An LLM-Powered Agent for Real-Time Analysis of the Vietnamese IT Job Market

TL;DR

This work tackles the lack of trustworthy, real-time career guidance in Vietnam's rapidly expanding IT sector by introducing the AI Job Market Consultant, a ReAct-based, tool-augmented agent that analyzes a real-time, LLM-parsed dataset of 3,745 job postings. It combines an end-to-end data pipeline (crawling with Playwright, LLM-based structuring, and semantic skill labeling) with a programmable agent capable of SQL querying, visualization, and personalized advice via vector search. Case studies demonstrate factual data retrieval with visualizations and nuanced, personalized career recommendations grounded in current market data, outperforming static, non-agentic chatbots in verifiability and depth. The approach meaningfully democratizes access to timely labor market insights and offers a scalable framework for real-time analysis in other domains as data sources grow. The practical impact lies in providing students, graduates, and career advisors with actionable, data-driven guidance anchored in live market signals.

Abstract

Individuals entering Vietnam's dynamic Information Technology (IT) job market face a critical gap in reliable career guidance. Existing market reports are often outdated, while the manual analysis of thousands of job postings is impractical for most. To address this challenge, we present the AI Job Market Consultant, a novel conversational agent that delivers deep, data-driven insights directly from the labor market in real-time. The foundation of our system is a custom-built dataset created via an automated pipeline that crawls job portals using Playwright and leverages the Large Language Model (LLM) to intelligently structure unstructured posting data. The core of our system is a tool-augmented AI agent, based on the ReAct agentic framework, which enables the ability of autonomously reasoning, planning, and executing actions through a specialized toolbox for SQL queries, semantic search, and data visualization. Our prototype successfully collected and analyzed 3,745 job postings, demonstrating its ability to answer complex, multi-step queries, generate on-demand visualizations, and provide personalized career advice grounded in real-world data. This work introduces a new paradigm for labor market analysis, showcasing how specialized agentic AI systems can democratize access to timely, trustworthy career intelligence for the next generation of professionals.

Figures (7)

• Figure 1: Overall System Architecture. The diagram shows the offline data pipeline (left) that populates the database and the online agent interaction flow (right) that leverages this data to answer user queries.
• Figure 2: Use case diagram of the AI Job Market Consultant
• Figure 3: The ETL Pipeline for retrieving job postings. Raw data from the crawler is structured by an LLM and semantically enriched before being loaded into the database.
• Figure 4: The ReAct Framework for Agent Operation. The agent iteratively reasons, acts by calling a tool, and observes the result to solve user queries.
• Figure 5: Personalized Career Consultation based on User Profile. The agent provides a detailed, multi-part response tailored to the qualitative input of the user, combining career suggestions with market data.