Editor de flujo de trabajo

Construya flujos de conversación con el editor visual de flujo de trabajo

​

Descripción general

El Editor de flujo de trabajo es una herramienta visual basada en nodos para diseñar la lógica de conversación. Arrastre, suelte y conecte nodos para crear flujos de conversación complejos.

​

Tipos de nodos

​

Nodo de inicio

El punto de entrada de cada flujo de trabajo. Cada flujo de trabajo tiene exactamente un nodo de inicio.

​

Nodo LLM

Envía un mensaje al modelo de IA configurado y devuelve la respuesta.

Configuración:

• Temperatura (0.0 - 1.0)
• Máximo de tokens
• Anulación personalizada del prompt del sistema

​

Nodo de condición

Ramifica el flujo de trabajo según condiciones. Soporta:

• Coincidencia de palabras clave
• Análisis de sentimiento
• Expresiones personalizadas

​

Nodo de llamada a herramienta

Ejecuta una función externa o llamada API. Los resultados se pasan de vuelta al contexto de la conversación.

​

Nodo de llamada de voz

Gestiona interacciones específicas de voz — reconocimiento y síntesis de voz.

​

Nodo final

Termina la conversación con un mensaje de cierre opcional.

​

Conexión de nodos

Haga clic en el puerto de salida de un nodo y arrastre hasta el puerto de entrada de otro nodo para crear una conexión. Cada conexión representa una ruta posible de la conversación.

​

Mejores prácticas

Construya siempre rutas explícitas entre nodos con condiciones claras. Sin embargo, en algunos casos la IA puede enrutar autónomamente a un nodo que no tiene arista directa — esto se denomina sinapsis. Las sinapsis ocurren cuando la IA determina que las condiciones de enrutamiento existentes son poco claras o insuficientes y decide alcanzar un nodo por su cuenta. Si bien esto proporciona flexibilidad, las sinapsis frecuentes generalmente indican que sus condiciones de arista necesitan ser más específicas.

• Mantenga los flujos de trabajo simples — los flujos complejos son más difíciles de depurar
• Use nodos de condición para manejar casos límite
• Pruebe cada ruta individualmente antes de publicar

---

​

Generar workflow con Claude Code

Si desea crear un workflow personalizado para su agente de IA basado en sus requisitos de negocio, puede usar Claude Code para generar una plantilla de workflow JSON lista para usar.

Prompt para generación de workflow

# Instruction: Generate a Revol Workflow Template JSON

## Context

I use Revol — a platform for building AI sales agents. Each agent
has a visual workflow editor with nodes and edges that define
conversation logic.

I need you to generate a workflow template as a JSON object that
I can import into my Revol agent. The JSON follows a strict schema
used by Revol's template system.

## JSON Schema

The output must be a single JSON object with these top-level keys:

{
  "nodes_data": [...],
  "edges_data": [...],
  "tools_data": {...},
  "memory_fields_data": [...]   // optional
}

### nodes_data (array of objects)

Each node object has these fields:

| Field | Type | Required | Description |
|-------|------|----------|-------------|
| index | integer | yes | Unique index (0-based), used for edge references |
| node_type | string | yes | One of: start, custom, system_stt, system_tts, system_product, system_media, system_company, system_formatter |
| name | string | yes | Display name on the canvas |
| position_x | integer | yes | Canvas X coordinate |
| position_y | integer | yes | Canvas Y coordinate |
| is_active | boolean | yes | Whether this node is active |
| conversation_goal | string | no | System prompt for this node (custom nodes only) |
| config | object | no | Node-specific configuration (see below) |
| llm_provider_override | string | no | Override LLM provider: openai, anthropic, gemini, groq |
| llm_model_override | string | no | Override model name |
| temperature_override | number | no | Override temperature (0.0-2.0) |

Node types and their purpose:
- start — entry point, exactly one per workflow, no conversation_goal
- custom — LLM-powered node with its own prompt, tools, and knowledge base
- system_product — searches products, checks availability, shows details
- system_media — retrieves photos, videos, documents
- system_company — company info and support questions
- system_formatter — combines outputs from parallel nodes into final response
- system_stt — speech-to-text (voice input), usually inactive by default
- system_tts — text-to-speech (voice output), usually inactive by default

Config for system_stt:
{
  "provider": "openai",
  "language": "en",
  "greeting_text": "Hi! How can I help you?",
  "greeting_audio_url": null,
  "farewell_text": "Thanks! Goodbye!",
  "farewell_audio_url": null
}

Config for system_tts:
{
  "provider": "openai",
  "voice": "nova",
  "model": "tts-1",
  "speed": 1.0
}

Config for custom nodes (optional):
{
  "save_to_memory": ["field_key1", "field_key2"],
  "max_tool_rounds": 3,
  "tool_timeout_seconds": 30
}

### edges_data (array of objects)

Each edge object connects two nodes:

| Field | Type | Required | Description |
|-------|------|----------|-------------|
| source_index | integer | yes | Index of the source node |
| target_index | integer | yes | Index of the target node |
| condition_type | string | yes | One of: always, keyword, intent, state, fallback |
| condition_value | object | no | Condition parameters (null for always/fallback) |
| priority | integer | no | Evaluation priority (default: 90 for always) |

Condition types and priorities:
- keyword (priority: 100) — matches words in the message
  condition_value: { "keywords": ["word1", "word2", ...] }
- state (priority: 95) — checks memory field values
  condition_value: { "conditions": [{"field": "name", "operator": "filled|empty|=|!=|contains|>|<", "value": ""}] }
- always (priority: 90) — unconditional, enables parallel fan-out
  condition_value: null
- intent (priority: 50) — LLM classifies the message intent
  condition_value: { "intents": ["intent_name"] }
- fallback (priority: 10) — routes only when nothing else matches
  condition_value: null

### tools_data (object, keys are node indexes as strings)

Maps node index to an array of tool names:

{
  "2": ["search_documents", "get_company_info"],
  "3": ["get_products", "get_product_details"]
}

Available built-in tools (9):
- get_products — search products by name/description
- get_product_details — full details for one product
- check_availability — check if product is in stock
- search_by_parameters — filter products by attributes
- get_company_info — company name, description, contacts
- search_documents — semantic RAG search in knowledge base
- get_photos — retrieve photos
- get_videos — retrieve videos
- get_documents — retrieve PDF/Word/Excel files

### memory_fields_data (optional array)

Define structured fields the agent should collect:

[
  {"key": "client_name", "label": "Client Name", "type": "text"},
  {"key": "client_phone", "label": "Phone", "type": "phone"},
  {"key": "topic", "label": "Topic", "type": "select", "options": ["sales", "support"]}
]

Field types: text, phone, email, number, select (with options array).

## Workflow Patterns

### Pattern 1: Simple (single expert)
Start → Custom Node → Formatter
Best for: FAQ bots, simple support, single-topic agents.

### Pattern 2: Parallel experts (always routing)
Start → Expert A → Formatter
      → Expert B → Formatter
      → Expert C → Formatter
Best for: agents that need to search products + documents + company info simultaneously.

### Pattern 3: Smart router (intent/keyword routing)
Start → (intent: sales) → Sales Expert → Formatter
      → (intent: support) → Support Expert → Formatter
      → (fallback) → General Expert → Formatter
Best for: multi-topic agents where different questions need different expertise.

### Pattern 4: Lead collection (state routing)
Start → (name empty) → Collect Name → Formatter
      → (name filled, phone empty) → Collect Phone → Formatter
      → (all filled) → Final Response → Formatter
Best for: lead qualification, appointment booking, form-filling flows.

### Pattern 5: Voice agent
STT → Start → Expert → Formatter → TTS
Same as any pattern above, but with STT/TTS nodes active.

## Layout Guidelines

- Start node at position (0, 0)
- STT node to the left: (-200, 0)
- Expert nodes to the right: (200, -100), (200, 0), (200, 100)
- Formatter further right: (400, 0)
- TTS node furthest right: (600, 0)
- Vertical spacing between parallel nodes: 100-200px

## Rules

1. Every workflow MUST have exactly one "start" node
2. Every workflow MUST have exactly one "system_formatter" node
3. STT and TTS nodes should be included but set to is_active: false
   unless voice is specifically requested
4. Custom nodes should have clear, focused conversation_goal text
5. Each custom node should have at least search_documents tool
6. Use intent routing instead of keyword for multilingual agents
7. The fallback edge ensures no message goes unanswered
8. Node indexes must be sequential starting from 0
9. All edge source_index and target_index must reference valid node indexes
10. conversation_goal should be written in the language the agent will use

## Output

Return ONLY the JSON object — no markdown, no explanation, no
code fences. The JSON must be valid and parseable.

## Input

My business: [DESCRIBE YOUR BUSINESS]
Agent role: [e.g., sales consultant, support agent, lead collector]
Languages: [e.g., English, Ukrainian, multilingual]
Voice enabled: [yes/no]
Key topics/departments: [e.g., products, billing, technical support]
Memory fields to collect: [e.g., name, phone, email, or none]
Special requirements: [any additional requirements]

Después de generar el JSON, puede revisar y ajustar los nombres de nodos, conversation goals o asignaciones de herramientas antes de importar. El formato de plantilla de workflow será importable directamente en una futura actualización de Revol.