading recommendation agents
Professional / B2B Profiles
These profiles serve enterprise and productivity use cases.coding_profile
coding_profile
Purpose: Development stack and coding style
Useful for: GitHub, IDEs, SaaS dev tools
Consumed by: Coding assistants
| Atom | Description |
|---|---|
prefers_typescript | Language preference |
avoids_prisma | ORM preference |
functional_style | Coding paradigm |
Consumed by: Coding assistants
career_profile
career_profile
Purpose: Career goals and skills
Useful for: LinkedIn, Coursera
Consumed by: Career advisors
| Atom | Description |
|---|---|
growth_oriented | Career motivation |
leadership_track | Management aspiration |
Consumed by: Career advisors
learning_profile
learning_profile
Purpose: Learning style preferences
Useful for: EdTech platforms
Consumed by: Tutors
| Atom | Description |
|---|---|
prefers_examples_over_theory | Learning method |
visual_learner | Content format |
Consumed by: Tutors
productivity_profile
productivity_profile
Purpose: Work habits
Useful for: Enterprise SaaS
Consumed by: Work assistants
| Atom | Description |
|---|---|
deep_work_blocks | Focus time preference |
async_communication | Communication style |
Consumed by: Work assistants
collaboration_profile
collaboration_profile
Purpose: Team vs solo work style
Useful for: GitHub, Jira
Consumed by: Team agents
| Atom | Description |
|---|---|
solo_operator | Independent work preference |
consensus_seeker | Team decision style |
Consumed by: Team agents
confidence_profile
confidence_profile
Purpose: Reliance on AI
Useful for: Coaching platforms
Consumed by: Coaching agents
| Atom | Description |
|---|---|
seeks_validation | Wants AI confirmation |
independent_thinker | Uses AI as tool, not authority |
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
memory_scope_profile
Purpose: What AI can remember
Useful for: Privacy-first platforms
Consumed by: All agents
| Atom | Description |
|---|---|
explicit_memory_only | Only remember what user says to |
session_only | Forget after conversation |
Consumed by: All agents
constraint_profile
constraint_profile
Purpose: Hard vs soft limits
Useful for: Planning software
Consumed by: Scheduling agents
| Atom | Description |
|---|---|
hard_constraints | Non-negotiable limits |
deadline_driven | Time-bound decisions |
Consumed by: Scheduling agents
authority_profile
authority_profile
compliance_profile
compliance_profile
Purpose: Regulatory sensitivity
Useful for: Banks, Healthcare
Consumed by: Compliance agents
| Atom | Description |
|---|---|
requires_citations | Needs sources for claims |
audit_ready | Maintains decision trail |
Consumed by: Compliance agents
feedback_style_profile
feedback_style_profile
Purpose: How feedback is delivered
Useful for: Coaching apps
Consumed by: Mentorship agents
| Atom | Description |
|---|---|
direct_feedback | Blunt, honest feedback |
gentle_feedback | Softened delivery |
Consumed by: Mentorship agents
goal_horizon_profile
goal_horizon_profile
Purpose: Short vs long term intent
Useful for: Strategy platforms
Consumed by: Planning agents
| Atom | Description |
|---|---|
long_term_planner | Strategic thinking |
opportunistic | Tactical, flexible |
Consumed by: Planning agents
Emerging Profiles
Experimental profiles with high upside. Ship carefully.exploration_profile
exploration_profile
Purpose: Novelty appetite
Useful for: Travel, discovery startups
Consumed by: Discovery agents
| Atom | Description |
|---|---|
novelty_seeking | Wants new experiences |
prefers_familiar | Sticks to known |
Consumed by: Discovery agents
environment_profile
environment_profile
Purpose: Physical context sensitivity
Useful for: Outdoor platforms
Consumed by: Context-aware agents
| Atom | Description |
|---|---|
altitude_sensitive | Health at altitude |
heat_averse | Temperature preference |
Consumed by: Context-aware agents
resource_profile
resource_profile
Purpose: Available resources
Useful for: Emerging markets apps
Consumed by: Offline agents
| Atom | Description |
|---|---|
low_bandwidth | Limited connectivity |
offline_mode | Works without internet |
Consumed by: Offline agents
taste_maturity_profile
taste_maturity_profile
Purpose: Sophistication level
Useful for: Luxury & culture brands
Consumed by: Curation agents
| Atom | Description |
|---|---|
refined_preferences | Discerning taste |
trend_fatigue | Avoids hype |
Consumed by: Curation agents
initiative_boundary_profile
initiative_boundary_profile
Purpose: Agent boundary limits
Useful for: Enterprise
Consumed by: Guardrail agents
| Atom | Description |
|---|---|
do_not_assume_intent | Never infer user intent |
Consumed by: Guardrail agents