I've been building a personal AI assistant for my developer blog – you know, one of those floating chat widgets that answers questions about my projects. The idea was simple: feed in my content, hook it up to an AI API, and let visitors chat with it. But my first implementation was a disaster. Visitors would type a question, see the spinner spin for ten seconds, and then get the entire response dumped at once. It felt like using dial-up. The problem wasn't the AI itself; it was how I was consuming the stream of tokens. Here's the story of how I went from clunky polling to the elegant world of Server-Sent Events (SSE).
The Initial Approach (and its failure)
Like many devs, I started with the most obvious solution: plain fetch. I sent a POST request to the AI endpoint with the user's message, and waited for the full response as JSON.
// The naive way
async function askAI(userMessage) {
