---
title: Behaviors
description: Define what an agent does — condition-triggered action patterns.
---

A **Behavior** is a condition-triggered action pattern — the "habits" and "reflexes" that compose skills and traits into contextual responses. When a trigger condition is met, the behavior fires its actions.

## Structure

```go
type Behavior struct {
    cortex.Entity
    ID            id.BehaviorID
    Name          string
    Description   string
    AppID         string
    Triggers      []Trigger
    Actions       []Action
    Priority      int
    RequiresSkill string
    RequiresTrait string
    Metadata      map[string]any
}
```

## Triggers

Triggers define when a behavior activates:

```go
type Trigger struct {
    Type    TriggerType
    Pattern string       // optional pattern for matching
}
```

### Trigger types

| Type | Description |
|------|-------------|
| `on_input` | Fires when user input matches a pattern |
| `on_tool_result` | Fires when a tool returns a specific result |
| `on_error` | Fires when an error occurs |
| `on_step_count` | Fires when the step count reaches a threshold |
| `on_context` | Fires based on conversation context |
| `always` | Fires on every step |

## Actions

Actions define what happens when a behavior triggers:

```go
type Action struct {
    Type   ActionType
    Target string      // action-specific target
    Value  any         // action-specific value
}
```

### Action types

| Type | Description |
|------|-------------|
| `inject_prompt` | Inject text into the system prompt |
| `prefer_skill` | Increase preference for a specific skill |
| `require_tool` | Force usage of a specific tool |
| `modify_param` | Modify a runtime parameter |
| `switch_cognitive` | Switch to a different cognitive phase |
| `add_guardrail` | Add a runtime guardrail check |

## Priority

When multiple behaviors trigger simultaneously, they execute in priority order (lower number = higher priority):

```go
behavior := &behavior.Behavior{
    Priority: 10, // fires before priority 20
}
```

## Skill and trait requirements

A behavior can require that a specific skill or trait is active:

```go
behavior := &behavior.Behavior{
    Name:          "verify-before-suggest",
    RequiresSkill: "code-review",
    RequiresTrait: "thoroughness",
    Triggers: []behavior.Trigger{
        {Type: behavior.TriggerAlways},
    },
    Actions: []behavior.Action{
        {Type: behavior.ActionInjectPrompt, Value: "Always verify your analysis before suggesting changes."},
    },
}
```

## Store interface

```go
type Store interface {
    CreateBehavior(ctx context.Context, behavior *Behavior) error
    GetBehavior(ctx context.Context, behaviorID id.BehaviorID) (*Behavior, error)
    GetBehaviorByName(ctx context.Context, appID, name string) (*Behavior, error)
    UpdateBehavior(ctx context.Context, behavior *Behavior) error
    DeleteBehavior(ctx context.Context, behaviorID id.BehaviorID) error
    ListBehaviors(ctx context.Context, filter *ListFilter) ([]*Behavior, error)
}
```

## API routes

| Method | Path | Description |
|--------|------|-------------|
| `POST` | `/cortex/behaviors` | Create a behavior |
| `GET` | `/cortex/behaviors` | List behaviors |
| `GET` | `/cortex/behaviors/{name}` | Get a behavior by name |
| `PUT` | `/cortex/behaviors/{name}` | Update a behavior |
| `DELETE` | `/cortex/behaviors/{id}` | Delete a behavior |