CareerCAN I VIBECODE
Rezi?
BUILD FIRST
- One defined user and a repeatable end-to-end job
- A small, clear data model with sign-in only if it is genuinely needed
- Loading, empty, error, and success states that make the workflow feel complete
LEAVE FOR LATER
- Large integration marketplaces
- Multi-region scale and enterprise administration
- Every power-user setting from the established product
RESEARCH NOTES
What this tool actually does.
Rezi is a web-based AI resume builder marketed as ATS-ready. Core workflow: start a new resume from scratch, import an existing PDF/DOCX, pull from LinkedIn via a Chrome extension, or use a conversational AI Resume Agent. The tool formats sections and spacing automatically, provides a real-time 'Rezi Score' with section-by-section feedback and suggestions, and lets users paste a job description to generate missing keywords/tailoring. It includes an AI summary writer, over 900 sample resumes, a job search board with application tracking, and an AI mock interview feature. Export options include PDF, DOCX, and Google Drive. It also supports connecting to external LLM tools (e.g., Claude, Codex, Gemini) via MCP for plain-English resume management. Official claims: used by 4.3M users, Forbes top pick, free tier available.
RESEARCHED BUILD PROMPT
Give this to your coding agent.
Build a focused replacement for Rezi, the AI resume builder. The core workflow: user provides basic profile info or pastes an existing resume; the app parses it into structured sections (summary, experience, education, skills); user pastes a target job description; the app scores resume-job match, lists missing keywords, and lets user accept AI-generated bullet rewrites and summary tailored to that job. User-facing requirements: step-by-step wizard, real-time ATS-style preview, per-section match score, keyword suggestions with one-click add, AI summary generator, dark mode, sample resumes, and export to PDF/DOCX. Technical requirements: a Next.js or similar SSR frontend with a PostgreSQL database for resumes, an LLM integration layer (OpenAI-compatible API) for parsing/rewriting/scoring, and a PDF generator (e.g., react-pdf or headless Chrome). Implementation approach: use a structured JSON resume schema, store job descriptions separately for comparison, compute keyword overlap with a simple TF/IDF or embedding similarity, and keep all AI calls async with streaming for feedback. Do not copy Rezi's brand, logo, color scheme, exact layout, or proprietary UI; create an original interface. Out-of-scope for v1: job board integration, LinkedIn import, mock interviews, MCP connectors, multi-user collaboration, and internal user accounts beyond simple auth. Deliver a README covering setup (env vars for DB and LLM key, migration/seed commands, run scripts) and important limitations (LLM hallucination of achievements, PDF fidelity differences, no guarantee of ATS compliance). Name the app 'ResuMatch' and reference Rezi as the inspiration workflow.