Instead of sending a generic CV and hoping for the best, what if a recruiter could instantly see how well I actually fit their role — scored, broken down, and honest about the gaps?

That’s what Job Fit Analyzer does. Paste a job URL or description, and a pipeline of AI agents reads the posting, compares it against my real experience, and returns a structured analysis in seconds.

The Idea #

Job searching is a matching problem. Recruiters skim CVs trying to connect dots between a role and a candidate. I wanted to flip that — give them a tool that does the matching for them, transparently showing where I’m strong and where I’d need to ramp up.

The result is honest by design. A score of 58 doesn’t try to spin itself as a great fit. It tells you exactly what matches, what doesn’t, and lets you decide.

What You Get #

• Match score (0-100) — An overall fit number, not inflated.
• Five dimensions scored independently — Technical stack, seniority, domain, soft skills, and location/logistics. Each tells its own story.
• Strengths — Specific things I bring to the role, citing real projects and experience.
• Gaps — Concrete missing pieces, never vague. “No professional Go experience” rather than “some areas for growth.”
• Summary — A recruiter-facing paragraph with a clear recommendation.
• Outreach message (private mode) — A LinkedIn cold DM draft that adapts its tone to the match score — confident when the fit is strong, upfront about gaps when it isn’t.

How It Works #

Three AI agents process the job posting in sequence, streamed to the UI in real time:

flowchart TD
    A[Job URL] --> B[Web Scraper<br/>extract content]
    B --> C[Agent 1: JD Analyst<br/>extract structured JD]
    C --> D[Agent 2: Profile Matcher<br/>score fit against CV]
    D --> E{Outreach mode?}
    E -->|Yes| F[Agent 3: Outreach Writer<br/>generate LinkedIn cold DM]
    E -->|No| G[SSE Stream]
    F --> G
    G --> H[React UI<br/>results]

    style A fill:#1a1a2e,stroke:#e94560,color:#fff
    style B fill:#1a1a2e,stroke:#0f3460,color:#fff
    style C fill:#1a1a2e,stroke:#16213e,color:#fff
    style D fill:#1a1a2e,stroke:#16213e,color:#fff
    style F fill:#1a1a2e,stroke:#16213e,color:#fff
    style G fill:#1a1a2e,stroke:#0f3460,color:#fff
    style H fill:#1a1a2e,stroke:#e94560,color:#fff

1. JD Analyst — Reads the raw posting and extracts structured data: title, company, tech stack, required vs. nice-to-have skills, seniority, domain, remote policy.
2. Profile Matcher — Scores my fit against the extracted JD across five dimensions, pulling strengths from real projects and flagging honest gaps.
3. Outreach Writer (optional) — Drafts a LinkedIn message calibrated to the match score.

Tech Stack #

• Next.js, React, Tailwind CSS
• OpenAI GPT-4o with structured JSON outputs
• Server-Sent Events for real-time streaming
• Deployed on Vercel