Build AI Business Solutions with Workflow Automation | NappAI - Template: Atencion al Cliente Ecommerce

graph TD %%{init: {'theme': 'mc','layout': 'elk'}}%% ChatInput-larrt[<div><img src="/_astro/messages-square.BaSDmT6g.svg" style="height: 20px !important;width: 20px !important"/></div>Chat Input] style ChatInput-larrt stroke:#a170ff GoogleGenerativeAIModel-hrflu[Gemini] style GoogleGenerativeAIModel-hrflu stroke:#a170ff GoogleGenerativeAIEmbeddings-fnjt0[Google Generative AI Embeddings] style GoogleGenerativeAIEmbeddings-fnjt0 stroke:#a170ff APIRequest-78xr1[API Request] style APIRequest-78xr1 stroke:#a170ff TelegramMessage-zvrp9[Telegram Message] style TelegramMessage-zvrp9 stroke:#a170ff ChatOutput-16z2g[<div><img src="/_astro/messages-square.BaSDmT6g.svg" style="height: 20px !important;width: 20px !important"/></div>Chat Output] style ChatOutput-16z2g stroke:#a170ff ChatOutput-0vfib[<div><img src="/_astro/messages-square.BaSDmT6g.svg" style="height: 20px !important;width: 20px !important"/></div>Chat Output2] style ChatOutput-0vfib stroke:#a170ff ChatOutput-7h910[<div><img src="/_astro/messages-square.BaSDmT6g.svg" style="height: 20px !important;width: 20px !important"/></div>Chat Output3] style ChatOutput-7h910 stroke:#a170ff GoogleGenerativeAIEmbeddings-mn2ew[Google Generative AI Embeddings2] style GoogleGenerativeAIEmbeddings-mn2ew stroke:#a170ff SplitText-xm92m[<div><img src="/_astro/scissors-line-dashed.CajsPhTx.svg" style="height: 20px !important;width: 20px !important"/></div>Split Text] style SplitText-xm92m stroke:#a170ff GDriveFilesComponent-q2n9y[<div><img src="/_astro/google_drive.wKmDsV2c.svg" style="height: 20px !important;width: 20px !important"/></div>Google Drive File Manager] style GDriveFilesComponent-q2n9y stroke:#a170ff ParseData-dpd2k[<div><img src="/_astro/braces.Djq0PW4_.svg" style="height: 20px !important;width: 20px !important"/></div>Parse Data] style ParseData-dpd2k stroke:#a170ff AdvancedAgent-zbpzj[Agent4] style AdvancedAgent-zbpzj stroke:#a170ff AdvancedAgent-aazz1[Agent] style AdvancedAgent-aazz1 stroke:#a170ff AdvancedAgent-hs2r4[Agent5] style AdvancedAgent-hs2r4 stroke:#a170ff ParseData-2g4fn[<div><img src="/_astro/braces.Djq0PW4_.svg" style="height: 20px !important;width: 20px !important"/></div>Parse Data2] style ParseData-2g4fn stroke:#a170ff ParseData-mrvuk[<div><img src="/_astro/braces.Djq0PW4_.svg" style="height: 20px !important;width: 20px !important"/></div>Parse Data3] style ParseData-mrvuk stroke:#a170ff ParseData-z8755[<div><img src="/_astro/braces.Djq0PW4_.svg" style="height: 20px !important;width: 20px !important"/></div>Parse Data4] style ParseData-z8755 stroke:#a170ff DeepseekModel-7c7w4[Deepseek2] style DeepseekModel-7c7w4 stroke:#a170ff DeepseekModel-juyng[Deepseek3] style DeepseekModel-juyng stroke:#a170ff DeepseekModel-ova3h[Deepseek4] style DeepseekModel-ova3h stroke:#a170ff SmartRouter-kldld[Agent Router] style SmartRouter-kldld stroke:#a170ff RetrieverTool-65vrx[<div><img src="/_astro/langchain-icon.BXtvU_nA.svg" style="height: 20px !important;width: 20px !important"/></div>RetrieverTool] style RetrieverTool-65vrx stroke:#a170ff AstraDB-bdkzn[Astra DB] style AstraDB-bdkzn stroke:#a170ff AstraDB-xlv27[Astra DB2] style AstraDB-xlv27 stroke:#a170ff ParseData-dpd2k -.- SplitText-xm92m linkStyle 0 stroke:#a170ff GDriveFilesComponent-q2n9y -.- ParseData-dpd2k linkStyle 1 stroke:#a170ff AdvancedAgent-zbpzj -.- ChatOutput-16z2g linkStyle 2 stroke:#a170ff AdvancedAgent-aazz1 -.- ChatOutput-7h910 linkStyle 3 stroke:#a170ff APIRequest-78xr1 -.- AdvancedAgent-aazz1 linkStyle 4 stroke:#a170ff AdvancedAgent-hs2r4 -.- ChatOutput-0vfib linkStyle 5 stroke:#a170ff TelegramMessage-zvrp9 -.- AdvancedAgent-hs2r4 linkStyle 6 stroke:#a170ff ParseData-2g4fn -.- AdvancedAgent-zbpzj linkStyle 7 stroke:#a170ff ParseData-mrvuk -.- AdvancedAgent-aazz1 linkStyle 8 stroke:#a170ff ParseData-z8755 -.- AdvancedAgent-hs2r4 linkStyle 9 stroke:#a170ff DeepseekModel-7c7w4 -.- AdvancedAgent-zbpzj linkStyle 10 stroke:#a170ff DeepseekModel-juyng -.- AdvancedAgent-aazz1 linkStyle 11 stroke:#a170ff DeepseekModel-ova3h -.- AdvancedAgent-hs2r4 linkStyle 12 stroke:#a170ff ChatInput-larrt -.- SmartRouter-kldld linkStyle 13 stroke:#a170ff GoogleGenerativeAIModel-hrflu -.- SmartRouter-kldld linkStyle 14 stroke:#a170ff SmartRouter-kldld -.- ParseData-2g4fn linkStyle 15 stroke:#a170ff SmartRouter-kldld -.- ParseData-mrvuk linkStyle 16 stroke:#a170ff SmartRouter-kldld -.- ParseData-z8755 linkStyle 17 stroke:#a170ff RetrieverTool-65vrx -.- AdvancedAgent-zbpzj linkStyle 18 stroke:#a170ff SplitText-xm92m -.- AstraDB-bdkzn linkStyle 19 stroke:#a170ff GoogleGenerativeAIEmbeddings-mn2ew -.- AstraDB-bdkzn linkStyle 20 stroke:#a170ff AstraDB-xlv27 -.- RetrieverTool-65vrx linkStyle 21 stroke:#a170ff GoogleGenerativeAIEmbeddings-fnjt0 -.- AstraDB-xlv27 linkStyle 22 stroke:#a170ff

Atencion al Cliente Ecommerce

🧩 Overview

This workflow automates customer service for an e-commerce platform by intelligently routing incoming queries to the most appropriate resolution path. It uses a Large Language Model (LLM) to classify the customer's intent and then directs the query to one of three specialized AI agents, each designed to handle a specific type of request. This system streamlines support by providing automated, context-aware responses for general information, order status inquiries, and escalations requiring human intervention.

⚙️ Main Features

Automatically classifies customer messages into three distinct support levels based on intent.
Routes queries to specialized agents: one for general company information, one for database-driven order/product inquiries, and one for handling escalations.
Integrates a Retrieval-Augmented Generation (RAG) system to provide accurate answers based on internal company documentation.
Connects to external systems like APIs for real-time data and Telegram for human agent notifications.
Includes a separate, configurable pipeline for building and populating a vector database from company documents.

🔄 Workflow Steps

Component Name	Role in the Workflow	Key Inputs	Key Outputs
Chat Input	Receives the initial customer query from the user interface.	User Message	Customer Message
Agent Router	Analyzes the customer's message to classify its intent into one of three categories (nivel1, nivel2, nivel3).	Customer Message, Language Model	Classification Result
Parse Data	Converts the structured classification result from the router into a plain text message for the next agent.	Classification Data	Formatted Message
Advanced Agent (Level 1)	A RAG-powered agent that answers general questions about the company using information retrieved from a vector database.	Formatted Message, Language Model, Retrieval Tool	AI Response
Advanced Agent (Level 2)	An agent equipped with an API tool to query business systems for specific data like order status or product inventory.	Formatted Message, Language Model, API Tool	AI Response
Advanced Agent (Level 3)	An agent designed to manage escalations, using a notification tool to alert a human employee via Telegram.	Formatted Message, Language Model, Notification Tool	AI Response
Chat Output	Displays the final AI-generated response back to the customer in the chat interface.	AI Response	Displayed Message

🧠 Notes

The workflow relies on pre-configured credentials for external services like Google Generative AI, Deepseek, AstraDB, and Telegram.
The Level 1 agent's knowledge is limited to the information contained within the pre-built vector database; it cannot access external web sources.
The system prompt for the Level 1 agent instructs it to strictly use its retrieval tool and not to invent information.
The vector database creation pipeline (involving Google Drive, text parsing, chunking, and embedding) is depicted as a separate, preparatory process.
The effectiveness of the routing depends on the accuracy of the LLM-based classifier and the clarity of the defined intention categories.