Margdarshak: AI-powered virtual career mentor

  • Unique Paper ID: 186627
  • PageNo: 2166-2175
  • Abstract:
  • Margdarshak is a Software-as-a-Service (SaaS) virtual mentor that offers ongoing, individualized career support with the goal of enhancing students' employability and career readiness. The platform includes a job-description-aware cover letter generator, an ATS-optimized and fully customizable resume generator, an AI-powered mock interview system with performance-over-time tracking and targeted improvement recommendations, and automated weekly industry insights (trending skills and salary benchmarks). Margdarshak's architecture combines large-language models, structured evaluation pipelines, and contemporary web frameworks: (1) a data ingestion layer that compiles labor-market indicators and updates insights on a weekly basis; (2) interactive mock interview modules that score responses, record performance metrics over time, and generate prescriptive feedback; and (3) resume/cover letter generation components that parse job descriptions and extract user profiles to create documents that are editable and ATS-friendly. The platform prioritizes scalability (SaaS multi-tenant deployment), explainability (user-interpretable feedback), and customization (user edits and templates). Initial prototype testing shows that generated resumes are more compliant with standard ATS checks and are better prepared for interviews. In order to scale career support across institutions and supplement human guidance, Margdarshak wants to serve as an on-demand digital mentor.

Copyright & License

Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

BibTeX

@article{186627,
        author = {Sreyash Salunkhe and Prof. Deepak Ranoji Naik and Atharva Patil and Rahul Gehlot and Atharva Shelar},
        title = {Margdarshak: AI-powered virtual career mentor},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {2166-2175},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186627},
        abstract = {Margdarshak is a Software-as-a-Service (SaaS) virtual mentor that offers ongoing, individualized career support with the goal of enhancing students' employability and career readiness. The platform includes a job-description-aware cover letter generator, an ATS-optimized and fully customizable resume generator, an AI-powered mock interview system with performance-over-time tracking and targeted improvement recommendations, and automated weekly industry insights (trending skills and salary benchmarks). Margdarshak's architecture combines large-language models, structured evaluation pipelines, and contemporary web frameworks: (1) a data ingestion layer that compiles labor-market indicators and updates insights on a weekly basis; (2) interactive mock interview modules that score responses, record performance metrics over time, and generate prescriptive feedback; and (3) resume/cover letter generation components that parse job descriptions and extract user profiles to create documents that are editable and ATS-friendly. The platform prioritizes scalability (SaaS multi-tenant deployment), explainability (user-interpretable feedback), and customization (user edits and templates). Initial prototype testing shows that generated resumes are more compliant with standard ATS checks and are better prepared for interviews. In order to scale career support across institutions and supplement human guidance, Margdarshak wants to serve as an on-demand digital mentor.},
        keywords = {},
        month = {November},
        }

Cite This Article

Salunkhe, S., & Naik, P. D. R., & Patil, A., & Gehlot, R., & Shelar, A. (2025). Margdarshak: AI-powered virtual career mentor. International Journal of Innovative Research in Technology (IJIRT), 12(6), 2166–2175.

Related Articles