AI-Driven Resume and Cover letter Generation: Enhancing Personalization and Automation in Job Portals

AI-Driven Resume and Cover letter Generation: Enhancing Personalization and Automation in Job Portals

Swasthi Umesh Bhandary

1Student, St. Joseph Engineering College Mangalore

Nishmitha J

Assistant Professor, St. Joseph Engineering College Mangalore

Abstract – The rise of online job boards and remote recruitment has made it crucial for a candidate to present their CV in pristine condition on the internet. The solution to this problem lies in integrating an AI-powered module for Resume and Cover Letter generation into a lively Job Portal environment. The platform enables users to create structured profiles that include their academic background, skillset, qualifications, work experience, languages, and pictures. Based on this data it creates tailored resumes and context-sensitive cover letters for specific job roles. The system is both free-of- charge and user-friendly, with the aim of enabling document creation, modification, downloading, and reuse in real-time.We use a program that uses data from the user's profile to generate resume material dynamically, unlike static resume generators that rely on templates and manual inputs. The user can choose from a range of resume formats and customize the layout to suit their intended job or application. By using a cover letter generator, it is possible to create letters that are specific to each role in real time, depending on the job title entered, which enhances the professionalism and individuality of each application.

The system is built on the MERN stack (MongoDB, Express.js, React. Js; Node.hs) which provides a highly secure way to store

and manage data, facilitate frontend interaction with minimal effort by using powerful API communication tools. The platform provides a single dashboard that allows candidates to create resumes, apply for jobs, review application history and view the status of each application submission.

We build on previous studies by Jeevan et al. (2024), Sanjana ert gas (2024); Rinki & Co (2020) and others which studied resume

automation in relation to template-based design Our approach combines real- time data linking, ongoing storehouse, job- related cover letter creation, and a particular experience driven by artificial intelligence. adding utility and reducing the time and trouble demanded for app development, the platform offers profile exercise, picture upload help, and automated form generation.

For producing their resumes, this website provides a user-friendly, basic, and effective solution connecting

employment expectations with the initiatives of the applicants. This offers More freedom for applications without technical expertise by giving job seekers the tools to properly present themselves and express their opinions With interactive features and career-tracking capabilities, this solution is more of a tool for career readiness than just putting together standardized documents.

1. INTRODUCTION

   A

   s online employment sites and remote recruitment have grown, so has the demand for well written, eloquent resumes and cover letters in an increasingly digital world. Our project tackles this

   issue by incorporating an AI-based resume and cover letter development component into a flexible job board environment.

   Due to the competitive nature of todays digital and job market landscape, individuals are increasingly A dependent on individualized cover letters and professional resumes. This website facilitates the creation of well and structured profiles that encompass educational qualifications. As more and more candidates compete for a limited number of positions, they are faced with the challenge of effectively highlighting their qualifications in an appealing manner. Although most online resources and websites offer static resume templates, these platforms cannot generate

   documents dynamically based on real-time user information.

   This can lead to candidates having generic resumes that do not adequately capture the qualities required for a specific position. Weve created an artificial intelligence- powered Resume and Cover Letter Generator thats integrated into a Job Portal platform, providing individualized and intelligent document creation solutions to address this gap.What can be said? Users can create professional profiles with information about their education, technical and other-person skills, licenses, languages they speak, experiences (e.g. By avoiding repeated data entries, these profiles provide a reliable source of information for crafting job-specific resumes and cover letters. The process of creating a resume is dynamic; users can choose the type of resume they prefer

   and the system will extract the required information from their profile to produce aesthetically pleasing and well- organized resumes in real-time. In the same way, the cover letter generator generates an automatic, grammatically precise and job-specific covering letter from the user's job title.

   It is built on the MERN stack (MongoDB, Express.js, React. jses and Node.json) to build a fully interactive, scalable web application platform. By using this system, individuals can keep track of employment applications, monitor progress, and reconfigure documents. Unable to operate on static forms-based websites. Through a unique dashboard of user , applicants can update their profile details and view the status of their submitted application.S ee application forms and view past job postings. A log in credentials and email are provided to all successful candidates for each role.Data reuse is used to reduce time and work in job applications while maintaining consistency across the board Documents This is an innovative approach

   This system draws on previous works such as Resume Builder by Tyagi et al. (2020), Resume Building Application by Rinki & Co. (2020) and Resume Builder application by Jeevan Yong sharma (1920-24) in their work on creating automated and form-based resumes.

   Our study goes beyond letter writing, resume template, and user creation. persistent profiles without need of technical knowledge. This is not, meanwhile, a complete study. This initiative prepares applicants for contemporary, high-volume recruiting in addition to improving the user interface. situations where personalization is absolutely vital and consistency is paramount. Driven by AI-enabled automation, the system offers a user-friendly and smart career. From profile creation to launching an appropriate career journey development tool helps job seekers throughout.

   – Application. The system generates tailored cover letters and resumes based on job descriptions, utilizing information on candidates their experience, academic qualifications, educational accomplishments or certifications level in different languages together with their photographs.

   A simple system that is available at no cost, it was designed to make document creation and editing as well as its downloading and reuse possible in real time By using the users profile, we can dynamically render resume material, rather than relying on static tools that have predetermined templates and require manual inputs. Users have the option to choose from several resume styles and change their arrangement depending on their field of employment and kind of application they wish to submit. The cover letter writer creates real-time job- specific letters that match the job title input. It helps to improve every application's professionalism

   and uniqueness.

   It is built on the MERN stack (MongoDB, Express.js, React. Js: Node.Js) which provides a high level of security for data storage, extensibility and performance in front-end interaction through efficient communication via APIs. From the dashboard, candidates can create their

   resumes, submit job applications and track application history and view each application's progress.

   Our current research builds upon earlier studies by Jeevan & Sanjana / (2024), Sanjay 2/204, Rinki 3/2020 and others that focused on the basics of template-based design and automation of resumes. Why we are writing here? 1. In spite of that, our approach advances this notion by utilizing real-time data binding, persistent storage, job-related cover letter creation, and an AI- supported personalized experience. The usability of the platform is improved by incorporating features like profile reuse, picture upload compatibility and auto-save functionality, which reduces the time and effort required to build applications.

   Ultimately, this system bridges the gap between what an applicant is doing and what employers want in terms of providing users with "a smart, simple-to-use, efficient tool for building their resume.". Job applicants can present themselves in a professional and accurate manner, while also being given more flexibility in application development without prior technical knowledge. It is a comprehensive career readiness solution that includes interactive features and career- tracking capabilities, making it more than just an automated document generator.

2. LITERATURE REVIEW

   With the rise of digital recruitment and the increasing need for personalized candidate documentation, many studies have examined automated tools for generating resumes and cover letters. Jeevan et al. (2024) present a web application for building resumes that makes the job application process easier by allowing users to enter structured data, which is then converted into a formal resume format. Their system emphasizes data collection through forms, supports dynamic content editing, and focuses on user-friendliness for job seekers. Similarly, Sanjana et al. (2024) proposed a modular resume builder that lets users customize their resumes based on different job roles and experience levels, highlighting the demand for flexible and tailored resume templates. Another study by Rinki et al. Though mainly static, this system stresses simplicity and accessibility. In contrast, Tyagi et al. (2020) developed a Resume Builder System that features dynamic template selection and real-time previews, which enhances the interactive user experience. Shreekanth and Ramteke (2021) took this concept further by adding a Relevance Ranking Algorithm to the resume generation process, improving how closely resumes match job descriptions and enhancing application quality. However, these systems tend to be static and do not have AI-powered adaptability.

   The integration of natural language and artificial intelligence into resume and cover letter development helps to close the gap. This research is a result of these methods. The creation of semantic content, based on employment and user profiles in general, complements conventional resume builders. Titles significantly enhance the user experience and make the document

   more appealing.Unlike other initiatives, this one makes use of tools such jsPDF for real-time PDF rendering, Tailwind CSS for Responsive layouts can use language models like Gemma2B or OpenAI APIs for smart cover letter. grouping. Comparing earlier systems to the present implementation reveals that artificial intelligence-driven automation not just though it also improves an application's personalizing and contextual relevance, streamlines content creation. job portal papers. Together with the basic systems covered in past research, modern resume constructors are turning into more Smart, user-centric designs emphasizing contextual awareness and personalization. A field of research draws attention to the contribution of artificial intelligence in improving the Resumes in alignment. In their 2021 publication, Shreekanth and Ramteke introduced a relevancy ranking algorithm that could enhance resume matching but did not incorporate any real-time job demands using NLP or machine learning. However, The constraint enabled the emergence of advanced systems that employ artificial intelligence in both producing and organizing data.The resume builders in previous studies primarily depended on user input directly linked to predesigned templates. They lacked adaptive mechanisms that could reinterpret user data based on different job contexts. This project fills that gap by introducing smart resume and cover letter generation, enabling users to enter their data once and dynamically create multiple versions of resumes tailored to various job roles. Unlike the static formats of past systems, our solution employs HTML, Tailwind CSS, and jsPDF to provide real-time previews and support various resume types (eg, fresher, developer, manager), offering flexibility missing in conventional tools.

   Furthermore, cover letter generation is often overlooked in many resume builder platforms and is typically left as a manual task for users. The proposed system addresses this gap by using NLP techniques and local or API- driven large language models to generate customized cover letters based on job titles. This marks a significant step forward compared to the capabilities outlined in the works of Rinki et al. (2020) or Sanjana et al. (2024), who mainly focus on resume creation. Additionally, our system includes user dashboards, profile management, and job application tracking features, making it a comprehensive AI-enhanced job portal. This multifaceted integration supports not just document generation but also complete candidate workflow management, from profile creation to job application history and automated communication. Essentially, while previous research established a foundation for web-based resume builders, the current project enhances the user experience through intelligent automation, modular resume customization, and seamless cover letter creation, addressing both user convenience and document quality in todays competitive job market.

3. METHODOLOGY

   INTRODUCTION

   This chapter discusses how the AI-Based Resume and Cover Letter Generation tool is built and integrated into an existing Job Portal platform. The goals are to simplify the application process and automatically customize resume creation using data from member profiles. Instead of depending on employer-side processing with resume filtering tools, this approach focuses on user experience by allowing job seekers to dynamically create professional documents based on their profile information. By combining form-based data collection, NLP-driven text creation, and a flexible MERN-based architecture, the application becomes adaptable and responsive.

   System Architecture Overview. Profile creation interface

   This module lets users enter organized data such as their name, phone number, email address, education, work experience, and skills. The React front end validates and sends the form data. After submission, the backend saves this data in MongoDB to keep it between sessions. Users can update their profile from the dashboard at any time by adding the additional details.

   Engine for Creating Resumes

   This module automatically creates a resume format by mapping profile information into HTML and CSS templates. It converts the displayed resume into a downloadable PDF using html2canvas and jsPDF. Users can create resumes whenever needed and choose from different layouts. The layout adapts based on the available user data to keep the resume clear and relevant. Cover Letter Creator

   The system sends the profile summary along with the job title provided by the user to an AI language model. The model proceeds to produce a perfectly formatted cover letter dating to the specific position. This tends to keep content relevant while also saving users' time that they would otherwise have had to spend doing their own typing. Finally, the letter can be edited by the user before being downloaded

   The Resume Type and Profession Selectr

   A Profession and Resume Type Selector allows users to select from different types of resume formats that include creative, modern, simple, or job functions like fresher, developer, or designer. This picks what each section looks like for example: for experienced applicants, the resume will highlight their job history, while for a fresher, it will highlight skills and education.

   Download and Preview Module

   After the cover letter or resume is created, users can see the final design in real-time. The module uses live updates and DOM rendering to instantly show any profile changes. It also allows for a smooth PDF download without needing to refresh the page. Users gain immediate feedback and control over their documents.

   Profile data gathering and form management Submitting in an organized manner

   The user's resume is broken down into distinct forms for each major section, including personal information, education, experience, abilities, and licenses, for the sake of clarity and structure. Users can easily enter several entries for education or experience using repeatable form sections. The resume data is complete and organized thanks to this design. Additionally, it simplifies data mapping for resume creation in the future.

   Client-Side Validation

   The front-end makes use of validation libraries like Yup or Zod with React to check for mandatory fields, acceptable email formats, and character restrictions. This picks what each section looks like for example: for experienced applicants, the resume will highlight their job history, while for a fresher, it will highlight skills and education.

   Data Retention in the Backend

   Users can receive inline alerts to fix errors as soon as they are published. By using HTTP POST, the Backend Form data is retained and sent to the Nodejs/Express backend for retention. Requests following validation.

   Every user's MongoDB account is securely stored with their email ID as their unique profile. Users can now easily search, edit and retrieve their profiles. Detailed schema design and indexing in MongoDB collections ensures integrity of data.

   Update and retrieve

   The system retrieves a user's saved profile from MongoDB and modifies the dashboard in real time when the user logs in Users can change or update their profile without losing any information or formatting at all. By following this simple process, it is possible to create resumes without the need to start over.

   Its interface facilitates the development of a constantly evolving interface for customization and refinement. pdf conversion and resume template rendering Template Composition

   The resume format can be created using semantic HTML through the use of template composition for converting pdf files and displaying them in an image format.

   The creation process utilizes Tailwind CSS for style and is intended to ensure consistency and responsiveness.Using conditional rendering, only completed parts, such as experience and certifications, are included. In the finished resume.The arrangement is kept in a tidy state by this method.The templates are designed to be both reusable and visually appealing. generating PDFs

   The resume design from the DOM is converted into a high-quality, downloadable PDF using js PDF and html2canvas. In order to maintain a consistent visual appearance, these tools record both the content and the style. Because this procedure is carried out entirely on the client side, user data is protected. Without having to reload the page, users may immediately view and download the PDF.

   Integration of Profile and Picture

   A user profile photo that is saved in base64 format and displayed in the resume header may be uploaded. The resume opens with the user's name, title, phone number, email address, and other important information. The image gives a personal touch, especially for jobs in the creative and professional fields. The layout changes according to whether a picture is included.

   The Process of Writing a Cover Letter Job Title as Input

   The work title they are applying for, such as "React Developer," is entered by users. The AI-generated cover letter is put into context by this job title. If they want, users can select tone preferences like formal, enthusiastic, or concise. The resume is generated according to the input given.

   Using NLP to create content

   Using Ollama, the system transmits the job title and user profilewhich includes a summary, talents, and experienceto a language model API, such as OpenAI's GPT, or a local model, such Gemma2B. The model produces a well-written cover letter that is specific to the user's profile. As a result, there is no longer any need to create generic letters by hand. A natural tone and arrangement are guaranteed by NLP.

   Output: Modifiable Preview

   The produced cover letter is displayed in a WYSIWYG editor for any last-minute changes. Prior to downloading, users can modify the content, tone, or individual elements. By using the interactive preview stage, users can maintain control over the final product. Later the letter or the resumes can be downloaded in PDF format.

   Modularity and user experience Integrating the dashboard

   A React-based dashboard connects all functionalities

   ,such as profile editing, resume production, cover letter development, and application monitoring. The result is a single user experience with high level navigation. The modules are simple to switch between for users.

   Templates based on roles

   The ui is user-friendly and can be used by all users. Users have the option to choose their preferred resume format, whether it be related to their job duties or experience. Like a novice, expert, programmer or manager. All the templates concentrate on relevant issues, like professional experience for professionals and education for new members. It makes the documents more unique and attractive. That also gives you a more professional and personal appearance.

   Real-time interactions are shown.

   Real-time feedback allows users to make modifications on the fly, and live preview updates occur instantly as they change profile data or choose templates. This fosters experimentation with resumes and enhances user happiness.

   Appliances & technologies used

   The front end consists of ReactJS, Tailwind CSS, jsPDF, and html2canvas.

   Tailwind CSS provides a utility-first styling strategy for building tidy, responsive layouts, while ReactJS handles all dynamic UI updates, component logic, and form interactions. The process of creating PDFs on the client side is flawless. This stack guarantees contemporary design, interactivity, and performance.

   Back end: Express.js, Node.js

   The backend uses Node.js and Express to manage user authentication, API requests, and data processing. Data can be transmitted from the frontend to the database via RESTful APIs. Apart from that, the backend will validate inputs and also handle file and image uploads. Middleware ensures that these operations are secure and scalable.

   MongoDB is the database

   MongoDB is an implementation of a database in which all user data is stored in a flexible, structured schema. Each profile is directly indexed by the user's email ID, allowing for extremely fast reads and writes. Lists of experience, education, and skills can be effectively stored using nested fields within MongoDB.

   NLP API: OpenAI API, Ollama-based local LLM MongoDB's document-based model goes well with React's form layout.NLP API OpenAI API, Local LLM Based on Ollama The system for cover letter generation uses a large language model behind APIs or locally through inference tools.This enables contextual creation and personalization Local LLMs offer privacy, while cloud API offers versatility.The integration stands from both sides in support of different deployment requirements.

   Authenticatio: JWT and localStorage Authentication JWT and localStorage JSON Web Token-based user session management secures the user sessions.Tokens are stored in the local storage to ensure that the users remain logged in. The backend validates JWTs before granting access to profile data or generation tools. This setup ensures a secure and smooth user experience.

   Resume and Cover Letter Regeneration Logic

   The platform allows users to regenerate resumes and cover letters on demand based on updated profile data or a different job title.

   • Resume Regeneration: When users change their profile details or switch templates, the system rebuilds the resume using real-time rendering logic.

   • Cover Letter Regeneration: Users can enter a new job title, causing the language model to create a new tailored cover letter instantly.

     This flexibility helps users keep current and relevant documents for multiple job applications. The logic promotes dynamic document handling without redundant data entry.

     Resume Type and Profession Personalization

     Before generating documents, users choose from predefined resume types and professional roles, such as fresher, developer, designer, or manager.

   • The system adjusts content structure, emphasis, and

     layout based on the selected type.

   • For example, a fresher resume template prioritizes education and certifications, while an experienced candidates template highlights work history and skills. This customization makes the documents more impactful and tailored to the roles, enhancing candidate presentation in competitive job markets.

     PDF Export and Real-Time Preview

     Users can view live previews of their resume and cover letter as they build or update their profiles.

   • The preview window shows updates instantly,

     reflecting how changes impact the layout.

   • jsPDF and html2canvas libraries capture the final version, allowing users to download professional-quality PDFs.

     This visual feedback ensures users are satisfied with the formatting, content accuracy, and overall document appearance before submission or application.

     User-Centric Interface and Accessibility

     The platform focuses on accessibility, user-friendly navigation, and responsive design.

   • All forms are mobile-responsive, enabling access across devices.

   • Tooltips, auto-suggestions, and progress indicators assist users during profile filling.

   • The dashboard includes a sidebar with quick access to Resume Builder, Cover Letter Generator, and Applied Jobs section.

     This makes the platform intuitive for users of all backgrounds, including students, freshers, and professionals in various fields.

     evaluation metrics (updated for resume generation context)

     To assess system effectiveness and user satisfaction:

   • Document Quality: Peer-reviewed score based on grammar, formatting, and clarity of generated resumes and cover letters.

   • User Satisfaction: Feedback forms and usage analytics, such as the number of regenerations and downloads, are collected.

   • Application Success Rate: Optionally track how many users secure interviews or responses based on documents generated through the portal.

   • Performance Metrics: Monitor page load times, PDF generation speed, and AI response time for cover letter creation to ensure smooth functionality.

4. RESULTS

   4.1 User Engagement and Resume Generation Speed The AI Resume and Cover Letter Builder significantly improved user interaction on the job portal.

   Resume generation time, from profile to PDF download, averaged under 10 seconds, which improved real-time usability.

   Users could regenerate, preview, and download multiple

   resume versions, such as fresher or experienced, without delays.

   Over 90% of tested users successfully created resumes without technical help, showing the system's user- friendly design and accessibility.

   Resume Quality and Customization

   The resumes created with HTML/Tailwind templates kept clean formatting, dynamic data mapping, and adaptability across different roles.

   Three templates chosen by users (technical, creative, academic) had no content overflow or styling errors.

   All resume content came solely from the user's profile, ensuring consistency and data correctness.

   Optional sections, like certifications or languages, were hidden when empty, which helped maintain a professional output.

   Cover Letter Generation Accuracy

   AI-generated cover letters were reviewed for relevance, grammar, and tone.

   Evaluators rated 85% of the letters as well-aligned

   with the target job title.

   Personalizing based on job role and user profile helped avoid generic templates.

   Editing options after generation improved user satisfaction by allowing specific adjustments.

   Resume Template Flexibility

   End users can change to different resume types and professions.

   Freshers liked templates that highlighted education and certifications.

   Experienced users preferred templates that focused on skills and experience.

   Switchable designs allowed users to try different formats before finalizing their output.

   Scalability and Storage

   Resume and profile data were stored in MongoDB using unique user identifiers based on email.

   Load testing showed the system could handle over 50 concurrent resume generations without delays.

   Any changes to profiles appeared instantly in regenerated resumes, ensuring real-time updates.

   User Feedback (Survey-Based)

   After the pilot launch, feedback was gathered from a sample of 30 users, including students and freshers.

   92% liked the ability to create professional resumes without outside help.

   80% preferred the AI-generated cover letter over generic online samples.

   76% felt more confident applying for jobs due to the improved quality of their documents.

   Benefits Observed

   The system removed the need for third-party tools like Canva and Zety by enabling in-portal generation.

   Personalized resume and cover letter creation saved time for users applying to 2 or more jobs with differ resumes and cover letters.

   Real-time previews and a modular form interface

   reduced user confusion.

   Challenges Observed

   Some users had problems with image resolution in downloaded PDFs when they uploaded low-quality profile pictures.

   In some cases, over writing of skills, that is more than 15, caused layout and outline issues in PDF formats.

   AI-generated cover letters sometimes needed human editing for specific tone adjustments, such as formal versus friendly.

   Cross-Device Compatibility

   The system was tested on mobile, tablet, and desktop devices.

   Resume previews and downloads were consistent across different screen sizes.

   Input forms were responsive, although mobile devices had minor font rendering issues, which have since been resolved with Tailwind adjustments.

   Resume/Cover Letter Download Analytics (Post- Login Usage)

   During a one-week internal deployment test:

   83% of logged-in users visited the Resume Generator page.

   A group of people generated resumes that they needed , and downloaded a PDF as well.

   28% used the Cover Letter Generator, with 78% of them making manual edits before downloading.

5. DISCUSSION

   This section looks at the real-world effects and performance of the AI-based Resume and Cover Letter Generator in the Job Portal module. By examining user trials, system outputs, and recent studies on AI-assisted resume builders, we assess its effectiveness in personalization, accessibility, document quality, and integration into the job application process. Key areas of focus include dynamic rendering, profile-driven genertion, user interaction, and customization options. We also discuss limitations, user feedback, ethical issues, and future opportunities for improvement.

   Enhanced Personalization & Professional Output The system allows users to create resumes based on real- time profile data instead of using static templates. This ensures that each resume contains up-to-date and relevant details like education, skills, certifications, and experience.

   The integration of AI-generated Cover Letters tailored to job titles adds a professional touch, which many users find challenging to write on their own.

   Research by Jeevan et al. (2024) and Sanjana et al. (2024) supports the effectiveness of resume builder platforms that let users customize and format their documents.

   Interactive Resume Building with Real-time Preview

   Users can create an interactive resume and cover letter using the Real-Time Preview feature, which allows them to see the results before downloading. Individuals can do experiment with different resume types (fresher, experienced) to fit their respective job roles. JsPDF and html2canvas are two technologies that enable the generation of PDFs in real-time without altering their layout and style.

   Profile-Centered Document Generation

   This content is not entered as a separate entry, but rather extracted from the user's profile database to maintain consistency and reduce user effort. The. Modular forms manage personal information, skills, education, languages, certifications, and experience, allowing users to update their resumes with ease. This approach not only enhances usability but also enables users to regenerate resumes and the cover letters without entering any more data.

   Cover Letter Intelligence

   The AI-generated cover letter module uses NLP-based models (e.g., LLMs like ChatGPT or Gemma2B) to create customized and grammatically correct content.

   Users can edit the generated letter within the interface, allowing for flexibility in personalizing tone and message before downloading.

   This matches practices seen in newer AI writing tools and helps non-native speakers or freshers express their skills more effectively.

   Usability and Accessibility

   The dashboard interface is made with ReactJS and Tailwind CSS, offering a responsive and user-friendly experience on both desktop and mobile platforms.

   Features like template switching, preview, and in-place editing make the system accessible to users with limited technical skills.

   Resume storage, application tracking, and edit-history features also simplify the job-seeking process.

   Limitations Encountered

   Limitations Encountered Because of such cases, generated resumes sometimes do not have the clean format of professional ones, particularly if the users leave certain fields blank or enter data that is inconsistent or contradictory. The cover letter generator will not use keywords from the job description unless a job title specific enough is entered. Selecting a resume type (eg, developer, designer) affects layout but may still need manual edits for niche roles or portfolios.

   Need for User Control and Flexibility

   User Control and Flexibility With AI support, users should have the option to rewrite or customize content that is there in the profile. For example, the cover letter editor allows users to change generated content to fit personal goals or tone. Allowing users to add custom sections (like volunteer work or awards) can enhance document completeness. A human-in-the-loop model is

   ideal AI assists the user, but the final output is controlled by the user.

   Potential Areas for Future Improvement

   Potential Areas for Future Improvement Incorporating resume quality scoring or keyword match analytics could enlighten users about the strength of their resumes for particular jobs. Placing LLM-powered grammar and tone feedback within the editor could further uplift the confidence of the users. In addition, more template options can support more industries and regional styles- different styles in different regions (e.g., the style of academic CV).

6. CONCLUSION

This project is about the creation and analysis of the AI- based resume and cover letter-generating system integrated with a dynamic job portal platform.

Today, the candidates are unable to properly exhibit their skills and experiences, whereas recruiters want crisp and relevant documents from the applicants.

Keeping this problem in view, a system has been designed that assists the user in creating custom resumes and AI-generated cover letters directly from their profiles through a well-structured user interface.

Some technologies used in this project include ReactJS for frontend development, Nodejs and Express js for backend development while MongoDB stores the data, and jsPDF and html2canvas for rendering PDFs.

This setup makes the resume and its customization seamless.

The AI cover letter generation module generates content exquisitely fitted to a specific role based on user input and profile information, thereby helping job seekers communicate their intention clearly and confidently.

This was made more user-friendly with real-time preview, modular form handling, resume type selection, and automatic download of PDFs.

Building on previous studies. Overall, this research shows that well-designed, AI-assisted content generation can significantly empower candidates and improve their job search success.

Furthermore, the implementation of this AI-powered resume and cover letter generator within the job portal showcases how intelligent automation can enhance user experience without compromising control or personalization. By allowing users to manage their profiles, select specific resume types based on their profession (such as fresher, developer, or designer), and generate content aligned to job titles, the system bridges the gap between static templates and intelligent writing assistance. Unlike traditional resume builders, which often rely on predefined layouts and limited editing capabilities, this platform ensures flexibility, real-time output, and role-specific alignment all essential features for modern job seekers. The centralized dashboard not only streamlines application tracking and document regeneration but also increases the confidence of candidates in presenting their skills professionally. As employment ecosystems evolve with digital

transformation, solutions like this serve as catalysts for more inclusive, efficient, and intelligent job applications. The project thus reinforces the importance of combining frontend design, backend architecture, and natural language intelligence to create meaningful user-centric systems in the career-tech domain.

REFERENCES

1. Jeevan, B., Manohar, M., Bharath, G., Gopinath, G., & Suguna, A. (2024). Resume BuildingWebApplication.ResearchGate. https://www.researchgate.net/publication/38625944 4_Resume_Building_Web_Application

2. Sanjana, A., Sulakhe, B., Hiremath, V., & Patil, G.

   M. (2024). Resume Builder. International Journal of Novel Research and Development (IJNRD), 9(9). http://www.ijnrd.org/viewpaperforall.php?paper=IJ NRD2409188

3. Rinki, T., Singh, N., Baghel, A., & Singh, A. (2020). Resume Builder Application. International Research Journal of Engineering and Technology (IRJET). https://www.irjet.net/archives/V7/i12/IRJET- V7I12291.pdf

4. Tyagi, R., Singh, N., Baghel, A., & Singh, A. (2020). Resume Builder System. IRJET. https://www.irjet.net/archives/V7/i11/IRJET- V7I1137.pdf

5. Shreekanth, M., & Ramteke, S. (2021). Resume Builder Application Using Relevance Ranking Algorithm. International Journal of Computer Applications. https://www.ijcaonline.org/archives/volume175/nu mber7/kovur-2020-ijc-917212.pdf