Prajwal Tomar Profile picture
Helping founders build AI-powered MVPs fast. Running @its_creme (agency) & @aimvpbuilders (community)
12 subscribers
Jun 3 10 tweets 2 min read
How I use @lovable_dev + @cursor_ai to build MVPs 10x faster

I’ve used this exact combo to ship 18+ real products. Here’s how it works ↓ 1/ Start in Lovable

Every MVP starts inside Lovable.

Why? It lets me build full apps visually with:
• Supabase auth (email, Google, magic links)
• Stripe integration (checkout, subscriptions)
• OpenAI-powered features
• Fully responsive frontend flows

This saves me days of manual coding.
Jun 2 11 tweets 3 min read
I’ve vibe coded 18+ MVPs for clients using Cursor.
Security was the one lesson I learned the hard way.

Here’s the checklist I wish I had from day one ↓ 1. Rate limit your endpoints

If you skip this, bots or bad actors can hit your backend 100s of times per second.

This can:
• Crash your database
• Drain your Supabase usage
• Spike costs or open you to attacks

Tools to use:
• Supabase Edge Functions with a rate limiter
• Vercel Middleware
• Basic IP throttling with Next.js middleware
May 28 12 tweets 3 min read
If you’re not using /generate cursor rules, you’re leaving 80% of Cursor’s power on the table.

Here’s how to actually make it code like a real dev: 👇 1/ Why Cursor Rules Matter

Most people think Cursor just writes code for you.

But the truth is: the AI only works well when you train it right.

Cursor Rules are how you do that.

They tell the AI how to behave, what your project is about, and how you like your code written.
May 26 8 tweets 2 min read
Every AI Tool I Use to Build MVPs FAST for My Clients

As someone running an AI-first dev agency, speed is everything.

Here’s my go-to AI stack that has revolutionized how I build MVPs: 1/ @boltdotnew

I now start all my builds inside Bolt.

It lets me:
• Build full UIs with routing and logic
• Sync with Supabase for backend
• Integrate Stripe, FAST

It’s the fastest way to scaffold a functional MVP UI.

Example:
Built a subscription web app with auth, payments, and dashboards in under an hour. It would’ve taken days manually.
May 12 11 tweets 2 min read
How to start vibe coding (the right way)

This is the beginner’s guide I wish I had when I started.

This guide walks you through how to build smart, fast, and clean with Cursor, Bolt, and more.

Bookmark this ↓ 1. Treat AI like a new programming language

You're not writing code. You're giving instructions.

The better your prompt, the better the result.

This is the core skill every dev needs to master now. AI is only as useful as the input you give it
May 10 10 tweets 2 min read
Cursor just got 100x more powerful.

And it wasn’t because I used a bigger model.

It was because I gave it better memory.

Here’s how I fixed it with Context 7 MCP ↓ 1. The core problem: outdated context kills your agent

Every LLM has a training cutoff.

Ask it to install expo and it runs a broken command.

Not because the model is bad. It just doesn’t know recent changes.
May 9 9 tweets 2 min read
If you’re new to Cursor, this will help you get started right.

Here are a few lessons I wish I knew earlier while building MVPs with Cursor, Bolt, and MCP.

Not everything I know, but enough to save you weeks of trial and error ↓ 1. The wrong stack will break your MVP

AI doesn’t code like humans. It replicates patterns it’s seen before.

So if your stack is rare or messy, it’ll hallucinate.

What works for me:
• Next/ React for frontend
• Supabase for backend
• Stripe for payments
• Vercel for deploying

AI flows clean when your stack is AI-native.
May 7 11 tweets 3 min read
Cursor + Supabase + MCP = AI-powered MVP development at its best.

This is how I’m shipping client MVPs faster, cheaper, and smarter with AI handling the backend, database, and migrations.

Let’s break it down. Image 1/ The Problem with Traditional Development

Building MVPs the old way takes too much time:

- Setting up the database
- Writing boilerplate code
- Managing API integrations
- Handling migrations manually

But with Cursor + Supabase + MCP, AI automates most of this, letting you focus on shipping fast.
May 6 12 tweets 4 min read
Top 5 MCP Servers for Vibe Coding

If you’re building with AI and still doing everything manually, this thread will change your workflow forever.

Bookmark this ↓ 1. What’s an MCP?

MCP = Model Context Protocol

Think of MCP like USB-C, but for AI.

It connects your AI agent to tools, databases, docs, and services in one clean setup.

Just like USB-C lets one cable do it all, MCP gives Cursor clean access to what it needs so it can actually work like a real dev.

No more dumping context manually.

This is how AI actually gets useful.
May 2 16 tweets 4 min read
The only UI/UX workflow you need (ChatGPT + UX Pilot)

Design your full MVP UI and design system in under 1 hour using AI.

Here’s the exact workflow ↓ 1/ My updated UI/UX workflow for client MVPs

Clients often want a “design phase” before development.

In the past, this used to take weeks. First build the design system. Then design every screen. Then send for feedback. Then iterate.

Now?

You can do all of this in under an hour using AI.

Here’s how ↓
Apr 30 16 tweets 4 min read
Bookmark this if you’re just getting started with Cursor

We’ve built 18+ MVPs using it and finally cracked the most efficient way to use it without breaking things.

If you’re a beginner, this thread has everything you need to get started and make Cursor work for you ↓ 1/ Plan before you code

A messy plan leads to messy prompts.

Use ChatGPT to generate:
• A simple PRD with your app goals, user flows, and features
• Your database schema and table relationships
• A color palette and typography reference
• Tech stack outline (e.g. Supabase, Stripe, Tailwind, etc.)

Pro tip: Save all of this as .md files inside your Cursor repo for better context. You can also use @CodeGuideDev to speed up this entire planning process.

That way, you and the AI stay aligned on scope from day one.
Apr 27 10 tweets 3 min read
I launched my MVP Development Agency in October

Till now, I’ve built 18 MVPs for clients with AI coding tools.

Here’s everything I learned in last 7 months.

Bookmark this if you want to build faster and smarter with AI: ↓ Image 1/ Why planning is critical for AI coding

AI models from Gemini or Sonnet are great at writing code.

But without context, they hallucinate.

And this hallucinations leads to:

• 100s of Bugs
• Wasted tokens
• Messy codebase

Planning is not optional. This is how you make AI to work like a real dev.
Apr 27 12 tweets 3 min read
Want to steal the UI/UX of top companies and use it in your own app? (Legally?)

Here’s the exact system I use to borrow proven designs and have AI rebuild them into production-ready UI

Mobbin → Figma → Windsurf

From idea to polished frontend in minutes ↓ Image 1/ You don’t need to invent design

You just need to reuse what already works

Products like Uber, Bolt, and Notion have spent millions perfecting their UX

Your job is to study their flow

And use AI to recreate it
Apr 26 10 tweets 2 min read
Vibe coding is not just prompting and hoping for the best.

If you want to build real products with Cursor, you need structure.

Here is the exact loop I use to build production-ready MVPs fast ↓ 1/ Load the full project context

First step is boring but critical.

Load all important files into Cursor.

Even if it takes time, do it.

AI can only help if it knows what is going on.
Apr 26 10 tweets 3 min read
Bolt’s new design AI makes building polished landing pages insanely fast.

But AI can only build what you plan.

Here is my exact system to create beautiful landing pages using @boltdotnew

Bookmark this for your next build ↓ Image 1/ Start with design inspiration

Before opening Bolt, I find strong design references.

Sources I use:
• Dribbble
• Behance
• Best SaaS landing pages

Focus on:
• Clean typography and spacing
• Strong CTAs
• Smooth animations and micro-interactions

Good design starts with knowing what works.Image
Apr 25 11 tweets 2 min read
UX Pilot + Bolt + Cursor

The 3 tools that changed how I build MVPs forever.

Here’s the exact system I wish I had when I started.

Bookmark this ↓ Image 1/ Plan using ChatGPT + CodeGuide

Before we build, we plan, fast.

My stack:
- ChatGPT to brainstorm features
- @CodeGuideDev to auto-generate the PRD + technical docs

This gives us:
- A clear feature list
- A lean scope
- Zero ambiguity
Apr 20 11 tweets 4 min read
Cursor is literally the best AI coding tool.

But most AI projects break because of 3 core issues:

- AI hallucinations
- Loop of errors
- Context awareness

Here’s the system I use to fix all 3.

It’s called the Context Boundary Method ↓ Image 1/ Context boundary = Knowledge base for AI

This is the coding doc. system I follow for every build:

- PRD
- App Flow Doc
- Tech Stack Doc
- Frontend Guidelines
- Backend Structure
- Implementation Plan

These docs act like a knowledge base for your AI dev. Without these, it’s chaos.Image
Apr 19 16 tweets 4 min read
The only UI/UX workflow you need for MVPs (ChatGPT + UX Pilot)

Design system + full UI in one flow

Clean, client-ready, fast.

Here’s exactly how I do it ↓ 🎥 Full video walkthrough (9 min):

Watch here →
Apr 17 8 tweets 2 min read
Everyone’s building with Cursor. Almost no one’s doing it right.

It’s not bad prompts that kill MVPs.

It’s the lack of a system.

Here are 7 hard lessons from building 17+ MVPs with Bolt, Cursor, and Supabase.

Bookmark this if you want to ship clean, not just fast. 1/ The wrong stack will break your MVP

AI doesn’t code like humans. It replicates patterns it’s seen before.

So if your stack is rare or messy, it’ll hallucinate.

What works for me:
- Next/ React for frontend
- Supabase for backend
- Stripe for payments
- Vercel for deploying

AI flows clean when your stack is AI-native.
Apr 16 11 tweets 3 min read
How to Set Up Cursor the Right Way

Cursor Rules are outdated. Project Rules is the correct way now.

Here’s why it matters and how to set it up properly: Image 1. Why .cursorrules wasn’t enough

Cursor originally used a single .cursorrules file at the root of a project, but this approach had serious problems:

Limited control
→ One rules file applied to the entire project, even when irrelevant.

Context overload
→ Cursor had to process every rule at once, often leading to ignored or misunderstood instructions.

Lack of scalability
→ As projects grew, .cursorrules became bloated and hard to manage.

Inconsistent AI responses
→ The AI often skipped or misapplied rules because the file lacked structure and precision.

Instead of improving code, .cursorrules often caused unpredictable results.
Apr 15 11 tweets 3 min read
You can now automate your browser from inside Cursor or Windsurf.

No more copy-pasting logs or screenshots.

I recorded a full video showing how to set up Browser MCP and use it to debug like a pro.

Watch it here ↓ 📺 Watch the full step-by-step video here: