APP IDEA #21 · AI + SAAS

Rezi — the AI resume builder doing $288K a month

One founder, a 2.2 GPA, and a Word template that turned into one of the highest-earning AI SaaS products on TrustMRR. Here's exactly how it works, what it'd take to build your own version, and the plan to ship it in a weekend.

$288K

MRR (TrustMRR verified)

+7%

Month-on-month growth

4.3M

Users to date

60%

Profit margin

01 / HOW IT WORKS

What the app actually does

Rezi is a resume editor where AI does the writing and the grading. The user picks a target job role, and the app builds a resume against it — not a generic template, a tailored one.

User pastes a job description (or just picks a role)

This becomes the target the resume gets optimized against — every keyword check runs off this text.

AI drafts metrics-driven bullet points

Instead of "managed a team," it writes "led a 6-person team to ship 3 features, cutting release time 20%" — the AI's job is adding specificity and numbers.

The resume is scored, live, on ~20+ metrics

Keyword density, formatting, length, action verbs — each scored and shown as a single number the user can chase upward.

Export as an ATS-safe PDF

No tables, columns, or graphics that confuse applicant tracking software — formatting is the actual product, not a side feature.

02 / INDIA POTENTIAL

Does this work as an India play

Resume tools built for the US market mostly ignore two things Indian job seekers actually deal with: campus placement season volume, and price sensitivity. Both are openings.

1.5Cr+

Students graduate every year in India and need a placement-ready resume within weeks of campus drives opening.

₹99–299

Realistic one-time price point for Indian users, vs Rezi's $29/month — pivot to pay-per-resume instead of subscription.

Strong India-specific competitors doing AI + ATS scoring + Hinglish job-description parsing together, as of now.

B2B

Campus placement cells and coaching institutes (Naukri, Internshala-adjacent) are a direct bulk-license channel, not just individuals.

03 / THE WEEKEND BUILD

Friday to Sunday, hour by hour

Scoped down to a single resume template, one AI rewrite flow, and one score metric — not Rezi's full 23-point system. Ship the core loop, not the whole company.

Friday

Evening · 3 hrs

7–8 PM Set up Next.js project, Supabase auth, and one resume template in React (no editor yet, just static layout).

8–9 PM Build the input form — name, role, job description, work history. Save to Supabase.

9–10 PM Wire up the Gemini/Claude API call that turns raw input into resume bullet points.

Saturday

Full day · 7 hrs

Morning Build the live resume preview — render the AI output into the template in real time as it streams.

Afternoon Add the score logic: keyword match % against the pasted job description, plus a simple formatting checklist.

Evening PDF export using a library like react-pdf, styled to match the on-screen template exactly.

Sunday

5 hrs

Morning Razorpay integration — ₹149 one-time unlock for PDF download, free for editing/preview.

Afternoon Polish UI, fix mobile layout, write 3 landing page lines explaining the ATS score hook.

Evening Deploy, test the full flow end-to-end, record the demo for your first post.

04 / APP STACK

What you're actually building with

Next.js 14

Frontend + API routes

One framework for the form, the live preview, and the backend calls — no separate server needed.

Supabase

Auth + database

Stores user accounts and saved resumes. Free tier covers your first few hundred users easily.

Claude / Gemini API

Resume rewriting

Gemini Flash is cheap enough to run the bullet-point rewrite at near-zero cost per resume.

Razorpay

Payments

UPI-first checkout for the ₹149 unlock — the only payment flow that matters for an India audience.

Pdf

react-pdf

PDF export

Renders the exact on-screen resume template to a downloadable, ATS-safe PDF.

Tailwind CSS

Styling

Fast enough to build and restyle the resume template repeatedly across a single weekend.

05 / WHERE & HOW TO DEPLOY

Going live

Where: Vercel for the app (free tier, deploys straight from GitHub), Supabase for the database (already hosted).

Push your project to a GitHub repo — git init, commit, push.

Import the repo into Vercel, it auto-detects Next.js — no config needed.

Add environment variables in Vercel: SUPABASE_URL, SUPABASE_KEY, GEMINI_API_KEY, RAZORPAY_KEY.

Deploy — Vercel gives you a live .vercel.app URL in under a minute.

Point a custom domain (₹600–800/yr on Namecheap) at it from Vercel's domain settings.

06 / MARKETING & REVENUE

Getting paying users

How to market it

Post the "before/after" resume rewrite as a reel — most viral format in this niche.
Run 10–20 reels/day across multiple accounts with different hooks and angles, not one official page — volume + variation finds the winning creative faster than any single account can.
Target college placement WhatsApp groups and LinkedIn campus communities directly.
Partner with one campus placement cell for a free bulk trial in exchange for testimonials.
Run the free ATS-score check as the hook, gate only the PDF download behind payment.

Who pays, and why

Final-year engineering and MBA students during placement season (Aug–Mar).
Working professionals applying abroad who need an ATS-format resume fast.
Coaching institutes wanting a value-add tool to bundle into their placement prep packages.

Scenario

Paying users/mo

Revenue/mo

Slow start

50 users × ₹149

₹7,450

One campus partnership

400 users × ₹149

₹59,600

Placement season + 10–20 reels/day (multi-account)

3,500 users × ₹149

₹5,21,500

07 / START BUILDING

Paste this into Claude or GPT

This prompt sets up the full build context so the AI scopes, plans, and starts coding the project with you from message one.

BUILD_PROMPT.txt

I want to build an AI-powered resume builder for the Indian job market, inspired by Rezi (a $288K MRR AI resume tool), scoped to ship in a single weekend. Core flow: 1. User pastes a job description and their raw work history. 2. AI rewrites their experience into metrics-driven resume bullet points tailored to that job description. 3. A live score (keyword match % + formatting checklist) updates as they edit. 4. User exports an ATS-safe PDF after a one-time ₹149 Razorpay payment. Stack I want to use: Next.js 14, Supabase (auth + database), Gemini API for the AI rewriting, Razorpay for payment (UPI-first), react-pdf for export, Tailwind for styling. Deploy target: Vercel. Help me, step by step, one question at a time: 1. Scope the exact database schema in Supabase for users and saved resumes. 2. Build the input form and AI rewrite API route first — get the core loop working before any styling. 3. Add the live ATS-style scoring logic. 4. Build the PDF export matching the on-screen template. 5. Wire up Razorpay for the ₹149 unlock. 6. Walk me through deploying to Vercel with environment variables set correctly. Keep explanations short and India-context aware — UPI payments, Vercel/Supabase free tiers, and ₹-priced. Push me to ship the smallest working version first, then improve it. If I get stuck on anything, tell me directly to ask @buildwithkanhaa for the next step or a fresh app idea.