GuardRail: Behavioral Activity

Behavioral Activity is the WitnessAI user behavior and intention GuardRail. Its purpose is to monitor user behavior during interactions with AI models, determine the user’s intentions, and provide control over these activities.

When this Guardrail detects specified activities, it provides the option to Allow, Warn, Block or Route the prompt to another model.

For example, technical support-related behaviors can be automatically routed to an internal model designed to assist employees, ensuring appropriate handling and alignment with internal policies.

WitnessAI Policies enable organizations to manage and control AI usage effectively. By using Behavioral Activity GuardRail, administrators can define rules that enhance compliance, productivity, and ethical AI use.

Use Case Examples

Ethical AI Usage

Warn or block users attempting to engage in unethical or non-compliant behavior.

Secure AI Usage:

Block users generating prompts that might lead to security or compliance risks.

Behavioral Activity GuardRails are integrated into policies to provide granular control over user behaviors.

Technical Support Queries

Route prompts requesting technical support to an internal model specialized for technical assistance.

Using Behavioral Activity Step-by-Step

This section covers details on how to add a Behavioral Activity GuardRail to a Policy.

Adding a Behavioral Activity GuardRail

WitnessAI policy editor showing how to add a Behavioral Activity GuardRail with numbered callouts: (1) Guard Rails tab highlighted, (2) Behavioral Activity selected in left panel, (3) enable toggle (blue), (4) Blocklist/Allowlist dropdown with (5) Blocklist option selected. Policy name shown: ‘AI policy: Using LLMs to write code is prohibited.’ The GuardRail description explains it detects user behaviors and provides Allow, Warn, or Route options.

After creating a Policy

Click the Guard Rails (1) tab in the policy editor.
Select the Behavioral Activity (2) GuardRail from the available options.
Click the slide button (3) to enable the GuardRail.
Click the down-arrow (4) and choose ‘Blocklist’ or ‘Allowlist’ from the drop-down list.

‘Blocklist’ only blocks the behaviors explicitly listed, and everything else is allowed by default.

‘Allowlist’ only allows the behaviors explicitly listed, and everything else is blocked by default.

Add one or more Behaviors

One or more Behaviors can be added to each Input Behavior section, and one or more Input Behavior sections can be added to a single Policy, as shown in the image below.

Specify the action to take when the Behavioral Activity GuardRail detects relevant behaviors. Note that choosing ‘Allowlist’ or ‘Blocklist’, will determine which options are displayed in the following section, as shown below.

Allowlist presents these options:

Allow: Permit the behavior without restriction.
Warn: Display a customizable warning message to the user.
Route: Redirect the detected behavior to a specific model for specialized handling (e.g., route technical queries to an internal support model).

“Block” is not available for the Allowlist option. All Allowlist behavior is expected to be allowed. Any behavior that needs to be blocked, should have a GuardRail defined for that.

Blocklist

Block: Block the behavior, with an optional message to the user.
Warn: Display a customizable warning message to the user.
Route: Redirect the detected behavior to a specific model for specialized handling (e.g., route technical queries to an internal support model).

“Allow” is not available for a GuardRail defined as “Blocklist” by default.

Customize any associated messages or routing details as needed.
Save the configuration.
Test the policy in a controlled environment to ensure it behaves as expected.

💡

Note: When multiple Behavior sections are defined within a Behavioral GuardRail, they have an implied “OR” relationship.

WitnessAI policy editor for ‘Seth’s Fortinet Block Policy’ showing the Behavioral Activity GuardRail with Allowlist mode and multiple Behavior sections. First Behavior has Input Behaviors: ‘Programming Inquiry’ and ‘Calculation Request’ with Action: Seth Fortinet - Block Policy - BA. Second Behavior has Input Behaviors: ‘Financial Advice’ and ‘Legal Advice’ with Action: Warn and Message: ‘Always check with a Licensed Professional for Financial and Legal advice.’

Best Practices

Multiple Input Behavior sections can be defined within a Behavioral GuardRail, as in the image above, they have an implied “OR” relationship. This means that as the GuardRail evaluates the User Prompts, it will evaluate each Behavior from the top to the bottom, and the first one that matches will have it’s action applied to the Prompt. Subsequent Behaviors lower down the list will not be evaluated for that Prompt.
Behavior Routing: Define clear rules for routing prompts to appropriate models based on detected behaviors.
Customization: Use the customizable warning feature to provide context-specific guidance.
Testing: Always test policies and GuardRails in a controlled environment before deploying them organization-wide.

Behavioral Activity GuardRail Use Case Examples Ethical AI Usage Secure AI Usage:Technical Support Queries Using Behavioral Activity Step-by-Step Adding a Behavioral Activity GuardRail Add one or more Behaviors Best Practices