Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68773
Volume:
10 |
11 |
Nov 2026
Pages:
1-6
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.

Information Technology
SVPM COE Malegaon (bk), Baramati

Information Technology
SVPM COE Malegaon (bk), Baramati

Information Technology
SVPM COE Malegaon (bk), Baramati

Information Technology
SVPM COE Malegaon (bk), Baramati

Information Technology
SVPM COE Malegaon (bk), Baramati

Information Technology
SVPM COE Malegaon (bk), Baramati
SkillPath AI is an Agentic AI-based student career readiness platform proposed to bridge the gap between academic learning and industry requirements. The platform aims to provide personalized career guidance by analyzing students' skills, career objectives, and learning requirements to identify skill gaps and recommend relevant technical skills. The proposed system follows a modular architecture consisting of a React-based frontend, Java Spring Boot backend, and Python FastAPI-based AI service. PostgreSQL with the pgvector extension is used for structured data management and embedding-based semantic similarity search. The currently implemented Skill Agent focuses on retrieving students' target career roles and generating relevant skill recommendations through semantic search and AI-service integration. It uses sentence-transformer-based embeddings to represent skills in a vector space and identify relevant skills based on career requirements. A locally deployed Large Language Model (LLM) through Ollama provides the foundation for AI-assisted interactions. The overall platform is designed to extend this functionality through additional intelligent agents for adaptive assessment, personalized learning, and career recommendations. This modular approach aims to establish an integrated and student-centric framework for improving career readiness through intelligent skill analysis and personalized recommendations.
KEYWORDS
This research presents SkillPath AI, an Agentic AI-based student career readiness platform designed to bridge the gap between academic learning and industry skill requirements. The reviewed studies highlight the potential of intelligent agents, semantic search, personalized recommendations, and knowledge-based techniques in supporting student skill development and career preparation. The current implementation focuses on the Skill Agent, which retrieves students' selected career roles and generates relevant technical skill recommendations using sentence-transformer-based embeddings and semantic similarity search. The system utilizes a React-based frontend, Java Spring Boot backend, and Python FastAPI AI service, with PostgreSQL and pgvector supporting structured data management and vector-based retrieval. This implementation establishes the foundation for the broader SkillPath AI architecture. The proposed platform aims to extend these capabilities through additional intelligent agents for adaptive assessment, personalized learning, and career guidance. Its objective is to help students identify relevant skill requirements and progressively prepare for their selected career roles. Although the current implementation establishes the foundation for semantic skill recommendations, further development and experimental evaluation are required to assess recommendation relevance, system performance, reliability, and practical effectiveness. Overall, SkillPath AI represents an approach towards connecting student competencies with industry-oriented skill requirements through intelligent and personalized career guidance.
[1] V. K. Vaisakh, A. Ravi, A. K. O. Aakash, A. Sai, and J. Bhaskar, “SkillCrest: A Skill Assessment System Using Deep Knowledge Tracing and User Feedback Sentiment Analysis,” in Proc. 2nd Global Conf. Advancement in Technology (GCAT), 2021, doi: 10.1109/GCAT52182.2021.9587697. [2] S. Seetaworn, P. Phenhiran, P. Ngokpol, M. Innoy, S. Ingboon, T. Utasri, and A. Takhom, “Leveraging Knowledge Graphs for Personalized Internship Recommendations: A Case Study on Software Engineering Courses,” in Proc. IEEE International Conference on Cybernetics and Innovations (ICCI), 2025, doi: 10.1109/ICCI64209.2025.10987407. [3] N. Bairi and G. N. R. Prasad, “Dynamic and Personalized Career Path Prediction Using Machine Learning and Job Market Insights,” in Proc. International Conference on Intelligent and Sustainable AI Systems (ICOSAAS), 2026, doi: 10.1109/ICOSAAS68663.2026.11649326. [4] S. K. Aithal, S. Santhosh, A. Shenoy, and S. Sandeep Kumar, “Machine Learning Based Ideal Job Role Fit and Career Recommendation System,” in Proc. 7th International Conference on Computing Methodologies and Communication (ICCMC), 2023, doi: 10.1109/ICCMC56507.2023.10084315. [5] H. Ngo, K. Vo, and T. Nguyen, “Personalized Learning Path Recommendations: Fusing Knowledge Graph Embedding, Sequence Mining, and Collaborative Filtering,” in Proc. IEEE International Conference on Big Data (BigData), 2024, doi: 10.1109/BigData62323.2024.10825001. [6] D. Lee and H. Kim, “A Survey on LLM Agents: Architecture, Applications, and Challenges,” in Proc. 40th International Conference on Information Networking (ICOIN), 2026, doi: 10.1109/ICOIN68469.2026.11480623. [7] V. Ramazanova, M. Sambetbayeva, S. Serikbayeva, Z. Sadirmekova, and A. Yerimbetova, “Development of a Knowledge Graph-Based Model for Recommending MOOCs to Supplement University Educational Programs in Line With Employer Requirements,” IEEE Access, vol. 12, pp. 193313–193331, 2024, doi: 10.1109/ACCESS.2024.3519263. [8] X. Wei, W. Han, S. Sun, J. Shan, and L. Zhou, “Educational Psychology-Empowered Personalized Learning Path Generation Strategy,” IEEE Transactions on Learning Technologies, vol. 18, 2025, doi: 10.1109/TLT.2025.3590602. [9] C. N. Hang, C. W. Tan, and P. D. Yu, “MCQGen: A Large Language Model-Driven MCQ Generator for Personalized Learning,” IEEE Access, 2024, doi: 10.1109/ACCESS.2024.3420709. [10] C. Upadhyay, H. Abu-Rasheed, C. Weber, and M. Fathi, “Explainable Job-Posting Recommendations Using Knowledge Graphs and Named Entity Recognition,” in Proc. IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2021, doi: 10.1109/SMC52423.2021.9658757.
Publication Date
11/5/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
5
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...