The “Recruiter’s Eye”: The app doesn’t just scan for words; it thinks like a human recruiter. It spots where your experience is strong and where you might be leaving out the “proof” that hiring managers look for.
ATS Scorecard: Different companies use different software to screen resumes. Our tool shows you how you rank across the three most popular systems (Greenhouse, Lever, and Workday) so you know exactly where you stand.
Evidence-Based Matching: Instead of guessing, the AI highlights the exact sentences in your resume that prove you can do the job. If it can’t find proof, it tells you exactly what’s missing.
Smart Rewriting: It provides a “Before and After” for your most important bullet points, showing you how to rephrase your achievements to sound more impactful without changing the facts.
One-Click Analysis: Simply paste a link to your Google Doc resume and the job you want. In seconds, you get a full strategic report on how to win the interview.
ATS Scorecard
Project Synopsis: ATS & Recruiter Simulation Engine
This application is a high-fidelity resume analysis tool designed to bridge the gap between job seekers and Applicant Tracking Systems (ATS). It provides a deep-dive “recruiter’s eye” view of how a resume stacks up against a specific job description.
1. The Model
The core intelligence of the application is powered by Gemini 3.1 Pro Preview.
Why this model? We selected the 3.1 Pro variant for its superior reasoning capabilities, high context window (essential for long resumes and complex JDs), and its ability to strictly adhere to complex JSON schemas for structured data output.
Structured Output: The model is configured with a strict responseSchema to ensure the UI receives predictable, typed data for scores, tables, and markdown reports.
2. How the Prompt Works
The prompt is engineered using a Role-Based Simulation framework. Instead of a simple “summarize this,” the prompt instructs Gemini to:
Assume a Persona: It acts as a “Senior Technical Recruiter and ATS Specialist.”
Multi-Perspective Scoring: It simulates three distinct ATS environments (Greenhouse, Lever, and Workday), each with its own weighting logic.
Evidence-Based Analysis: The model is forbidden from “hallucinating” skills. It must provide exact “Evidence Quotes” from the resume to justify every match.
Actionable Feedback: It generates a “Top 12 Edits” list, prioritizing changes that yield the highest estimated “points gained” in an ATS ranking.
Recruiter Simulation: It provides a “Decision” (e.g., “Strong Yes,” “Skim & Reject”) along with validation questions for a human interviewer.
3. How the App Was Built
The application uses a modern Full-Stack TypeScript architecture:
Frontend (React + Vite):
UI/UX: Built with Tailwind CSS for a “Technical Dashboard” aesthetic.
Animations: Framer Motion handles the smooth transitions between the input stage and the multi-tab analysis report.
Icons: Lucide-React provides the visual language for technical metrics.
Client-Side AI: To minimize latency and follow security best practices, the Gemini API is called directly from the browser using the @google/genai SDK.
Backend (Express):
Text Extraction: A custom Node.js server handles the heavy lifting of fetching and parsing external data.
Google Docs Integration: Uses axios to fetch raw text from public Google Doc links.
Web Scraping: Uses cheerio to extract job descriptions from various career sites, handling retries and basic rate-limiting detection.
Security & Configuration:
Secrets Management: Uses AI Studio’s native Secrets panel to securely inject GEMINI_API_KEY2 without exposing it in the source code.
Environment Sync: A custom Vite define configuration ensures that environment variables are correctly mapped between the server-side environment and the client-side bundle.
Key Features of the Approach:
By using Google AI Studios I was able to create an APP less than 20 minutes. The code was generated using AI and then fine tuned with AI input. 🚀
01.
This ATS Scorecard is provided for educational and demonstration purposes only. Results are automated estimates and do not guarantee hiring outcomes or reflect any specific employer’s actual screening process. The creator assumes no responsibility for decisions made based on this tool’s output.
This project was developed as a portfolio demonstration showcasing coursework completed through Johns Hopkins University in Baltimore, Maryland.