[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.

[waleedk]

I think of context as something dynamic that you build as you need it. Part of getting something like Claude Code to the point where it can produce great results is selecting different parts to emphasize.

Intent is important, but so are goals, and I see the context as something that you collaboratively build with you filling in the gaps in the context the agent doesn't see.

It's almost like you repetitively ask the question: based on how the agent is behaving, what is the context I should add to help it perform better? If it's screwing up how to use an API, then I should ask it to read the docs and create a guide for itself or provide it with an llms.txt.