office-assistant-ingest-meeting.yaml

name: office-assistant-ingest-meeting
description: >
  Turn a pasted meeting transcript into structured notes. An LLM writes a summary
  and extracts action items; the notes are stored in a Postgres full-text
  knowledge base; a single Jira issue is opened for the action items; and the
  summary is posted to Teams. Pair with office-assistant-ask.yaml for retrieval.
  Requires the schema in office-assistant-kb-schema.sql.

inputs:
  title:
    type: string
    description: Meeting title
  meeting_date:
    type: string
    description: "Meeting date, YYYY-MM-DD (optional)"
    default: ""
  attendees:
    type: string
    description: "Comma-separated attendee names (optional)"
    default: ""
  transcript:
    type: string
    description: The full meeting transcript — paste it in via a --values file

steps:
  # 1. Summarize the transcript and extract structured action items.
  - name: summarize
    action: ai/completion
    credential: openai
    timeout: "90s"
    params:
      model: gpt-4o
      system_prompt: >
        You are a meeting-notes assistant. From a raw transcript produce: a
        concise summary; a list of concrete action items, each with a short
        title, a one-line description, and the owner if one was named; a
        plain-text rendering of those same action items, one per line as
        "Title — description (owner)"; and the key topics discussed. Use only
        information present in the transcript.
      prompt: >
        Meeting: {{ inputs.title }}
        Attendees: {{ inputs.attendees }}

        Transcript:
        {{ inputs.transcript }}
      output_schema:
        type: object
        properties:
          summary:
            type: string
          action_items:
            type: array
            items:
              type: object
              properties:
                title:
                  type: string
                # description/owner are nullable rather than optional: OpenAI
                # strict structured output requires every declared property to
                # appear in `required`, so absent values must be expressible as
                # null instead of being omitted from the schema.
                description:
                  type:
                    - string
                    - "null"
                owner:
                  type:
                    - string
                    - "null"
              required:
                - title
                - description
                - owner
              additionalProperties: false
          action_items_text:
            type: string
          topics:
            type: array
            items:
              type: string
        required:
          - summary
          - action_items
          - action_items_text
          - topics
        additionalProperties: false

  # 2. Persist the note into the knowledge base (see office-assistant-kb-schema.sql).
  #    action_items and topics are stored as JSONB; the search tsvector is
  #    generated by Postgres from title/summary/transcript.
  - name: store-note
    action: postgres/query
    credential: kb-db
    depends_on:
      - summarize
    timeout: "15s"
    params:
      # ON CONFLICT makes re-ingesting the same transcript a no-op (dedupe_key
      # is md5(transcript)); rows_affected is then 0 and the steps below skip.
      query: >
        INSERT INTO meeting_notes
          (title, meeting_date, attendees, summary, action_items, topics, transcript)
        VALUES ($1, NULLIF($2, '')::date, $3, $4, $5::jsonb, $6::jsonb, $7)
        ON CONFLICT (dedupe_key) DO NOTHING
      args:
        - "{{ inputs.title }}"
        - "{{ inputs.meeting_date }}"
        - "{{ inputs.attendees }}"
        - "{{ steps['summarize'].output.json.summary }}"
        - "{{ jsonEncode(steps['summarize'].output.json.action_items) }}"
        - "{{ jsonEncode(steps['summarize'].output.json.topics) }}"
        - "{{ inputs.transcript }}"

  # 3. Open one Jira issue capturing the action items (skipped if there are none).
  #    Per-item fan-out would need a loop construct, which the engine does not
  #    yet have — a single checklist issue is the clean one-step equivalent.
  - name: create-action-items
    action: jira/create_issue
    credential: jira
    depends_on:
      - summarize
      - store-note
    if: "steps['store-note'].output.rows_affected > 0 && size(steps['summarize'].output.json.action_items) > 0"
    params:
      project_key: OPS
      issue_type: Task
      summary: "Action items — {{ inputs.title }}"
      # jira/create_issue wraps description as a plain-text ADF paragraph, so
      # send the plain-text rendering rather than markdown (which would show
      # its syntax literally).
      description: "{{ steps['summarize'].output.json.action_items_text }}"

  # 4. Post the summary to a Teams channel (incoming-webhook credential).
  #    Skipped on a duplicate re-ingest (store-note inserted no row).
  - name: notify-team
    action: teams/send_message
    credential: teams
    depends_on:
      - store-note
    if: "steps['store-note'].output.rows_affected > 0"
    params:
      title: "Meeting notes — {{ inputs.title }}"
      text: "{{ steps['summarize'].output.json.summary }}"