Chat AI agent
/dashboard/chat-ai — configure a per-client AI agent that auto-replies to inbound
text when the conversation is in AI mode.
What you configure
- Persona name — what the agent calls itself (“Maya”, “Acme’s assistant”)
- Persona tone — friendly / formal / casual / professional
- Business description — markdown blob folded into the system prompt
- FAQ knowledge — markdown FAQ block; the agent uses this for retrieval-ish Q&A
- Guardrails — hard rules as bullet points (“Never quote prices”, “Don’t make promises about timelines”, “Always greet the customer by name if known”)
- Auto-handover phrases — substring matches that flip the conversation to HUMAN mode (“agent se baat”, “talk to a human”, “real person”)
- Confidence threshold — 0..1. Replies below this are suppressed; conversation flips to HUMAN.
- Reply delay — min + max milliseconds. The agent waits a randomised interval before sending so it doesn’t feel bot-fast.
- Max replies per conversation — safety cap to prevent infinite back-and-forth.
Chat modes per conversation
| Mode | Behaviour |
|---|---|
| HUMAN | AI silent. Agent replies manually. |
| AI | Every text inbound triggers an AI reply. |
| FLOW | A flow is running on this conversation; AI defers. |
| HYBRID | AI suggests a reply (shown in the composer); agent reviews + sends. |
Toggle via the conversation header in the inbox.
How the AI knows what to say
System prompt is assembled from:
- Persona name + tone (gives a voice)
- Business description (gives context)
- FAQ knowledge (gives canned answers)
- Guardrails (gives don’ts)
- Recent conversation history (last ~10 turns)
User prompt is the customer’s latest inbound text.
Auto-handover
Two paths to handover:
- Substring match on configured auto-handover phrases → instant HUMAN flip
- Low confidence — AI returns reply but the confidence score is below threshold → suppress + flip HUMAN
In both cases the conversation gets a system note: “Handed off to a human agent.”
Last updated on