1) Home page
2) Analyze page
3) Action plan feature
4) Voice summary
5) Role alignment feature
6) ATS Review feature
7) Strategy feature
8) Career toolkit feature
9) Evidence traceability feature
10) Claim review feature
11) Score simulator feature
12) Interview question generator and Tailored professional summary
13) Skill Roadmap feature
14) History page
15) Clearing the saved history feature

Inspiration

As a team, we wanted to make the job application process a little less overwhelming. Job seekers often have trouble seeing how clearly their resume reflects the requirements of a particular role. We set out to build a tool that turns a resume and job description into practical, understandable feedback.

What it does

AI Resume Optimization and Career Recommendation System analyzes an uploaded resume and, optionally, a target job description. It provides resume-quality and role-match scores, highlights matching and missing terms, and suggests practical next steps. The report can also include ATS-style checks, interview practice questions, and a skill roadmap based on the job description.

The recommendations are guidance rather than a substitute for the applicant’s judgment. Users should only include skills and experience they can honestly support.

How we built it

We built the interactive experience with Streamlit. Users can upload a PDF or DOCX resume, review its extracted text, and paste a job description for a more tailored analysis. The app checks resume structure, contact information, action verbs, measurable outcomes, and overlap between the resume and job-posting terms. It presents the results in a downloadable report.

The project also includes a FastAPI backend for analysis-related API requests. Together, resume parsing, text processing, scoring, and visual reporting help turn uploaded information into actionable feedback.

What we learned

Working on this project helped us learn how to extract useful text from documents, compare resume content with job requirements, and present analysis in a clear and actionable way. We also saw why explainability matters: users should be able to understand what a score or recommendation is based on.

Challenges we faced

One challenge was handling differences in resume formatting and ensuring that uploaded PDF and DOCX files produced readable text. Scanned PDFs can be difficult to analyze when they do not contain selectable text.

We also wanted keyword matching to be useful without suggesting that a missing keyword means a candidate lacks the underlying skill. The app encourages users to review recommendations and include information only when it accurately reflects their experience. Balancing role-specific feedback with honest, evidence-based guidance was an important part of our work.