The complete beginner’s guide to coding with AI: from PRD to generating your very first lines of code
How I AI5 Marras 2025

The complete beginner’s guide to coding with AI: from PRD to generating your very first lines of code

This episode is for complete beginners. I walk you through how to build your very first coding project using AI tools—even if you’ve never written a line of code. Together, we’ll create a personal project hub that automatically generates documentation and lets you build interactive prototypes. I’ll show you the process step by step—from setting up a repository, to creating AI agents that help with specific tasks, to deploying a functional web app locally.


What you’ll learn:

  1. How to set up a simple Next.js application from scratch using Cursor’s AI agent capabilities

  2. My workflow for creating AI agents that generate consistent documentation (like PRDs in Markdown format)

  3. How to build and display clickable prototypes without worrying about complex backend functionality

  4. The basics of using GitHub to track changes and manage your code repository as a non-technical person

  5. Why starting with a personal project hub is the best way to ease into AI-assisted coding

  6. My favorite practical tips for iterating on designs and functionality using AI tools—without needing deep technical expertise

Brought to you by:

ChatPRD—An AI copilot for PMs and their teams

In this episode, we cover:

(00:00) Introduction

(05:11) Starting with a requirements document in ChatPRD

(08:22) Attempting to use v0 for initial prototyping

(15:02) Pivoting to Cursor for initial prototyping

(20:20) Running the app locally and reviewing the initial version

(24:07) Setting up GitHub for version control

(27:09) Creating an AI agent for writing PRDs

(31:04) Using the agent to create a sample PRD

(35:00) Building a prototype based on the PRD

(37:00) Testing and improving the prototype

(40:00) Adding documentation and improving the design

(43:20) Recap of the complete workflow

Tools referenced:

• Cursor: https://cursor.com/

• ChatPRD: https://www.chatprd.ai/

• v0: https://v0.dev/

• GitHub Desktop: https://desktop.github.com/

• Next.js: https://nextjs.org/

• Tailwind CSS: https://tailwindcss.com/

Other references:

• Lovable: https://lovable.ai/

• Bolt: https://bolt.new/

• Claude Code: https://www.claude.com/product/claude-code

• Markdown: https://www.markdownguide.org/

• GitHub: https://github.com/

Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.

Tämä jakso on lisätty Podme-palveluun avoimen RSS-syötteen kautta eikä se ole Podmen omaa tuotantoa. Siksi jakso saattaa sisältää mainontaa.

Jaksot(93)

This solo builder runs 24/7 local AI on his own hardware | Alex Finn

This solo builder runs 24/7 local AI on his own hardware | Alex Finn

Alex Finn is an AI builder, YouTuber, and the creator of Vibe Code Academy, a community for people learning to build with AI tools. He runs one of the most ambitious local AI setups I’ve come across: ...

13 Heinä 35min

GPT-5.6 Sol vs. Claude Fable: Why OpenAI’s new model crushes my benchmark

GPT-5.6 Sol vs. Claude Fable: Why OpenAI’s new model crushes my benchmark

GPT-5.6 Sol is back, and I ran it through my full How I AI vibe benchmark against GPT-5.6 Terra, Luna, Claude Fable 5, and Sonnet 5 across five categories: PRDs, prototypes, wireframes, debugging, and...

9 Heinä 36min

What a harness is and how to build one with Claude Agent SDK

What a harness is and how to build one with Claude Agent SDK

Everybody is saying, “It’s not the model, it’s the harness,” but almost nobody stops to explain what a harness actually is. So I did. I built one live on the show: a Sentry bug-debugging harness for m...

8 Heinä 24min

How I run autonomous coding agents from my phone with OpenAI Symphony + Linear | Alessio Fanelli (Kernel Labs)

How I run autonomous coding agents from my phone with OpenAI Symphony + Linear | Alessio Fanelli (Kernel Labs)

Alessio Fanelli, founder of Kernel Labs and co-host of Latent Space podcast, walks us through two very different AI workflows: (1) a fully autonomous coding setup using OpenAI Symphony + Linear, where...

6 Heinä 35min

Sonnet 5 review: I ran 64 generations to find out if it's worth it

Sonnet 5 review: I ran 64 generations to find out if it's worth it

I’ve been testing every major frontier model release since the start of the year, and when Anthropic dropped Sonnet 5, I wanted more than a vibe check. I got tired of one-off tests I couldn’t repeat o...

30 Kesä 25min

No Figma. No Jira. No docs. How Gusto built a new product line with Claude Code | Eddie Kim (CTO)

No Figma. No Jira. No docs. How Gusto built a new product line with Claude Code | Eddie Kim (CTO)

Eddie Kim is the co-founder and CTO of the payroll and HR platform Gusto, which just crossed $1 billion in revenue and serves more than 500,000 small businesses. Recently he did something most CTOs do...

29 Kesä 51min

GLM 5.2: why I’m replacing Opus in Claude Code with this new model

GLM 5.2: why I’m replacing Opus in Claude Code with this new model

I put GLM 5.2, the open-weight coding model from Z.AI, through four real tasks inside my actual codebase: a codebase architecture audit, a UI redesign, and a 45-minute autonomous bug-hunting session p...

24 Kesä 27min

How Claude Mythos found a 15-year-old bug in Mozilla Firefox | Brian Grinstead

How Claude Mythos found a 15-year-old bug in Mozilla Firefox | Brian Grinstead

Brian Grinstead is a distinguished engineer at Mozilla, where he’s worked on Firefox and the web platform since 2013 (he joined to help launch Firefox DevTools). Recently he and his team pointed an ag...

22 Kesä 48min