ChatSeven: Implementation and Result Analysis of an Agentic AI-Based Multi-Agent Platform for Multi-Channel Customer Conversation Management and Campaign Automation
Jul 2026· International Journal of Scientific Research in Science Engineering and Technology· 0 citations
TL;DR
ChatSeven is an agentic AI-based multi-agent platform for customer conversation management and campaign automation that integrates retrieval-augmented generation, Lang Graph ReAct agents, visual workflow automation, a unified inbox, and multi-channel campaign delivery.
Abstract
Customer conversation platforms increasingly require artificial intelligence, multi-channel messaging, workflow automation, and campaign delivery in a single operational environment. This paper presents the implementation and result analysis of ChatSeven, an agentic AI-based multi-agent platform for customer conversation management and campaign automation. ChatSeven is implemented using a React frontend, an Express/TypeScript backend, Python FastAPI services for Chat AI and vector search, PostgreSQL regional databases, Redis/Bull background queues, and Socket.IO real-time messaging. The system integrates retrieval-augmented generation (RAG), Lang Graph ReAct agents, tool calling through MCP/Zapier-style integrations, visual workflow automation, a unified inbox, and multi-channel campaign delivery.
Task management is one of the common challenges faced by students when dealing with demanding academic activities and multiple overlapping deadlines. Existing task management applications are generally passive and are not yet capable of providing proactive assistance in determining work priorities. This study aims to develop an AI Task Agent system based on a Telegram chatbot, integrated with n8n as a workflow automation platform and Supabase as the database. The developed system allows users to record tasks with attributes such as task type, description, scheduled time, deadline, urgency level, and the lecturer’s level of strictness. In addition, the system can respond interactively to user commands, display task lists, provide priority recommendations, and send automated reminders. The research employed a system development method consisting of problem identification, requirements analysis, system design, implementation, and testing. The results indicate that the system can improve the effectiveness of students’ task management through more practical, responsive, and structured interactions.
Huzain Azis, N. Widiyanti· Indonesian Journal of Data a...· 0 citations
A reverse engineering technique is presented for extracting a behavioural model of a deployed chatbot through the automated exploration of its functionality via Large Language Models through the automated exploration of its functionality via Large Language Models.
Iván Sotillo del Horno, Alejandro del Pozzo, Esther Guerra et al.· SN Computer Science· 0 citations
Organizations today rely on multiple diversified digital platforms and tools for task planning, daily schedule aggregation, human resource support, communication, document handling, etc. These tools often operate independently, expecting employees to switch between multiple apps, leading to excessive cognitive load, reduced productivity, and unnecessary chaos. This paper introduces Collabrium, an AI-enabled enterprise collaboration platform that unifies HR assistance, daily agenda aggregation and management, In-chat reminder, Business Language translator, Contextual Tagging, Multi-Message Abstraction, and Document-based question answering features. These features make Collabrium a unique and unified platform for improving productivity and workflow management. The system incorporates semantic text understanding, retrieval-augmented generation, and vector-based similarity search to convert conversations into vectors and fetch contextually similar vectors within a vector database. The proposed approach improves functional effectiveness by incorporating artificial intelligence directly into communication workflows and tasks, for better workflow operation.
S. M, H. M· International Conference Com...· 0 citations
University regulations and announcements at Bursa Technical University (BTU) are dispersed across PDF files, web pages, and notice boards, causing information retrieval inefficiencies for students and administrative staff. This study presents the development and quantitative evaluation of BTU-Chatbot, an Agentic Retrieval-Augmented Generation (RAG) powered conversational assistant that consolidates fragmented institutional information into a single citation-aware dialogue interface. Ninety-seven PDF documents were processed using PyPDFLoader and regular-expression-based preprocessing, then embedded into 1536-dimensional vectors using OpenAI’s text-embedding-ada-v2 model and stored in a 29 MB ChromaDB collection. The vector-based retrieval layer selects the three most relevant passages per query using cosine similarity search. The upper layer implements a LangChain-orchestrated multi-agent ReAct loop, in which the retrieve tool accesses the vector database while the Google_search_univ tool performs domain-restricted searches limited to the “*.btu.edu.tr” domain. GPT-4o-mini, with a 128k context window, serves as the generative backbone. System reliability was measured using the RAGAS metric suite. The best performing run achieved Context Recall = 0.97, Context Precision = 0.99, and F1- RP (the F1 score of Context Recall and Precision) = 0.954, demonstrating nearperfect retrieval accuracy. The average cost per query was 6.6×10⁻⁵ USD, with 7.6 s of latency for typical 124-token exchanges. BTU-Chatbot demonstrates that an Agentic RAG pipeline can deliver source-grounded, citation-attributed answers to university-specific queries at low operating cost, although further improvements in generation faithfulness are needed before full deployment.
T. Bilgin, Yusuf Gül, Yücel Akgün· Serbian Journal of Electrica...· 0 citations
This study introduces WA Daksha, an academic chatbot on WhatsApp, linked with Gemini AI, designed to facilitate intelligent academic service automation inside the Faculty of Engineering at Universitas Negeri Surabaya. The study concentrates on analysis and design at Technology Readiness Level 1-3, where system readiness is evaluated through structural requirement validation and expert-based architectural mapping. This process generates a verified system architecture, knowledge base structure, conversation flow, and use case model. The suggested system employs a hybrid conversational methodology that integrates rule-based routing, knowledge-based retrieval using Retrieval-Augmented Generation, and generative AI answers. The design comprises client, platform integration, application, data, and infrastructure layers to guarantee modularity and scalability. The chatbot offers three primary services: academic information, FAQ support, and AI-generated dynamic inquiries via WhatsApp chat. The knowledge base amalgamates institutional academic data, administrative protocols, and contextual AI processing to enhance response precision and dependability. The architectural evaluation demonstrates that WA Daksha provides an accessible and scalable framework for automating realtime academic services, facilitating multi-user interaction among students, lecturers, and the public. This research advances the creation of AI-driven academic service assistants in higher education and promotes SDG 4 by enhancing access to inclusive and high-quality education via intelligent digital academic services.
Rizky Basatha, B. Putra, S. A. Alamsyah et al.· E3S Web of Conferences· 0 citations
The rapid evolution of Large Language Models (LLMs) has opened new possibilities for building intelligent, human-like conversational systems capable of understanding and responding to open-domain queries in real time. Traditional chatbot architectures, whether rule-based or narrow-domain trained, are constrained by limited contextual understanding, poor conversational continuity, and an inability to generate fluent, human-like responses across varied topics. This paper presents the design, development, and evaluation of an AI-Powered Conversational Web Assistant that integrates Google's Gemini 1.5 Flash large language model with a lightweight Python Flask web application to deliver real-time, context-aware conversational support. The system accepts free-form natural-language input through a responsive browser-based chat interface, forwards the query to the Gemini API through secure RESTful calls, and renders the generated response asynchronously without page reload. A Flask backend manages session handling, prompt construction, and API communication, while a SQLite-backed logging layer stores conversation history for auditing and future personalization. The architecture is deliberately modular, separating the presentation layer, the dialogue-management logic, and the external LLM service, which allows any of these layers to be replaced or extended independently. Experimental use of the deployed prototype across a range of factual, technical, and conversational queries demonstrated that the assistant produces fluent, contextually relevant, and largely accurate responses while maintaining low perceived latency. The study also documents the practical challenges encountered during development, including prompt-engineering trade-offs, API rate limits, session-memory handling, and safe-response filtering, together with the mitigation strategies adopted. The resulting prototype confirms that a cloud-hosted multimodal LLM, when combined with a minimal and well-structured web stack, can serve as a practical foundation for next-generation digital assistants suitable for customer support, education, and personal productivity applications, with a clear pathway toward voice interaction, sentiment-aware responses, multilingual support, and persistent contextual memory in future iterations.
Index Terms: - Artificial Intelligence • Natural Language Processing • Large Language Models • Google Gemini API • Conversational AI • Chatbot • Flask Framework • Prompt Engineering • Intent Recognition • Dialogue Management • Natural Language Generation • SQLite • Human-Computer Interaction • Web-Based Assistant.
G. Vamsi, Vinay Kumar Male· International Scientific Jou...· 0 citations