<p><strong>Follow along with the project by going here: </strong><a href="https://www.parsity.io/5-day-ai-advisory-board?cid=ec617c6d-dc85-4af5-aaf5-b77d6f2cec99" target="_blank" rel="noopener noreferrer nofollow"><em><strong>https://www.parsity.io/5-day-ai-advisory-board</strong></em></a></p><p>In this episode, I walk you through a side project that, if you actually build it, will put you ahead of roughly 90–95% of software developers right now.</p><p>Most developers are using AI tools. Very few are actually building with them.</p><p>So instead of talking about it, we build something real.</p><p>The project is an AI advisory board — a system where you can ask questions like:</p><ul><li><p>What would Theo Browne say about Node?</p></li><li><p>What would ThePrimeagen say about Vim?</p></li><li><p>What would Alex Hormozi say about sales?</p></li><li><p>What would I say about testing?</p></li></ul><p>And instead of generic AI responses, you get answers grounded in real transcripts and real opinions.</p><p>We go step-by-step through:</p><ul><li><p>Calling an LLM programmatically (Gemini API)</p></li><li><p>Setting up a backend route to handle requests</p></li><li><p>Adding system prompts and guardrails</p></li><li><p>Building a simple knowledge base</p></li><li><p>Pulling in real YouTube transcripts</p></li><li><p>Injecting data into the model at the right time (naive RAG)</p></li></ul><p>This is the kind of project that forces you out of “AI user” mode and into actually building AI-powered products.</p>