Skip to main content
Cevro includes built-in detection for compliance-critical scenarios. Configure these in Settings → Agent Configuration → Compliance.

​
Responsible Gaming (RG)

Cevro can detect when players express responsible gaming concerns and respond appropriately.

​
What It Detects

  • Self-exclusion requests (“I need to stop gambling”)
  • Addiction concerns (“I can’t control my spending”)
  • Financial distress related to gambling
  • Requests for cooling-off periods or deposit limits
  • References to problem gambling resources

​
Configuration

Toggle Detect Responsible Gaming to enable detection. When enabled, choose how Cevro should respond:
ActionBehavior
EscalateImmediately transfers to a human agent
Empathic ResponseCevro acknowledges with empathy and continues handling

​
Communication Instructions

Provide guidance for how Cevro should communicate when RG is detected. This shapes the tone of the response before escalating or continuing. Example for Escalate: 
Inform the player: "I'm sorry to hear you're having difficulty. We're here to help.
It's important to review our responsible gaming policies.
I'm going to transfer you to a specialist who can assist you."
Example for Empathic Response: 
Inform the player: "I'm sorry to hear you're having difficulty. We're here to help.
It's important to review our responsible gaming policies and get support from a professional.
We're here to support you."
Most jurisdictions require escalation to trained staff for RG concerns. Use Empathic Response only if your compliance team has approved AI-handled RG responses.

​
Toxicity Detection

Cevro can detect and handle abusive language from players.
Toxicity detection must be enabled by your account executive. If you don’t see these settings in Compliance, contact your CSM.

​
How It Works

When enabled, Cevro categorizes problematic language and responds based on severity:
CategoryWhat It DetectsWhat Happens
ThreatsViolence, harm directed at agentImmediately escalated to live agent
Severe ProfanityAbuse directed at the agent personallyChat closes immediately, no warnings
Moderate ProfanityFrustration about the situationSingle warning, closes if repeated
Light ProfanityCasual expressionsIgnored, conversation continues

​
Custom Warning Instructions

You can customize how Cevro delivers warnings for moderate profanity. This lets you add your brand’s voice to warning messages. Example: 
Our platform values respectful communication. Please keep our conversation
professional so I can best assist you. Continued profanity will result
in chat closure.
Custom instructions only apply to moderate profanity warnings. Threats are always escalated immediately, and severe abuse closes the chat without warnings.

​
Regulatory Notes

Many jurisdictions require:
  • Clear self-exclusion processes
  • Prompt response to RG concerns
  • Audit trails for RG interactions
  • Escalation to trained staff
Cevro’s RG detection and escalation features help meet these requirements, but human oversight is still required for final RG decisions. RG-flagged conversations are logged for audit purposes and should be retained according to your jurisdiction’s requirements.