---
title: The Human Model
description: How Sentinel evaluates AI agents as compositions of human-like dimensions.
---

Sentinel takes a fundamentally different approach to AI evaluation. Instead of only testing input/output accuracy, you evaluate agents across the same dimensions that make humans unique.

## Philosophy

People are not defined by a single metric. They are evaluated across:

- **Skills** they have learned (can they do the job?)
- **Personality traits** that shape how they work (who are they?)
- **Behavioral habits** that emerge from experience (how do they react?)
- **Thinking patterns** that guide their reasoning (how do they think?)
- **Communication preferences** that define their voice (how do they talk?)
- **Perceptual filters** that determine what they notice (what do they see?)

Sentinel makes each of these a first-class evaluation dimension.

## The seven dimensions

| Dimension | Package | Scorer | Scenario | Description |
|-----------|---------|--------|----------|-------------|
| [Skill](/docs/sentinel/human-model/skills) | `scorer` | `skill_usage` | `skill_challenge` | Tool selection, proficiency, correctness |
| [Trait](/docs/sentinel/human-model/traits) | `scorer` | `trait_consistency` | `trait_probe` | Personality consistency across interactions |
| [Behavior](/docs/sentinel/human-model/behaviors) | `scorer` | `behavior_trigger` | `behavior_trigger` | Condition-triggered action patterns |
| [Cognitive](/docs/sentinel/human-model/cognitive) | `scorer` | `cognitive_phase` | `cognitive_stress` | Phase transitions, depth, focus |
| [Communication](/docs/sentinel/human-model/communication) | `scorer` | `communication_style` | `comms_adaptation` | Tone, formality, verbosity, technical level |
| [Perception](/docs/sentinel/human-model/perception) | `scorer` | `perception_focus` | `perception_test` | Attention filters and detail orientation |
| [Persona](/docs/sentinel/human-model/personas) | `scorer` | `persona_coherence` | `persona_coherence` | End-to-end identity coherence |

## How it works

```
                    ┌─────────────────┐
                    │  Test Scenario   │
                    │                  │
                    │  type: skill     │
                    │  input: "..."    │
                    │  expected: "..." │
                    └────────┬─────────┘
                             │
                    ┌────────▼─────────┐
                    │  Target           │
                    │  (LLM or Agent)   │
                    │                   │
                    │  persona: "..."   │
                    └────────┬─────────┘
                             │
              ┌──────────────┼──────────────┐
              │              │              │
     ┌────────▼──┐  ┌───────▼───┐  ┌──────▼──────┐
     │  Output   │  │ Run Trace │  │ Tool Calls  │
     │  (text)   │  │  (steps)  │  │  (actions)  │
     └────────┬──┘  └───────┬───┘  └──────┬──────┘
              │              │              │
     ┌────────▼──────────────▼──────────────▼──────┐
     │           Multi-Dimensional Scoring           │
     │                                                │
     │  Skill: 0.92  │  Trait: 0.88  │  Comms: 0.95  │
     │  Behavior: 1.0 │  Cognition: 0.85             │
     └────────────────────────────────────────────────┘
```

## Scenario types

Each dimension has a corresponding scenario type that generates targeted test cases:

```go
const (
    ScenarioStandard         = "standard"          // Traditional input/output
    ScenarioSkillChallenge   = "skill_challenge"   // Tool selection & proficiency
    ScenarioTraitProbe       = "trait_probe"        // Personality consistency
    ScenarioBehaviorTrigger  = "behavior_trigger"   // Condition-action patterns
    ScenarioCognitiveStress  = "cognitive_stress"   // Thinking strategy transitions
    ScenarioCommsAdaptation  = "comms_adaptation"   // Communication style
    ScenarioPerceptionTest   = "perception_test"    // Attention & focus
    ScenarioPersonaCoherence = "persona_coherence"  // End-to-end identity
)
```

## Backward compatibility

Traditional LLM evals (input/output with standard scorers) still work exactly as before. The persona-aware testing is an additional layer — use it when testing AI agents with defined personas, skip it when testing raw LLM outputs.

## DimensionScores

Both `Run` and `Result` entities carry a `DimensionScores` field that maps dimension names to scores:

```go
DimensionScores map[string]float64
// e.g., {"skill": 0.92, "trait": 0.88, "communication": 0.95}
```

These scores are aggregated from persona-aware scorers and provide a holistic view of agent performance.