The AI pipeline
When a customer sends a message, Chatonio's AI pipeline processes it through several steps:
- Context building — the system prompt, conversation history, relevant FAQ entries, and knowledge base articles are assembled
- AI response — the configured AI model generates a response using this context
- Escalation check — a lightweight check determines if the conversation should be flagged for human review
- Delivery — the response is sent back through the originating channel
Knowledge sources
The AI draws from two main knowledge sources to give accurate answers:
- FAQ entries — question/answer pairs matched by keyword relevance
- Knowledge base articles — longer-form content, truncated and injected as reference
Both FAQ and articles must have AI enabled turned on to be included in the AI's context.
Model configuration
Chatonio supports multiple AI providers (Anthropic Claude, DeepSeek, Ollama). You can configure:
- Primary model — used for customer responses (higher quality)
- Utility model — used for summaries, escalation checks (lower cost)
Models are configured at the project level and can be overridden per channel.