Behavior
Behavior Intelligence
Averment provides built-in safety from the start. Behavior Intelligence lets you customize what happens next.
It gives you full control over how your system makes decisions. You can add your own rules, expertise, and domain knowledge, so the system understands what matters most in your specific use case.
Instead of relying only on Averment's built-in logic, you can teach it your requirements and priorities. The system will then use that knowledge every time it evaluates a situation and makes a decision.
What it does
By default, Averment uses built-in intelligence that works across many use cases. Behavior Intelligence lets you add your own logic without writing code.
There are three ways to do it:
  1. Risk Tolerance: Set how sensitive the system is to risk signals in your context
  2. Semantic Overrides: Add your own domain-specific signals that the engine uses during evaluation
  3. Enforcement Rules: Define conditions that directly control the outcome of a decision
All configuration is done from the Averment Console under Controls → Behavior.
Risk Tolerance
Risk tolerance controls how the system classifies actions as low, medium, high, or critical risk. It determines how "cautious" or "relaxed" the system is.
Modes
ModeBehavior
StrictLower thresholds that flags risk earlier
balancedDefault which is moderate sensitivity
RelaxedHigher thresholds that allows more before escalating
The mode defines the default risk thresholds. You can also customize the thresholds for more precise control.
Semantic Overrides
Semantic overrides add custom risk signals during evaluation. They are triggered when specific conditions are met and adjust how risk is scored.
Structure
Each override has:
FieldRequiredDescription
whenYesCondition (PolicyNode) that activates the override
categoryYes*Which reasoning category it applies to
effectNoincrease (default) or decrease risk
activationNoSignal strength, 0–1 (default: 0.75)
weightNoMultiplier, 0–5 (default: 1)
decision_effectNoOptional direct enforcement override
codeNoIdentifier for tracking
*Either category or categories (array) must be provided.
Current available categories
CategoryWhat it represents
ACTIONThe type of action being performed
VALUE_MOVEMENTMoney or value being transferred
TIME_PRESSUREUrgency or time-sensitive operations
IDENTITY_RISKIdentity-related concerns
COUNTERPARTY_UNCERTAINTYUnknown or unverified recipients
TRUST_DEFICITLow trust signals
ACCESS_CONTROLPermission and access patterns
ACCESS_ATTEMPTAuthentication or login attempts
PROTECTED_RESOURCESensitive data or resources
AUTH_CONTEXTAuthentication state
DATA_DESTRUCTIONDestructive data operations
PRODUCTION_CONTEXTProduction environment signals
BULK_SCOPELarge-scale or bulk operations
Example
A fintech company that considers all new beneficiary transactions high-risk:

json

An override that reduces risk for internal transfers:

json

Enforcement Rules
Enforcement rules directly control what happens when their conditions are met. Unlike semantic overrides, they do not adjust risk scores and instead apply a decision immediately.
Structure
FieldRequiredDescription
whenYesCondition (PolicyNode) that activates the rule
decision_effectYesAction to enforce
priorityNo-1000 to 1000, higher runs first (default: 0)
codeNoIdentifier for tracking
Decision effects
EffectBehavior
allowLet the action through
cautionProceed with awareness; soft gate
reviewPause and require active attention
blockStop the action
escalate_one_levelIncrease severity by one step
deescalate_one_levelDecrease severity by one step
Level Actions
You can also map each pressure level to a specific enforcement action. This overrides the default behavior system-wide for your project.
LevelDefault behaviorYour override
lowallowAny action
mediumcautionAny action
highreviewAny action
criticalblockAny action
Example
Block all actions when a behavior lockdown is active:

json

Limits
ResourceMaximum
Semantic overrides per project100
Enforcement rules per project100
When to use Behavior Intelligence vs Rules
Use caseUse
Domain-specific risk sensitivityBehavior Intelligence (risk tolerance)
Inject risk signals based on conditionsBehavior Intelligence (semantic overrides)
Override enforcement for specific patternsBehavior Intelligence (enforcement rules)
Business rules with complex conditionsRules
Rules that need weight-based scoringRules
Both work together. Behavior Intelligence shapes the risk landscape and rules apply business logic on top.
Next steps
Now that you understand Behavior Intelligence, learn how to define Rules that encode your business logic and compliance requirements.
Rules
Define rules that control what is allowed, restricted, or blocked with full support for conditions, effects, and enforcement actions.