Elastic Stack · OpenAPI Overlay 1.0.0

API Evangelist conversational phrasing for Kibana Observability AI Assistant API

2 actions 2 updates phrasing extends openapi/elk-stack-observability-ai-assistant-api-openapi.yml

Generated by API Evangelist Written by API Evangelist tooling for Elastic Stack's API. It is a proposal applied on top of the contract, not a document Elastic Stack publishes.

View Overlay File View on GitHub Overlay Specification

What the actions change

x-apievangelist-phrasing

Targets 2

$.info

$.paths['/api/observability_ai_assistant/chat/complete'].post

OpenAPI Overlay

# Generated by API Evangelist (build-phrasing.py). Our phrasing, not observed demand.
overlay: 1.0.0
info:
  title: API Evangelist conversational phrasing for Kibana Observability AI Assistant API
  version: 1.0.0
extends: openapi/elk-stack-observability-ai-assistant-api-openapi.yml
actions:
- target: $.info
  update:
    x-apievangelist-phrasing:
      method: generated
      generated: '2026-09-26'
      generator: build-phrasing.py
      label: Generated by API Evangelist
      operations: 1
- target: $.paths['/api/observability_ai_assistant/chat/complete'].post
  update:
    x-apievangelist-phrasing:
      intent: Get a chat completion from the AI Assistant
      effect: write
      questions:
      - How do I ask the Observability AI Assistant a question through the API?
      - Can I continue an existing AI Assistant conversation?
      - Can I stop the assistant from calling functions during a chat?
      instructions:
      - text: 'Send messages {messages} to the Observability AI Assistant using connector {connectorId}, saving the conversation: {persist}.'
        slots:
          messages: requestBody.messages
          connectorId: requestBody.connectorId
          persist: requestBody.persist
      - text: Continue conversation {conversationId} with {messages} via connector {connectorId}, persist {persist}.
        slots:
          conversationId: requestBody.conversationId
          messages: requestBody.messages
          connectorId: requestBody.connectorId
          persist: requestBody.persist
      method: generated
      generated: '2026-09-26'