Agent structure
Each agent consists of several configuration sections:General settings
Basic agent metadata displayed in the UI.Visual identifier for the agent (single emoji)
Multi-language agent name
Multi-language description of agent purpose
Context settings
Control which business data is automatically injected into the agent’s system prompt.Include company branding information
Include branch locations and details
Include service catalog information
Include product catalog information
Personality
Define your agent’s character and behavioral guidelines. All fields support multi-language configuration.The agent’s persona name (e.g., “Sarah the Support Specialist”)
What the agent does
List of what the agent can do
Behavioral guidelines and restrictions
Communication style directives
Well-defined personality traits dramatically improve conversation quality. Be specific about tone, capabilities, and ethical boundaries.
Utterances
Configure opening and closing messages.How the conversation begins:
None- Wait for user to speak firstStatic- Predefined greetingDynamic- AI-generated based on context
Multi-language static opening (if OpeningType is Static)
Multi-language closing message
Interruptions
Configure turn-taking and barge-in behavior. See Interruptions for detailed configuration.Enable strict turn-taking (no barge-in allowed)
Configuration for detecting when user has finished speaking
Optional: Pause agent speech when user starts talking
Optional: Use LLM to verify if interruption is intentional
Knowledge base
Configure RAG (Retrieval Augmented Generation) for your agent.Enable knowledge base integration
When to retrieve knowledge:
OnEveryQuery- Search on every user messageOnDemand- Only when AI requests it via toolHybrid- Combination approach
Number of relevant chunks to retrieve
Minimum similarity score (0.0 - 1.0)
Optional: Use LLM to refine and summarize retrieved chunks
Integrations
Connect your AI service providers. Iqra AI follows a “Bring Your Own Model” architecture.Language model configurationSupported providers:
- OpenAI (GPT-4, GPT-3.5)
- Azure OpenAI
- Anthropic (Claude)
- Google (Gemini)
- Groq
- Custom endpoints
Speech-to-Text configurationSupported providers:
- Deepgram
- Azure Speech
- Google Speech
- AssemblyAI
Text-to-Speech configurationSupported providers:
- ElevenLabs
- Azure Speech
- Google TTS
- OpenAI TTS
- PlayHT
Cache
Optimize performance with intelligent caching.Audio caching
Automatically cache repeated TTS outputs
Cache after N identical generations
Embeddings caching
Cache vector embeddings for knowledge base
Settings
Background audio
S3 link to background music/ambience file
Volume level (0-100)
References
Agents can be deployed to multiple channels:- InboundRoutingReferences - Phone numbers for SIP inbound calls
- TelephonyCampaignReferences - Outbound calling campaigns
- WebCampaignReferences - WebRTC/WebSocket deployments
Configuration best practices
Test personality changes
Small changes in tone or ethics can dramatically affect behavior. Test thoroughly.
Match integrations to language
Use native-language models when possible (e.g., Azure for Arabic, Deepgram for English).
Next steps
Visual IDE
Build conversation scripts visually
Interruptions
Configure advanced turn-taking
Integrations
Connect AI service providers