Topic
6 articles on Context Engineering, written from production systems rather than documentation.
Long sessions fill the window and something has to go. What you drop, and what you replace it with, decides whether the system degrades or forgets.
Prompt engineering asks what to say to the model. Context engineering asks what should be in front of it at all, which is the harder half.
Examples are the fastest way to fix a format problem and a slow way to fix a reasoning one. Adding more has a ceiling that arrives earlier than expected.
Conversation history, retrieved knowledge and learned state all get called memory. They have different lifetimes, and conflating them is why agents drift.
Caching the stable prefix of a prompt cuts cost and time to first token substantially. It only works if the stable part is genuinely first.
A million-token window suggests you can stop being selective about context. Attention is uneven across a long window, and cost scales with what you send.
Whether it needs designing from scratch or rescuing from its own success, tell me what you’re building and I’ll tell you how I’d architect it.
Open to remote and hybrid work worldwide