EUVIMEDEUVIMED entdecken
Crossref

AI-AGENT FOR WORKING WITH TOURISM BUSINESS

Iryna Yurchak, Olha Kychuk, Nataliуa Huzynets, Andriy Khich

Computer Design Systems. Theory and Practice · 2026 · 8 (1) · 11-28

DOI: 10.23939/cds2026.01.011 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Design Systems. Theory and Practice, online erschienen am 30.04.2026. Verfasst von Iryna Yurchak und 3 weiteren Autor:innen. Die Arbeit nennt 11 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper is devoted to the development of an intelligent agent for automating user interaction with the web resources of tourism companies. An approach is proposed that combines prompt engineering techniques, contextual fine-tuning, and integration with web data through the n8n platform in order to obtain reliable information in real time. The core idea is to use the language model not only as a text generator, but also as a universal interpreter of HTML content and a semantic aggregator of data from the web resources of a tourism company. A generalized scheme of a combined model training approach is formed, which ensures increased relevance of the agent’s responses in the domain of tourism business. The agent architecture is based on a distributed serverless model, where n8n acts as the central orchestrator of interaction logic between the user, the language model, and external data sources. The AI agent dynamically determines the required tools, activates appropriate HTTP requests, integrates the retrieved HTML fragments into the query context, and generates structured, informative responses. This approach provides high factual accuracy of results and distinguishes the proposed system from universal chatbots that operate on generalized knowledge. An interactive web interface of the agent in the form of an HTML chat has been implemented, ensuring convenient user interaction with the system. Message handling mechanisms, typing indicators, response structuring, and connection error handling have been introduced. Special attention is paid to the behavioral aspects of the agent, including informativeness, stylistic consistency, and increased determinism of responses. A multi-level testing approach is proposed, which includes basic, functional, scenario-based, integration, and stress tests, as well as quantitative evaluation of response quality using the LLM-as-a-judge method. The testing results demonstrate a high level of correctness, relevance, and completeness of the agent’s responses, with an average integral score of about 90%, confirming the practical applicability of the developed system. The paper also addresses issues of security, stability, and the adaptability of the agent to other tourism resources without changes to the internal system logic. The modular architecture and independence of the language model from the structure of web resources enable rapid scaling of the solution and its application in various subject domains. The obtained results confirm the feasibility of using large language models in combination with orchestration platforms to create applied AI agents oriented toward real-world business scenarios.

Zitieren

APA

Yurchak, I., Kychuk, O., Huzynets, N., & Khich, A. (2026). AI-AGENT FOR WORKING WITH TOURISM BUSINESS. Computer Design Systems. Theory and Practice, 8(1), 11-28. https://doi.org/10.23939/cds2026.01.011

Vancouver

Yurchak I, Kychuk O, Huzynets N, Khich A. AI-AGENT FOR WORKING WITH TOURISM BUSINESS. Computer Design Systems. Theory and Practice. 2026;8(1):11-28. doi:10.23939/cds2026.01.011

BibTeX
@article{Yurchak2026,
  author = {Yurchak, Iryna and Kychuk, Olha and Huzynets, Nataliуa and Khich, Andriy},
  title = {AI-AGENT FOR WORKING WITH TOURISM BUSINESS},
  journal = {Computer Design Systems. Theory and Practice},
  year = {2026},
  volume = {8},
  number = {1},
  pages = {11--28},
  doi = {10.23939/cds2026.01.011}
}
Kostenlos starten →