Release notes

September 1, 2026

Glossary API is available

The Glossary API provides create, read, update, and delete access to an AI Agent’s glossary. A glossary term is a word or phrase the AI Agent should recognize in an end user’s message. In custom mode, the AI Agent also restates the term using your preferred wording. Manage glossary terms through code and version control instead of only through the dashboard.

API endpoints

Five REST endpoints are available:

  • List glossary terms (GET /v2/glossary/): Returns the AI Agent’s terms in cursor-paginated pages ordered by id.
  • Create a glossary term (POST /v2/glossary/): Creates a term. The external_id is your own identifier for it and must be unique within the AI Agent.
  • Get a glossary term (GET /v2/glossary/{glossary_term_id}): Returns a single term by its id.
  • Update a glossary term (PATCH /v2/glossary/{glossary_term_id}): Partially updates a term; only the fields in the request body change.
  • Delete a glossary term (DELETE /v2/glossary/{glossary_term_id}): Permanently deletes a term, along with any availability rule attached to it.

Each term can carry an availability_rules rule that gates when it applies. Set voice_detection_enabled to help the voice agent recognize the term in speech. Set voice_pronunciations to control how the AI Agent says the term on a voice call.

Get started

Read the full reference for fields, limits, and authentication.

September 1, 2026

Playbooks API is available

The Playbooks API provides create, read, update, and delete access to an AI Agent’s Playbooks. Playbooks are the structured, step-based workflows that guide the Agent through multi-step conversations. Manage Playbooks through code and version control instead of only through the dashboard.

API endpoints

Five REST endpoints are available:

  • List Playbooks (GET /v2/playbooks/): Returns the AI Agent’s Playbooks, enabled or not, in cursor-paginated pages ordered by id.
  • Create a Playbook (POST /v2/playbooks/): Creates a Playbook. New Playbooks default to draft.
  • Get a Playbook (GET /v2/playbooks/{playbook_id}): Returns a single Playbook by its id.
  • Update a Playbook (PATCH /v2/playbooks/{playbook_id}): Partially updates a Playbook in place; only the fields in the request body change.
  • Delete a Playbook (DELETE /v2/playbooks/{playbook_id}): Deletes a Playbook, and returns 409 when another Playbook’s run step targets it.

Each Playbook can carry an availability rule that gates when the Agent uses it. Rules reference variables by id.

Setting enabled: true validates the step graph, the variable scopes, and the condition operators before the Playbook goes live. A Playbook that fails validation is not saved.

Get started

September 1, 2026

Web Chat SDK: control whether reset() applies caller meta fields

The Web Chat SDK now supports the allowMetaFieldsInReset setting. It controls whether a full reset({ metaFields }) applies caller-supplied meta fields to the new conversation.

The setting defaults to true, so reset meta fields apply. Set it to false to block them. The SDK captures the value for each start() call. Calling stop() and then start() with different settings can enable reset meta fields again. Other meta field methods remain available to page scripts.

When you opt out, a full reset restores the meta fields you passed to the initial start() call. The new conversation starts from that host baseline.

History-preserving resets (resetChatHistory: false) apply reset meta fields regardless of this setting.

To learn more, see the Web Chat SDK reference.