Skip to main content

​
Compliance & Security

These features enforce compliance, prevent hallucinations, and protect against misuse during voice calls.
Automatically announce that the call is being recorded, either before or after the greeting. 
{
  "complianceConsentEnabled": true,
  "complianceConsentMessage": "This call may be recorded for quality and training purposes.",
  "complianceConsentPosition": "before_greeting"
}
SettingTypeDefaultDescription
complianceConsentEnabledbooleanfalseEnable recording consent announcement
complianceConsentMessagestring—Consent announcement text
complianceConsentPositionstringbefore_greetingWhen to play: before_greeting or after_greeting

​
Hallucination Guardrails

Restrict the agent to specific topics, block sensitive topics, and prevent prohibited statements. 
{
  "guardrailsEnabled": true,
  "allowedTopics": ["billing", "account", "products", "shipping"],
  "blockedTopics": ["politics", "religion", "competitors"],
  "prohibitedStatements": [
    "I guarantee that...",
    "You will definitely...",
    "We promise..."
  ],
  "requireKnowledgeBase": true,
  "guardrailAction": "apologize"
}
SettingTypeDefaultDescription
guardrailsEnabledbooleanfalseEnable topic guardrails
allowedTopicsstring[][]Topics the agent CAN discuss (empty = all allowed)
blockedTopicsstring[][]Topics the agent must NEVER discuss
prohibitedStatementsstring[][]Phrases the agent must never say
requireKnowledgeBasebooleanfalseOnly provide info from the knowledge base
guardrailActionstringapologizeOn violation: apologize, redirect, escalate

​
Guardrail Actions

ActionBehavior
apologize”I’m sorry, I’m not able to help with that topic.”
redirectRedirect conversation back to an allowed topic
escalateOffer to transfer the caller to a human agent

​
Knowledge Gap Detection

Track when the agent doesn’t know the answer to a question. Gaps are logged for knowledge base improvement. 
{
  "knowledgeGapDetectionEnabled": true,
  "knowledgeGapWebhookUrl": "https://your-app.com/webhooks/knowledge-gaps"
}
When the agent encounters a question it can’t answer, it internally marks it with [KNOWLEDGE_GAP: topic]. After the call, gaps are extracted and sent to the configured webhook or saved to the session.

​
Live Call Monitoring

Allow supervisors to listen to active calls and optionally join (barge-in) or whisper to the agent. 
{
  "liveMonitoringEnabled": true,
  "monitoringAllowBargeIn": true,
  "monitoringAllowWhisper": true
}
SettingTypeDefaultDescription
liveMonitoringEnabledbooleanfalseEnable live monitoring
monitoringAllowBargeInbooleanfalseAllow supervisor to speak to the caller
monitoringAllowWhisperbooleanfalseAllow supervisor to coach the agent silently

​
Speech Emotion Detection

Monitor the caller’s emotional state through voice analysis and adjust the agent’s behavior accordingly. 
{
  "speechEmotionDetectionEnabled": true,
  "emotionDetectionModel": "basic",
  "emotionEscalationThreshold": 0.7
}
ModelBehavior
basicMonitor emotions through word choices. Acknowledge frustration empathetically.
advancedTrack tone, pace, and word choices. Proactively adjust approach for strong negative emotions.

​
Call Scoring & QA

Automatically score each call against quality criteria after it ends. 
{
  "callScoringEnabled": true,
  "scoringCriteria": [
    "greeting_quality",
    "issue_resolution",
    "professionalism",
    "call_efficiency"
  ],
  "scoringModel": "gpt-4o-mini"
}
After the call, the LLM reviews the transcript and assigns scores for each criterion.

​
Example — Create Agent with Compliance & Security

curl -X POST https://api.thinnest.ai/v1/agents \
  -H "Authorization: Bearer $THINNESTAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Compliant Support Agent",
    "model": "gpt-4o",
    "instructions": "You are a customer support agent. Stay on-topic — only discuss billing, accounts, and products. Never make promises or guarantees.",
    "voiceEnabled": true,
    "transcriber": { "provider": "deepgram", "model": "nova-2-conversationalai" },
    "voice": { "provider": "deepgram", "voiceId": "aura-2-thalia-en" },
    "complianceConsentEnabled": true,
    "complianceConsentMessage": "This call may be recorded for quality and training purposes.",
    "complianceConsentPosition": "before_greeting",
    "guardrailsEnabled": true,
    "allowedTopics": ["billing", "account", "products", "shipping"],
    "blockedTopics": ["politics", "religion", "competitors"],
    "prohibitedStatements": ["I guarantee", "You will definitely", "We promise"],
    "guardrailAction": "apologize",
    "knowledgeGapDetectionEnabled": true,
    "callScoringEnabled": true,
    "scoringCriteria": ["greeting_quality", "issue_resolution", "professionalism"],
    "scoringModel": "gpt-4o-mini"
  }'