Skip to content
Log in

Prompt engineering for library agents: development of an AI-based conversational reading recommendation system

Manuel Blázquez-Ochando J. Prieto-Gutiérrez María-Antonia Ovalle-Perandones
Jul 2026 · Library hi tech · 0 citations · 40 references

TL;DR

Pilot test results indicate adequate average response times, thematic and temporal diversity of authors and robust data structuring, confirming its viability as an applicable prototype and advancing the integration of generative AI into library services.

Abstract

This article presents the design, development and implementation of LaIABot, an artificial intelligence agent based on structured prompting for bibliographic recommendations in library environments. The system addresses common limitations such as staff shortages and time constraints, improving the accessibility and personalization of the service. A key innovation is the design of prompts that generate two simultaneous outputs: one for the user, with clear recommendations and another for the institution, in JSON format with metadata from the interaction, which allows for feedback and optimization of the system, integration into SIGB and enrichment of document analysis and management processes. A user-centered approach grounded in library science and ethical principles was adopted. LaIABot is developed with a configurable base prompt composed of five modules: user profile, suggestion filtering, collection typology, library services and feedback mechanisms. The technical architecture employs Flask, HTML5, JavaScript and CSS3, with SQLite for initial validation and the possibility of migration to more robust database managers. The pilot test, using 150 synthetic queries and a corpus of approximately 8,500 records, evaluated precision, diversity and JSON output consistency, achieving a 99.33% structural success rate and a 96.67% effective retrieval rate. Libraries are encouraged to explore the use of specialized conversational agents as a reader advisory tool, prioritizing structured prompting tailored to their specific context and collections. Documenting and auditing recommendations is essential to ensure authorial and thematic diversity, alongside implementing ethical oversight and data governance protocols. The dual output (user/JSON for institutional use) should be leveraged for usage analysis and catalog enrichment. The model's open-source and modular architecture supports its replication in public, academic and specialized libraries, enabling progressive AI integration aligned with institutional infrastructure and resources. LaIABot extends library service availability by operating 24/7, personalizes recommendations according to user profiles and integrates with existing systems, supporting reader advisory without requiring significant investment. Its JSON dual output enables integration with ILS platforms, statistical analysis and continuous service improvement. Pilot test results indicate adequate average response times, thematic and temporal diversity of authors and robust data structuring, confirming its viability as an applicable prototype. The system can enhance the visibility of historical collections and lesser-known authors, strengthening the library's social and educational role. This work introduces a pioneering approach to applying structured prompting with dual output for bibliographic recommendation. Unlike generic AI solutions, it offers a parameterizable architecture grounded in library science and ethical standards, capable of simultaneously producing valuable user-facing responses and structured institutional data. Its open and replicable nature, combined with technical validation in a controlled environment, lays the foundation for deployment in diverse contexts. This research advances the integration of generative AI into library services, combining technological innovation with the preservation of professional values such as neutrality, inclusion and equitable access to knowledge.

DOI Semantic Scholar
View source

Similar papers

Conference Jul 2026

A Collaborative Version-Controlled Framework for Evolutionary Optimization of AI Prompts

Prompt engineering is now a significant aspect of large language models (LLMs) to make them as effective in applications like conversational agents, educational assistants, automated code-generating systems, and content generation systems. Nonetheless, urgent design is frequently done in informal and solitary fashion devoid of systematic processes of collective enhancement, quality evaluation, or evolutionary monitoring. This paper suggests NeuroPrompt, an open-source prompt engineering system, which combines version tracking with evolution, directed acyclic graph (DAG) based lineage modeling, and community-based quality assessment. Users can create prompts, fork better prompts, and assess the performance of prompts with a multi-rater consensus system to assess the prompts based on clarity, creativity, and usefulness. The forking is directed by a utility-based decision model that ensures that unnecessary prompt duplication is avoided, and the effectiveness of optimization is enhanced. Experimental analysis reveals that collaborative prompt evolution is more effective in prompt quality and the overall accuracy of prompt generation in providing relevant and useful responses to tasks is 96.3% in comparison against baseline prompt design methods which has a score of about 88-91. There are also the results of the improved consensus reliability and lesser variance of ratings among the community evaluators. The suggested system will change timely engineering into a transparent and organized evolutionary process allowing sharing of knowledge systematically and optimizing prompt through collaborative optimization to large-scale AI initiatives.

D. Ragunath, Vaishak C J · 0 citations
Conference Open access 2026

Development of a Hybrid AI System Integrating Chatbot-Based Intelligent Assistants for Adaptive Interaction

The rapid expansion of digital transformation, growing environmental challenges and increasing global demands for sustainability, has created a need for systems that can balance technological performance with environmental responsibility and more intelligence. This research introduces a hybrid artificial intelligence (AI) that incorporates chatbot intelligent assistants based. The proposed system combines large language model (LLM) with rule-based filtering, allowing it to tailor its conversational responses according to user profiles, interaction histories, and relevant contextual information. The system is assessed based on three main criteria: response accuracy, the effectiveness of adaptive personalization, and energy consumption during each inference cycle. The experimental findings that the proposed research increases user satisfaction by 34,7% compared base chatbot and reduces computational consumption by 21,3% through dynamic model routing. The system supports Sustainable Development Goals 1, 4, and 17 by accessible digital services, inclusive education through intelligent tutoring, and collaboration among stakeholders to expand technology adoption in developing economies.

M. Akbar, Riza Akhsani Setyo Prayoga, Ersha Aisyah Elfaiz et al. · 0 citations
Conference Open access 2026

WA Daksha: Design of a WhatsApp-Based Academic Chatbot Integrated with Gemini AI for Intelligent Faculty Service Automation

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.

Rizky Basatha, B. Putra, S. A. Alamsyah et al. · 0 citations
Open access Aug 2026

Design and Implementation of an AI-Driven Chatbot for Federal Polytechnic Nekede Admissions and Information Services

The study concludes that AI-powered chatbot systems offer a substantive remedy to institutional communication inefficiencies and recommends full deployment alongside continuous model retraining using current institutional data.

Ulysses Chinenyeaka Ebizie · 0 citations
Conference Jul 2026

Smart Campus Assistant using RAG-based AI

This paper presents the design and implementation of intelligent chatbots using Retrieval-Augmented Generation architecture to derive accurate, context-based responses from domain-specific knowledge sources such as PDFs and CSV files. The proposed system integrates information retrieval mechanisms with large language models to overcome crucial limitations of traditional chatbots: hallucination, knowledge cut-off, and inability to access private organizational data. The proposed architecture uses a six-stage pipeline consisting of document ingestion, text splitting, and embedding generation with sentence transformers, semantic retrieval, and response generation via Large Language Models (LLMs). By preprocessing the PDF and CSV documents using a RecursiveCharacterTextSplitter and converting them into 384-dimensional semantic embeddings, the system works via a similarity-based retrieval of document chunks. For implementation, the LlamaIndex framework was used for data indexing and query orchestration, and HuggingFace Transformers for language modeling. Experimental validation conducted on the smart campus chatbot system demonstrated significant improvements in the accuracy, relevance and transparency of responses across education, student services, and administrative support domains compared with a standalone language model. Because of its modular design, it supports a wide range of domain-specific topics without the combinatorial costs of re-training. This is another important application for systems that require regular updates and accurate information. Overall, the proposed framework provides a simple and practical approach for easily implementing domain-aware chatbots.

Varsha Spoorthi Shree Narravula, V. K, Yashaswini B. Suresh et al. · 0 citations
Review Open access Jul 2026

An Intelligent AI Check-In Framework for Automating International Student Onboarding and Administrative Services

International and transfer student check-in processes involve complex, multi-step workflows that can be streamlined with artificial intelligence (AI). This paper presents the design and implementation of an AI-driven check-in agent that automates student onboarding tasks in a university setting. The agent integrates a graphical user interface (GUI) with AI capabilities to guide students through login/authentication, document uploads, advisor assignment based on region, course pre-selection, and real-time status tracking. We provide a comprehensive literature review of similar systems in the U.S. and globally, highlighting how institutions have leveraged chatbots and AI for admissions and orientation. The system’s architecture is described with a technical focus on its Python-based implementation (Tkinter for GUI, PIL for imaging), web integration through Jupyter Notebook compatibility, and open-source API utilization (including BeeWare for cross-platform deployment). We detail each system component and discuss security measures (compliance with FERPA, GDPR) to protect educational data privacy. Challenges such as user adoption, multilingual support, and integration with cloud services are examined, along with future enhancements like machine learning-driven personalization. The paper concludes with expected benefits in institutional efficiency and student satisfaction, positioning the AI check-in agent as a valuable contribution to smart campus initiatives.

Sahar Bukhari · 0 citations