Jorge Laurel
Writing

Part 1: The Spark - When Vision Meets Digital Reality

Jorge Laurel · ·4 min read

Day 1 of a 5-part series: From Idea to Launch

Have you ever had one of those moments where you’re staring at your weekly routine and think, “There’s got to be a better way to do this”? That’s exactly what happened to me with my Friday Wrap Up newsletter.

For months, I’d been manually crafting my cybersecurity newsletters, juggling Google Docs, Feedly, Zapier, and Make. Although I had semi-perfected my process I wanted to find a way to expand beyond LinkedIn and Substack and see what potentials were possible outisde of these two platforms. As someone who preaches about efficiency in cybersecurity operations, I was ironically running my own newsletter like it was 2010.

Then it hit me: what if I could build something custom? Not just another generic newsletter platform, but something designed specifically for cybersecurity professionals who need intelligent content curation, beautiful presentation, and some pretty good security that was built in from the start aka Secure-by-Design. Yeah, I know, there are already sites that do this. But I wanted to create my own and learn about this “vibe coding” thing.

The problem? I’m not a developer. Sure, I can script my way out of a paper bag and understand technical concepts, but building a full-stack web application? That’s a different beast entirely.

Enter my new collaboration partner: AI.

The “Aha!” Moment

The lightbulb went off several weeks ago when for some strange reason I started seeing all sorts of “vibe coding” content popping up in my social media streams. It’s been around for a while but I was just now getting introduced to it. And I was curious. What if I could create a platform that would:

  • Automatically aggregate cybersecurity news from trusted sources

  • Use AI to categorize and analyze threat intelligence

  • Present everything in a mobile-friendly, professional format

  • Handle subscriptions and user management seamlessly for the Friday Wrap Up

  • Do it all with enterprise-grade security from day one

The vision was clear. The execution? That’s where things got interesting.

Setting the Foundation

Rather than diving straight into code, I decided to start with what every good project needs: a solid Product Requirements Document (PRD).

Here’s where the AI collaboration magic began to shine. Instead of struggling alone with requirements gathering, I had a thought partner who could:

  • Challenge assumptions in real-time

  • Suggest technical implementations for business requirements

  • Help balance ambition with practical constraints

  • Iterate on ideas at the speed of conversation

My initial PRD started ambitious—maybe too ambitious. We talked about complex user tiers, real-time collaboration features, and a dozen other “wouldn’t it be cool if” features. But through rapid back-and-forth, the AI Agent and I refined the scope to focus on what really mattered:

Core Features That Made the Cut:

  • AI-powered content analysis using OpenAI’s GPT-4o

  • Automated RSS feed processing from major cybersecurity sources

  • Mobile-first responsive design with clean, Apple-inspired aesthetics

  • Firebase authentication for secure admin access

  • Searchable archive system for historical content

  • Enterprise-grade security built from the ground up

Features I Refined Away:

  • Complex user subscription tiers (simplified to Substack integration)

  • Real-time collaboration features (focused on content creation instead)

  • Multi-language support (prioritized English-first approach)

The PRD became my north star—a living document that guided every technical decision that followed.

The Human-AI Dynamic

Here’s what I learned early on: AI doesn’t replace human judgment; it amplifies it. My role was to provide domain expertise, user experience insights, and strategic direction. The AI Agent’s role was rapid technical implementation, security best practices, and the ability to iterate at lightning speed.

This wasn’t about me becoming a programmer overnight. It was about combining human creativity and domain knowledge with AI’s technical execution capabilities to build something neither of us could have created alone.

Three Early Lessons

1. Start with the Problem, Not the Tech Stack It’s tempting to jump straight into “Should I use React or Vue (like I really knew what they were)?” but the real magic happened when I focused first on user problems and let technical solutions emerge naturally.

2. Security Can’t Be an Afterthought In cybersecurity, you shouldn’t think about security later. I made the decision early that every feature would be built with security considerations from the ground up.

3. AI Moves Fast—Have Clear Direction an AI Agent can implement features at an incredible speed, but that speed is only valuable when you know where you’re going. The PRD became essential for keeping my rapid iterations focused.

What’s Coming Next

Tomorrow in Part 2: “Code, Coffee, and Course Corrections”, I’ll dive into the technical nitty-gritty: how I went from PRD to production-ready code in just seven days. I’ll explore the architecture decisions, the features that made the cut (and the ones that didn’t), and the iterative development process that made it all possible.

Spoiler alert: there were some surprising pivots along the way, and not everything went according to plan. But that’s where the real learning happened.