Product leader, 2x founder, and 4x patent holder exploring AI by building Burrow - a semantic search platform using Replit/Claude Opus + OpenAI embeddings and personalization for hyper-local discovery. MS Engineering (Georgia Tech), BS Physics (RPI).
AI marketing
Building a full, respectable marketing site - copy, media, and SEO - took only four hours with AI tools. I leveraged Replit's product knowledge for the core build, then fine-tuned images & video with chatGPT & Pika. Box checked, site live, and a huge "Good job!" to my AI helpers!
AI
We've found the 'Vibe Coding Limit' for AI. Stunning productivity hits a wall where human engineering must step in to prevent 'Spaghetti Code.' AI agents miss best practices (SSOT, KISS, DRY) & struggle with context, showing human review is critical for code quality.
AI
Our multi-model AI code audit (Claude Opus 5.5 & GPT-5.2) improved things, but a human engineer still found basic, overlooked issues. The Spaghetti Code Limit (SCL) still lingers on the horizon, proving AI is a powerful tool, but not a replacement for a human expert.
Porduct Requirements Documents
Vibe coding is fast, but it hits the 'Spaghetti Code Limit.' To build a real product, PRDs (Product Requirements Documents) and best practices are still essential for scaling beyond the brink. Don't let the magic run out.
AI hype
Six months of "weekend AI warrioring" led to the launch of our MVP, Burrow. We're now focused on hardening the product and validating with real user input. The journey proves AI is impressive, but it must include proper product development process.
AI Agents
Level up your code quality with a 3-LLM review process! Learn the 6-step workflow using ChatGPT, Claude Opus (via Replit), and Gemini to tap into the collective intelligence of current state-of-the-art AI. A tiny team's secret weapon for better code, faster.
AI Agents
Treat your codebase like your house: give it a deep clean with a single-prompt, AI-driven refactoring! I use the most advanced model (Opus 4.5) to iteratively refactor, clean, consolidate, simplify, and harden my code, maintaining a solid foundation. It's well worth the cost for the best quality.
AI Agents
Keeping your agents' knowledge base pristine isn't just about tidiness - it’s about speed and preventing confusion. I use a clear file structure (like an agents/ folder) and a specific cleanup prompt to maintain a concise single source of truth, ultimately making it easier to keep the code clean.
AI Agents
A significant benefit of AI assistive agents is documenting things you learn as you develop, preventing "context drift." They turn troubleshooting into permanent, accessible best practices. Stop losing context; start preserving history's lessons alongside your code.
AI Product Development
What if your development project had an AI product team? I used expertise-specific "agents" to enforce best practices and add rigor to my project on Replit, creating guardrails tailored to my needs. These are currently powerful reference libraries, anticipating real-time monitoring in the future.
Vibe Coding
Scaffolding is a key to transforming an AI project into a reliable, goal-directed product. Learn how our team revamped the "Burrow" project with engineering rigor, focused prompts, and a methodical approach, moving away from 'glamour apps' to proper product development at a much faster pace.
Vibe Coding
The key principles from Agile teams that AI accelerates but doesn't replace. Focus on incremental development, rigorous testing, and solid standards for architecture, security, and quality. Embrace the "boring" stuff - it's what prevents disaster and, with AI, can actually be a lot of fun!