Flows

Apa Itu Flow?

Flow adalah graf orkestrasi yang didefinisikan dalam YAML dan menjelaskan bagaimana pesan dan data bergerak melalui digital worker Anda. Flow disimpan dalam file .ygtc dan mendefinisikan:

Nodes - Langkah pemrosesan individual (komponen WASM)
Edges - Koneksi antar node
Triggers - Apa yang memulai flow
Conditions - Logika percabangan

Struktur Dasar Flow

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

Komponen Flow

Nodes

Node adalah building block dari sebuah flow. Setiap node merepresentasikan komponen WASM yang memproses data:

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

Jenis Node Umum

Type	Purpose
`reply`	Mengirim pesan kembali ke pengguna
`llm`	Memanggil LLM (OpenAI, dll.)
`template`	Merender template Handlebars
`script`	Mengeksekusi script Rhai
`branch`	Percabangan kondisional
`http`	Membuat request HTTP
`state`	Mengelola state session

Edges

Edge menghubungkan node satu sama lain. Edge dapat bersifat implisit (melalui next) atau eksplisit:

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

Trigger mendefinisikan apa yang memulai flow:

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

Percabangan Kondisional

Gunakan node branch untuk logika kondisional:

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?"

Bekerja dengan State

Flow dapat membaca dan menulis state session:

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

Integrasi LLM

Integrasikan LLM untuk respons berbasis AI:

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

Rendering Template

Gunakan template Handlebars untuk konten dinamis:

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

Validasi Flow

Validasi flow Anda sebelum deployment:

greentic-flow doctor ./flows/

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

Praktik Terbaik

Jaga flow tetap fokus - Satu flow per intent pengguna atau workflow
Gunakan ID yang bermakna - ID node harus menjelaskan tujuannya
Dokumentasikan dengan komentar - Tambahkan deskripsi pada flow yang kompleks
Uji secara bertahap - Validasi setelah setiap perubahan
Versikan flow Anda - Gunakan semantic versioning

Contoh: Flow Layanan Pelanggan Lengkap

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

Langkah Berikutnya

Packs - Kemas flow Anda untuk deployment
Components - Buat jenis node kustom
Flow Schema Reference - Skema YAML lengkap