Skip to main content
Page owners choose allowed modes:
  • human — route directly to a person.
  • agent_assisted — use public knowledge first and offer human escalation.
  • agent_to_agent — allow an external agent to converse with the owner’s agent when explicitly enabled.
The default excludes agent-to-agent chat. Conversations store participant type, opaque agent identity, routing mode, messages, and escalation timestamps. Suggested-reply pills are returned as structured options so both the visual widget and an external agent can choose the same guided path. Creation returns an opaque participant_token once. Send it as X-Conversation-Token when posting later messages or requesting a human; the stored conversation contains only its hash. The authenticated workspace inbox can list a conversation, read its messages, mark a human as joined, reply as the owner, and close it. A human-escalation request respects the workspace’s chat notification preference.
The initial API provides durable conversation and escalation state. An LLM provider is not called automatically, so owners can connect their preferred model and moderation policy without coupling conversation storage to one vendor.