Tutorials Prompt Engineering Tutorial
AI Resume Analyzer — PromptVerse Project
AI Resume Analyzer — PromptVerse Project: free step-by-step lesson with examples, common mistakes, and interview tips — part of Prompt Engineering Tutorial on Toolliyo Academy.
On this page
Prompt Engineering Tutorial · Lesson 92 of 100
AI Resume Analyzer
Prompts ✓ → Apps
Apps · 2 — RAG & agents · ~10 min · Module 10: Real-World AI Projects
What is this?
PromptVerse HR module scores resumes against a JD with evidence quotes — no demographic inference.
Why should you care?
Recruiters get JSON they can sort and filter instead of re-reading PDFs.
See it live — copy this example
Copy the prompt into ChatGPT, Claude, or your LLM API playground and compare outputs.
SYSTEM: Score only JD skills. Never infer protected attributes. Every score needs evidence_quote from resume text.
USER: JD: (skills list) RESUME: (text)
EXPECTED: { match_score: 1-10, skills_found: [], gaps: [], evidence_quotes: [], recommend: "screen|hold|reject" }What happened?
- Rubric in system restricts scope.
- evidence_quotes anchor scores.
- recommend enum drives ATS workflow.
Practice next
- Use redacted sample resume.
- Run extract prompt.
- Verify every skill has quote or gap.
- Add must_have skills gate.
- Flag resume shorter than 100 words as hold.
Remember
JD-grounded scoring. Evidence quotes mandatory. Structured ATS output.
Bulk screen
200 applicants for one role.
Outcome: Sorted JSON list; recruiter reviews top 20.
Interview prep for this lesson
Practice these questions aloud after reading—each links to a full structured answer.
Sign in to ask a question or upvote helpful answers.
No questions yet — be the first to ask!
