Atención al cliente restaurante
Guía al cliente de un restaurante durante las tres etapas clave: entrantes, plato principal y postre. El agente accede al menú desde Google Drive y es capaz de adaptarse a las peticiones del usuario.
graph TD
%%{init: {'theme': 'mc','layout': 'elk'}}%%
GoogleGenerativeAIModel-jufh8[Gemini]
style GoogleGenerativeAIModel-jufh8 stroke:#a170ff
GDriveFilesComponent-g8fwu[<div><img src="/_astro/google_drive.wKmDsV2c.svg" style="height: 20px !important;width: 20px !important"/></div>Google Drive File Manager]
style GDriveFilesComponent-g8fwu stroke:#a170ff
ChatInput-p6m3d[<div><img src="/_astro/messages-square.BaSDmT6g.svg" style="height: 20px !important;width: 20px !important"/></div>Chat Input]
style ChatInput-p6m3d stroke:#a170ff
ChatOutput-yxmzc[<div><img src="/_astro/messages-square.BaSDmT6g.svg" style="height: 20px !important;width: 20px !important"/></div>Chat Output]
style ChatOutput-yxmzc stroke:#a170ff
TelegramMessage-17wff[Telegram Message]
style TelegramMessage-17wff stroke:#a170ff
AdvancedAgent-38qxe[Agent2]
style AdvancedAgent-38qxe stroke:#a170ff
ChatInput-p6m3d -.- AdvancedAgent-38qxe
linkStyle 0 stroke:#a170ff
AdvancedAgent-38qxe -.- ChatOutput-yxmzc
linkStyle 1 stroke:#a170ff
GoogleGenerativeAIModel-jufh8 -.- AdvancedAgent-38qxe
linkStyle 2 stroke:#a170ff
GDriveFilesComponent-g8fwu -.- AdvancedAgent-38qxe
linkStyle 3 stroke:#a170ff
TelegramMessage-17wff -.- AdvancedAgent-38qxe
linkStyle 4 stroke:#a170ff
Atención al cliente restaurante
🧩 Overview
This workflow implements a conversational AI agent designed to act as a virtual waiter for a restaurant. It automates the customer service process by guiding patrons through the three main stages of their dining experience: appetizers, main courses, and desserts. The agent dynamically interacts with the customer, provides accurate menu information by accessing a document from Google Drive, confirms each order, and automatically notifies the kitchen staff via Telegram once an order is finalized.
⚙️ Main Features
- Provides a structured, multi-stage conversational flow for taking restaurant orders.
- Integrates with Google Drive to fetch and reference the restaurant's current menu.
- Confirms each customer order before proceeding to the next stage.
- Sends automated order notifications to restaurant staff via Telegram.
- Adapts to specific customer requests and changes during the ordering process.
🔄 Workflow Steps
| Component Name | Role in the Workflow | Key Inputs | Key Outputs |
|---|---|---|---|
| Chat Input | Captures the initial user query or message to start the interaction. | User message text | User message for the agent |
| Agent | The core conversational agent that manages the dialogue, follows the ordering protocol, and decides when to use its available tools. | User message, system prompt, language model, available tools | Agent's conversational response |
| Google Drive File Manager | Serves as a tool for the agent to retrieve the restaurant's menu document from Google Drive. | File selection command | Retrieved menu file content |
| Telegram Message | Serves as a tool for the agent to send order confirmation notifications to a specified Telegram chat. | Order details and chat ID | Telegram notification sent |
| Gemini Model | Provides the underlying language model powering the agent's reasoning and text generation capabilities. | Model configuration | Configured language model |
| Chat Output | Displays the agent's final response back to the user in the chat interface. | Agent's response message | Formatted chat message |
🧠 Notes
- The workflow requires valid API credentials for Google Generative AI (Gemini) and Telegram to function.
- The agent's behavior is strictly defined by a detailed system prompt that outlines the ordering stages, confirmation steps, and tool usage rules.
- The Google Drive File Manager component must be configured to point to the correct menu file.
- The Telegram Message component requires a valid target chat ID to send notifications successfully.
- The workflow is designed for a linear, guided ordering experience and may require adjustments for more complex or open-ended customer service scenarios.