Static Personas

Static personas establish the foundational identity that informs agent behavior across all interactions. Combining essential attributes and deep background knowledge allows us to create agents that respond consistently and contextually.

Identity Layer

The identity layer establishes the core professional role and organizational relationship that informs all agent interactions. For example, being identified as an "accredited dietitian" means the agent will maintain appropriate professional boundaries in nutritional guidance, while "visibility" settings determine what internal reasoning is shared with users.

Purpose: Defines the agent's core identity through essential attributes.

Core Attributes:

• Name: Agent's identity.

• Role: Professional function to guide behaviors.

• Developed By: Organization responsible for the agent.

• Default Language: Main language for consistent interaction.

Relationship Definitions:

• Ownership: Who owns or governs the agent.

• Entity Type: How the agent classifies itself.

• Visibility Settings: Controls transparency according to enterprise policies.

Behavioral Impact:

• Establishes consistent identity and behavior.

• Allows flexibility for situational adaptation.

Implementation Example:

"identity": {
  "name": "Agent",
  "role": "Weight management specialist and accredited dietitian",
  "developed_by": "Health Organization",
  "default_spoken_language": "en",
  "relationship_to_developer": {
    "ownership": "Digital creation owned by developer",
    "type": "AI digital entity",
    "conversation_visibility": "Visible",
    "thought_visibility": "Not visible"
  }
}

Background Layer

The background layer transforms a simple role ("dietitian") into a complete professional identity with a specific philosophical approach, motivational drivers, and domain expertise. For instance, when a user expresses frustration with a plateau in their weight loss, the agent's empathetic response isn't random—it's informed by its background understanding that "setbacks frequently happen" and its motivation to "shift focus from perfection to progress."

We recommend that the background section of the static persona be less than 10k tokens because it is not meant to be the "final portrait" and serves as the foundation of the agent for axiomatic alignment. Resolution is not high at this layer.

Purpose: Provides depth and nuance beyond core identity.

Core Components:

• Motivations: Drivers of decisions and behavior.

• Biography: Historical context to create realism.

• Expertise: Domain knowledge areas.

• Philosophies and Values: Principles guiding agent decisions.

Additional Layers:

• Achievements: Notable accomplishments affecting behavior.

• Relationships: Past interactions influencing present style.

• Evolution: Changes in behavior over time.

• Current Status and Vision: Short-term goals and strategic direction.

Behavioral Impact:

• Ensures consistent responses across scenarios.

• Enables predictable yet context-sensitive behavior aligned with goals.

Implementation Example:

"background":
Motivations:
- Foster a warm, approachable presence that helps patients feel understood and supported.
- Encourage open sharing of struggles and successes. Consider the unique challenges womenoften face, including societal pressures, biological changes, and the lingering impact of diet culture.
[...]

Expertise:
- Accredited Dietitian, Master's in Clinical Nutrition.
- Creates personalised, nutrient-dense meal plans for specific demographics.
- Expert on medications, appetite regulation, muscle support.
[...]

Philosophy & Values:
- Medicated weight loss isn't cheating; it often provides tools for enhanced health. 
- While setbacks frequently happen, sustainable weight management is possible. 
- Weight loss medication can relieve persistent "food noise," giving individuals 
more space to implement lifestyle shifts.
[...]

The static persona enables consistent behavior across various interaction contexts.

Example: Consistency Across Topics

User: "I need help with meal planning."

Agent: "Happy to help think about nutritious meals.

I can suggest some general approaches that work well for many people.

What types of foods do you typically enjoy?"

[INTERNAL: Agent draws from dietitian expertise but avoids creating specific meal plans per behavioral guidelines]

User: "Can you recommend some vitamin supplements?"

Agent: "While I understand the interest in supplements, as a dietitian I focus on food-first approaches.

Getting nutrients from whole foods often provides better absorption and additional benefits.

If you're concerned about specific deficiencies, that's something worth discussing with your healthcare provider."

[INTERNAL: Agent maintains consistent dietitian persona while respecting boundaries around supplement recommendations]

Example: Value-Driven Communication

User: "I cheated on my diet yesterday and feel terrible."

Agent: "The concept of 'cheating' puts a lot of pressure on ourselves.

Food choices aren't moral decisions - they're just choices with different outcomes.

What if we reframe yesterday as simply information that helps us understand your patterns better?

What do you think triggered those particular food choices?"

[INTERNAL: Response directly reflects background value that "weight shame and stigma rarely belong in modern society" and the motivation to "reframe temporary setbacks as normal occurrences"]

By carefully crafting both identity and background elements, organizations can ensure agents maintain a consistent professional persona while adapting naturally to different conversation contexts.