> ## Documentation Index
> Fetch the complete documentation index at: https://docs.contactbutton.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Human and agent chat

> Configure chat routing modes for human, agent-assisted, and agent-to-agent conversations, with suggested replies, participant tokens, and human escalation.

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.

<Note>
  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.
</Note>


## Related topics

- [Set up with a coding agent](/agents/coding-agents.md)
- [Update notification and agent policy settings](/api-reference/workspaces/update-notification-and-agent-policy-settings.md)
- [Changelog](/changelog.md)
- [Connect Telnyx](/guides/telnyx.md)
- [Update a page](/api-reference/pages/update-a-page.md)