Inspiration
In today’s fast-paced tech ecosystem, students and early professionals often feel overwhelmed by career choices. There are countless tutorials, roadmaps, certifications, and job roles — but very little personalized guidance.
Many learners don’t know:
- Whether they are job-ready
- What skills they are missing
- How to structure their preparation
- How to move from learning to earning
This inspired the creation of AI Career Navigator — an AI-powered system designed to bring clarity, structure, and measurable direction to career development.
What it does
AI Career Navigator is a personalized AI mentor that:
- 📄 Analyzes resumes and extracts structured skill insights
- 🎯 Detects skill gaps for a selected target role
- 🗺 Generates a customized 4–8 week learning roadmap
- 💡 Suggests portfolio-ready project ideas
- 🎤 Simulates mock interviews with AI evaluation
- 📊 Calculates a Career Readiness Score (0–100)
Instead of generic advice, the system provides data-driven, role-specific recommendations.
How we built it
The application was built using:
- Python
- Streamlit for an interactive dashboard interface
- Google Gemini API for intelligent reasoning and evaluation
- Pandas for structured data handling
- Plotly/Matplotlib for visual progress representation
The architecture follows a modular structure:
- Resume Analysis Module
- Skill Gap Detection Engine
- Roadmap Generator
- Project Idea Generator
- Mock Interview Simulator
- Career Readiness Scoring System
Gemini API is used extensively for:
- Structured resume parsing
- Skill comparison reasoning
- Personalized roadmap generation
- Interview answer evaluation
We also implemented a scoring formula:
[ \text{Career Readiness Score} = 0.4 \times S_m + 0.3 \times I_s + 0.3 \times R_q ]
Where:
- (S_m) = Skill Match Percentage
- (I_s) = Interview Score
- (R_q) = Resume Quality Score
This transforms career guidance into a measurable system.
Challenges we ran into
- Ensuring Gemini consistently returned structured JSON outputs for reliable parsing.
- Avoiding generic AI responses by refining prompt engineering techniques.
- Designing a scoring system that feels logical, fair, and practical.
- Keeping the multi-feature dashboard clean and user-friendly within Streamlit.
Balancing AI flexibility with structured outputs was the biggest technical challenge.
Accomplishments that we're proud of
- Building a fully modular AI-powered career system in a short timeframe
- Successfully integrating Gemini API across multiple intelligent workflows
- Designing a quantifiable Career Readiness Score
- Creating a product that feels like a real startup solution rather than just a demo
Most importantly, we transformed career planning into an interactive AI-driven experience.
What we learned
- Advanced prompt engineering for structured AI outputs
- Designing scalable modular architectures
- Turning AI-generated content into actionable insights
- Thinking like product builders instead of just developers
We learned that AI is most impactful when it provides clarity and direction, not just information.
What's next for AI Career Navigator
- ATS-optimized resume rewriting
- LinkedIn profile analysis
- Real-time job market trend integration
- Adaptive long-term career tracking
- Integration with learning platforms for direct course recommendations
Our long-term vision is to evolve AI Career Navigator into a complete AI-powered career operating system.
Log in or sign up for Devpost to join the conversation.