Comment by zorrolovsky

Thanks for the article, very insightful! I’m researching dev + AI workflows to build something to improve them. In your view, what’s the right granularity for storing and reusing context: A long file with lots of context per project? A small file with small bits of context per task? something in-between? And what type of context is useful for most workflows: stylistic preferences, intent, tech stack? Curious to know where you think context boundaries should actually sit to maximize usefulness without noise.