Safety protections are built into every AloAi Voice Agent and are always active by default. They run automatically in the background, so there’s nothing for admins to configure or manage.
During each call, the system evaluates the conversation in real time before generating a response or triggering any action.
If a safety violation is detected, the interaction is immediately stopped and the call is ended. This prevents any restricted or unsafe content from being delivered to the user.
How content is evaluated
The safety system continuously reviews both what the user says and how the agent responds. This ensures that conversations stay within defined safety and compliance boundaries.
To do this, it applies checks across two areas: (1) what the agent is allowed to say and (2) what inputs it can respond to.
Restricted output categories
The agent will not generate responses involving:
Harassment or abusive language
Self-harm or suicide-related content
Sexual exploitation or explicit content
Violence or threats of harm
Defense or national security-related topics
Illegal or harmful activities
Gambling-related content
Regulated professional advice (e.g., medical or legal guidance)
Child safety or exploitation-related content
Restricted input categories
User inputs are also evaluated to detect and block attempts to interfere with the system, including:
Bypassing instructions through prompt injection or jailbreaking
Manipulating or overriding system behavior or safety rules
What happens when a violation is detected
When the system identifies a violation, it immediately shifts to a fail-safe state:
Response generation stops instantly
No partial or in-progress response is returned
No tools or external actions are executed
The call is disconnected right away
At the same time, the system records the event by creating an audit log that includes the bot ID, company ID, call ID, and the reason for disconnection.
Scope of enforcement
These safety protections apply consistently across all AloAi Voice Agents and cannot be adjusted or turned off at the agent level.
They cover all voice-based experiences, including inbound and outbound agents, AI Call Rescue flows, and IVA bots.
Important clarification
These protections are designed to intervene only when necessary. Standard, on-topic conversations are not affected.
Under normal conditions, the agent continues to operate as configured, following its prompts, using assigned tools, and handling conversations without interruption.