03Requirements
Reduce repeated work across résumé analysis, job matching, tailoring and application tracking while making candidate information and workflow state visible.
OPENING THE SYSTEM
Loading the next page…
Loading the next page…
A full-stack prototype for comparing resumes with job requirements, drafting tailored material and tracking review steps through a persistent workflow.
React and FastAPI connect résumé ingestion, Gemini analysis, ChromaDB matching and SQLite application state. Matching and tailoring workflows include review steps and audit logs. Job discovery and Playwright application adapters currently simulate outcomes rather than submit real applications.
Job applications require repeated sourcing, requirement analysis and careful matching against a candidate’s actual experience.
Extract candidate information from résumé documents and store relevant context for matching and later reuse.
Reduce repeated work across résumé analysis, job matching, tailoring and application tracking while making candidate information and workflow state visible.
Extract candidate information from résumé documents and store relevant context for matching and later reuse.
Coordinating model output, saved state and human approval without confusing a prepared or simulated action with a confirmed application.
Résumé documents and job descriptions provide the matching context. ChromaDB enables retrieval; SQLite stores applications, résumé versions, reusable answers and audit logs.
Gemini and retrieved profile context support match scoring, skill-gap analysis and AI-assisted résumé tailoring. Scores help organise review; they are not a calibrated probability of being hired.
FastAPI exposes job, résumé, saved-answer and history APIs. The frontend uses React, Vite and Tailwind CSS. Docker and Docker Compose package the application.
Persist workflow state separately from vector retrieval. Keep generated résumé changes reviewable, record application events and reuse confirmed form answers.
Matching and tailoring still need representative quality evaluation. A feature branch adds explicit non-submission results and four regression tests; that change is separate from the default branch. No real application-submission rate or hiring-outcome benchmark is claimed.
Implemented matching, résumé tailoring, review flows, SQLite persistence and audit logs in a full-stack prototype. Discovery and submission adapters remain simulations, including synthetic confirmation values in the default browser stub.
Handling missing candidate information, changing application forms and incomplete discovery integrations while keeping the workflow understandable.
Useful automation depends on reliable state and inspectable decisions as well as language generation.
Merge explicit simulation statuses, evaluate matching and tailoring against controlled fixtures, and implement verified platform integrations before attempting real submissions.