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

# Query Meeting Memories

> Queries the user's meeting knowledge bases (pre-meeting prep and/or post-meeting follow-up) with metadata filtering, date sorting, and optional LLM-powered Q&A. Supports recurring event series via wildcard patterns.



## OpenAPI

````yaml /api-reference/v1/v1.1.0_openapi.json post /action/meeting_prep_query_meeting_memories
openapi: 3.0.0
info:
  version: 1.1.0
  title: AI Actions - Get Data
  description: API specifications for 'Get Data' category AI actions.
  license:
    name: MIT
servers:
  - url: https://api-lr.agent.ai/v1
security:
  - bearerAuth: []
paths:
  /action/meeting_prep_query_meeting_memories:
    post:
      tags:
        - Meeting Prep V3
      summary: Query Meeting Memories
      description: >-
        Queries the user's meeting knowledge bases (pre-meeting prep and/or
        post-meeting follow-up) with metadata filtering, date sorting, and
        optional LLM-powered Q&A. Supports recurring event series via wildcard
        patterns.
      operationId: meetingPrepQueryMeetingMemories
      requestBody:
        required: true
        content:
          application/json:
            schema:
              type: object
              properties:
                event_id:
                  type: string
                  description: >-
                    Calendar event ID. For recurring meetings, a specific
                    instance like 'abc_20260217T153000Z' is auto-converted to
                    'abc_*' to match the full series. Use 'abc_*' directly for
                    explicit wildcards, or 'abc123' for a single event.
                kb_scope:
                  type: string
                  enum:
                    - both
                    - pre
                    - post
                  description: Which meeting KB(s) to query.
                  default: both
                sort_order:
                  type: string
                  enum:
                    - desc
                    - asc
                  description: Sort memories by meeting date.
                  default: desc
                context_limit:
                  type: string
                  description: Maximum number of meeting memories to include.
                  default: '20'
                  pattern: ^[0-9]+$
                mode:
                  type: string
                  enum:
                    - list
                    - query
                  description: >-
                    'list' returns memories with metadata (no LLM). 'query'
                    sends memories as context to an LLM with your prompt.
                  default: list
                prompt:
                  type: string
                  x-ui: textarea
                  description: >-
                    The question to ask about the meeting memories (only used in
                    'query' mode).
                output_variable_name:
                  type: string
                  description: >-
                    Variable name to store the result. In 'list' mode: memories
                    array. In 'query' mode: includes llm_response.
                  default: meeting_memories
                  pattern: ^[a-zA-Z][a-zA-Z0-9_]*$
              required:
                - kb_scope
                - sort_order
                - context_limit
                - mode
                - output_variable_name
      responses:
        '200':
          description: Successful response
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ActionResponse'
        '400':
          description: Bad request
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ActionResponse'
        '401':
          description: Unauthorized - invalid or missing bearer token
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ActionResponse'
        '500':
          description: Internal server error
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ActionResponse'
components:
  schemas:
    ActionResponse:
      type: object
      properties:
        status:
          type: integer
          format: int32
          description: HTTP status code of the action response
        response:
          type: object
          description: Response data from the action
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: >-
        Bearer token from your account
        ([https://agent.ai/user/integrations#api](https://agent.ai/user/integrations#api))

````