Navigate Select ESC Close

Be a 10x Vibe Coder (Claude Code + Cursor + MCP)

2025-12-01 People & Blogs
177.0k
4.5k
159
Greg Isenberg
Greg Isenberg
674.0k subscribers

Unlock all features

FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.

Description

The Blueprint to build profitable apps: https://startup-ideas-pod.link/app-blueprint On this episode I sit down with indie app builder and designer Chris Raroque to walk through his real AI coding workflow. Chris explains how he ships a portfolio of productivity apps doing thousands in MRR by pairing Claude Code and Cursor instead of picking just one tool. He live-demos “vibe coding” an iOS animation, then compares how Claude Code and Cursor’s plan mode tackle the same task. The episode closes with concrete tips on plan mode, MCP servers, AI code review, dictation, and deep research so solo devs can build bigger apps than they could alone. *Timestamps* 00:00 – Intro 03:04 – Which Tools & Models to Use 09:16 – Thoughts on the Vibe Coding Mobile App Landscape 11:14 – Live demo: prompting Claude Code to build an iOS “AI searching” animation 18:07 – Live demo: prompting Cursor with same task 21:02 – Chris’s Best Tips for Vibe Coders *Key Points* * You don’t have to pick one IDE copilot: Chris actively switches between Claude Code and Cursor because they have different strengths. * For very complex bug-hunting, he prefers Cursor with plan mode; for big-picture app architecture, he leans on Claude Code with Opus. * Non-developers should start on higher-level “vibe coding” platforms like Create Anything for mobile apps before graduating to Claude/Cursor. * Plan mode plus detailed, spoken prompts dramatically improves code quality, especially for UI and animation work. * MCP servers and AI code review bots let solo developers safely set up infra, enforce security, and catch bugs they’d otherwise miss. * Claude’s deep research is a powerful way to choose the right patterns and libraries before handing implementation back to Claude Code or Cursor. Summaries 1. Why Use Both Claude Code and Cursor Instead of committing to a single tool, Chris runs Cursor as his main editor and terminal, with Claude Code running in a side panel, and swaps based on the task. He uses Claude Code with Opus 4.1 for extremely complex or architectural work until he hits usage limits, then relies on Cursor plan mode with GPT-5.1 high for planning and Sonnet for execution. He notes that Claude feels slightly better at UI work, while Cursor’s plan mode shines on gnarly bugs and multi-step changes. 2. Claude Code vs Cursor Plan Mode To compare tools, Chris undoes the Claude changes and asks Cursor plan mode (with Sonnet for execution) to implement the same animation. Cursor generates a detailed plan, asks clarifying questions about replay behavior and placeholders, then edits the code. On first try, Chris and Greg agree Cursor’s result is slightly smoother than Claude’s initial attempt, even though both use the same Sonnet model under the hood. Chris uses this to illustrate how plan mode alone can dramatically change outcomes. 3. Core Workflow Tips: Plan Mode, UltraThink, Background Tasks, MCP Chris’ first big tip is to enable plan mode for almost every action in Cursor and Claude Code so the model can think through steps before touching the codebase. In Claude Code, he also uses the “UltraThink” keyword on most complex prompts to force deeper reasoning, and runs servers as background tasks so Claude can read logs directly during debugging. He then layers MCP servers like Context 7 (for up-to-date, compressed docs) and Supabase/Firebase/AWS MCP (for schema, security rules, and infra setup), arguing that AI often configures security better than rushed humans—though he’s more cautious in production. 4. Security and Shipping For solo developers without teammates to review code, Chris relies on AI code review tools like BugBot and Cursor’s PR reviewer to scan for security issues and bugs before merge. He dictates most prompts via Whisperflow so he can give long, detailed instructions without slowing down, and he uses Claude’s deep research in the chat app to explore “best practice” patterns before implementing anything. The combination—plan mode, MCP, AI reviewers, dictation, and deep research—lets him ship sophisticated apps quickly while still sleeping at night. The #1 tool to find startup ideas/trends - https://www.ideabrowser.com/ LCA helps Fortune 500s and fast-growing startups build their future - from Warner Music to Fortnite to Dropbox. We turn 'what if' into reality with AI, apps, and next-gen products https://latecheckout.agency/ The Vibe Marketer - Resources for people into vibe marketing/marketing with AI: thevibemarketer.com Startup Empire - get your free builders toolkit to build cashflowing business - https://startup-ideas-pod.link/startup-empire-toolkit Become a member - https://startup-ideas-pod.link/startup-empire FIND ME ON SOCIAL X/Twitter: https://twitter.com/gregisenberg Instagram: https://instagram.com/gregisenberg/ LinkedIn: https://www.linkedin.com/in/gisenberg/ FIND CHRIS ON SOCIAL Youtube: https://www.youtube.com/@raroque X/Twitter: https://x.com/raroque Instagram: https://www.instagram.com/chris.raroque/

Top Comments (10)

@MrRichMartin 2025-12-01

Using a reasoning model (GPT-5.1) specifically for the Plan phase and a coding model (Opus) for the Build phase makes so much sense. It’s like having a separate architect and engineer.

86 4 replies
@raroque 2025-12-01

Thanks for having me on again Greg 🙏 hope this was helpful for anyone building with AI and happy to answer any questions!

77 9 replies
@GregIsenberg 2025-12-01

hi if you're seeing this and not hitting the like/comment section right now... i thought we were friends!

51 5 replies
@modlife 2025-12-07

Rather than using “ultrathink”, I’ve found that using “deeply analyze the logic that arrives at this problem, strategize and then debug and repair the problem.” - 99.9% of the time almost any model can solve the most difficult problems.

12
@gargeyabelial 2025-12-01

I've binge watched many of your videos today. Best decision I've made after many days. Thank you!

12
@tedbrunker 2025-12-01

Love how Chris breaks down using both Claude Code and Cursor strategically - plan mode + MCP servers is a game changer for shipping faster without sacrificing code quality!

8
@sbmh2001 2025-12-19

i switched to claude-4.5-opus-high-thinking on Cursor, and that chewed up my monthly credit in one day!! Then i looked into the pricing for different models and this is what i found on my account: - Claude-4.5-Sonnet-Thinking: $1.73 / 1M tokens (Highest) - Claude-4.5-Opus-High-Thinking: $1.07 / 1M tokens - GPT-5.1: $0.99 / 1M tokens - GPT-5.2-XHigh: $0.96 / 1M tokens - GPT-5.2: $0.68 / 1M tokens - GPT-5: $0.57 / 1M tokens - GPT-5.2-High: $0.52 / 1M tokens (Lowest) hope this helps

6
@speang 2025-12-06

Love this video. Out of all vibe coding tutorials, this one is my favorite so far. Thank you for doing this guys.

3
@mishftw 2025-12-01

Great video. I started experimenting with Claude Code when it first came out, and it's become an integral part of my workflow. I'd say applying software engineering principles on top of these tools is the best way to get optimal output.

3
@stevenmunoz26 2025-12-24

Amazing, that dictation tip with Wispr Flow, I tried and I just have to say, it’s truly incredible! I really appreciate these wonderful tutorials, they're so helpful and inspiring. They really assist us in learning how to vibe code more effectively, launch products to the market, and move faster using all the tools available to us. Thanks so much for sharing these!

0

Unlock the Data Inside
Turn Videos into Knowledge

  • Get FREE 10/day: transcripts, summaries, chats
  • Chat with videos, export text & PDF
  • $1 free API credit for RAG, chatbots & research

Free forever plan • All features unlocked

App screenshot