Good context leads to good code: How we built an AI-Native Eng Culture
1–4 of 4 posts
Re: Good context leads to good code: How we built an AI-Native Eng Culture
#2Author here. Happy to answer any questions you have.
I know the HackerNews crowd is anti-AI in the workforce overall, but I wanted to share a different approach which is optimizing for collaboration between humans and AI. This maps into certain practical things you can do, including things like how you structure your repo.
Re: Good context leads to good code: How we built an AI-Native Eng Culture
#3Thanks 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.
Re: Good context leads to good code: How we built an AI-Native Eng Culture
#4Thanks 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…
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.