Skip to content
All projects

Evidence-Based AI · Full-Stack Application / v1.6.1

AI Job Application Assistant

A full-stack AI application that compares a PDF CV with a job description, extracts role requirements, verifies candidate evidence, calculates a deterministic match score, and generates guarded application material with a local LLM.

Next.jsTypeScriptTailwind CSSPythonFastAPIPydanticOllamaLlama 3.2PyPDFHTTPX

Project overview

PDF CV content and a complete job description are processed into a structured requirement-evidence table.

Requirements are classified into MATCHED, PARTIAL, and MISSING states before scoring.

A deterministic Python scoring layer produces a transparent 100-point breakdown.

The local LLM is kept out of the scoring path and used for guarded natural-language generation.

System workflow

01

Extract

PDF CV + job description → normalized candidate and role text

02

Verify

Requirements → canonical evidence states

03

Score

Deterministic Python weighting → explainable score

04

Generate

Structured evidence → guarded local application material

Explore the implementation

This case study is based on the project’s own documentation.

More projects

Let’s talk about AI and software development