We Traced One Query Through Perplexity’s Entire Stack in Cohort – Here’s What Actually Happens in 3 Seconds

<p>It was about 90 minutes into the session. We’d just finished building a RAG pipeline from scratch in Python the kind where you stare at FAISS indices and embeddings and wonder if you’ll ever actually deploy this in prod.</p> <p>The instructor stopped scrolling through code and looked up.</p> <p>“Alright,” he said. “Let’s stop pretending we’re building search. Let’s trace one live query through Perplexity. See what <em>actually</em> happens in the 3 seconds between you hitting enter and reading the answer.”</p> <p>The room got quiet. Someone typed the question.</p> <h2> First, the Simple RAG Pattern (So We Have a Baseline) </h2> <p>If you’ve built any RAG system, you know the dance:</p> <ol> <li> <strong>Ingest</strong> — chunk documents, embed them, store in a vector DB </li> <li> <stro