コンテンツにスキップ
Greentic Docs

Flows

Flow とは?

Section titled “Flow とは?”

Flow は、メッセージとデータが digital worker 内をどのように移動するかを記述する YAML 定義の orchestration graph です。flow は .ygtc ファイルに保存され、次を定義します:

  • Nodes - 個々の処理ステップ (WASM components)
  • Edges - node 間の接続
  • Triggers - flow を開始するきっかけ
  • Conditions - 分岐ロジック

基本的な Flow 構造

Section titled “基本的な Flow 構造”
flows/hello.ygtc
name: hello_world
version: "1.0"
description: A simple greeting flow


# Define the nodes (processing steps)
nodes:
  - id: greet
    type: reply
    config:
      message: "Hello! How can I help you today?"


# Define what triggers this flow
triggers:
  - type: message
    pattern: "hello|hi|hey"
    target: greet

Flow の構成要素

Section titled “Flow の構成要素”

Nodes

Section titled “Nodes”

node は flow の building block です。各 node はデータを処理する WASM component を表します:

nodes:
  - id: unique_node_id
    type: node_type           # Component type
    config:                   # Component-specific configuration
      key: value
    next: next_node_id        # Optional: next node to execute

一般的な Node Types

Section titled “一般的な Node Types”
Type用途
replyユーザーにメッセージを返す
llmLLM を呼び出す (OpenAI など)
templateHandlebars template を render する
scriptRhai script を実行する
branch条件分岐
httpHTTP request を送る
statesession state を管理する

Edges

Section titled “Edges”

edge は node 同士を接続します。next による暗黙的な接続、または明示的な接続が可能です:

nodes:
  - id: start
    type: template
    config:
      template: "Processing your request..."
    next: process


  - id: process
    type: llm
    config:
      model: "gpt-4"
      prompt: "{{message}}"
    next: respond


  - id: respond
    type: reply
    config:
      message: "{{llm_response}}"

Triggers

Section titled “Triggers”

trigger は flow を開始する条件を定義します:

triggers:
  # Message pattern trigger
  - type: message
    pattern: "order|purchase|buy"
    target: handle_order


  # Default trigger (catch-all)
  - type: default
    target: fallback_handler


  # Event trigger
  - type: event
    event_type: "user.created"
    target: welcome_user

条件分岐

Section titled “条件分岐”

条件ロジックには branch node を使用します:

nodes:
  - id: check_intent
    type: branch
    config:
      conditions:
        - expression: "intent == 'greeting'"
          next: greet_user
        - expression: "intent == 'help'"
          next: show_help
        - expression: "intent == 'order'"
          next: process_order
      default: fallback


  - id: greet_user
    type: reply
    config:
      message: "Hello! Nice to meet you!"


  - id: show_help
    type: reply
    config:
      message: "Here's what I can help you with..."


  - id: fallback
    type: reply
    config:
      message: "I'm not sure I understand. Can you rephrase?"

State を扱う

Section titled “State を扱う”

flow は session state の読み書きができます:

nodes:
  - id: save_name
    type: state
    config:
      action: set
      key: "user_name"
      value: "{{extracted_name}}"
    next: confirm


  - id: get_name
    type: state
    config:
      action: get
      key: "user_name"
      output: "stored_name"
    next: greet_by_name

LLM 統合

Section titled “LLM 統合”

AI を活用した応答のために LLM を統合できます:

nodes:
  - id: analyze
    type: llm
    config:
      model: "gpt-4"
      system_prompt: |
        You are a helpful customer service agent.
        Extract the user's intent and any relevant entities.
      prompt: "User message: {{message}}"
      output_format: json
    next: process_result

Template Rendering

Section titled “Template Rendering”

動的コンテンツには Handlebars template を使います:

nodes:
  - id: format_response
    type: template
    config:
      template: |
        Hi {{user_name}}!


        Here's your order summary:
        {{#each items}}
        - {{name}}: ${{price}}
        {{/each}}


        Total: ${{total}}
    next: send_response

Flow Validation

Section titled “Flow Validation”

deployment の前に flow を検証します:

Terminal window
greentic-flow doctor ./flows/


# Or with the GTC CLI
gtc flow validate ./flows/hello.ygtc

ベストプラクティス

Section titled “ベストプラクティス”
  1. Keep flows focused - 1つの user intent または workflow ごとに 1 flow にする
  2. Use meaningful IDs - node ID は役割が分かる名前にする
  3. Document with comments - 複雑な flow には説明コメントを追加する
  4. Test incrementally - 変更のたびに検証する
  5. Version your flows - semantic versioning を使う

例: 完全なカスタマーサービス Flow

Section titled “例: 完全なカスタマーサービス Flow”
flows/customer_service.ygtc
name: customer_service
version: "1.0"
description: Handle customer inquiries with AI assistance


nodes:
  # Analyze the incoming message
  - id: analyze_intent
    type: llm
    config:
      model: "gpt-4"
      system_prompt: |
        Classify the customer's intent into one of:
        - greeting
        - order_status
        - product_question
        - complaint
        - other


        Respond with JSON: {"intent": "...", "confidence": 0.0-1.0}
      prompt: "{{message}}"
      output_format: json
    next: route_intent


  # Route based on intent
  - id: route_intent
    type: branch
    config:
      conditions:
        - expression: "intent.intent == 'greeting'"
          next: handle_greeting
        - expression: "intent.intent == 'order_status'"
          next: handle_order_status
        - expression: "intent.intent == 'complaint'"
          next: handle_complaint
      default: handle_general


  # Handle greeting
  - id: handle_greeting
    type: reply
    config:
      message: "Hello! Welcome to our support. How can I help you today?"


  # Handle order status
  - id: handle_order_status
    type: http
    config:
      method: GET
      url: "https://api.example.com/orders/{{order_id}}"
    next: format_order_response


  - id: format_order_response
    type: template
    config:
      template: |
        Your order #{{order_id}} is currently: {{status}}
        Expected delivery: {{delivery_date}}
    next: send_order_response


  - id: send_order_response
    type: reply
    config:
      message: "{{formatted_response}}"


  # Handle complaints with escalation
  - id: handle_complaint
    type: reply
    config:
      message: "I'm sorry to hear that. Let me connect you with a specialist who can help resolve this."
    next: escalate_to_human


  - id: escalate_to_human
    type: event
    config:
      event_type: "escalation.requested"
      payload:
        reason: "complaint"
        conversation_id: "{{session_id}}"


  # General handler
  - id: handle_general
    type: llm
    config:
      model: "gpt-4"
      system_prompt: "You are a helpful customer service agent. Be friendly and concise."
      prompt: "{{message}}"
    next: send_general_response


  - id: send_general_response
    type: reply
    config:
      message: "{{llm_response}}"


triggers:
  - type: message
    target: analyze_intent

次のステップ

Section titled “次のステップ”