The foundational explainers — the “what is X” pieces that define how modern AI agents are actually built. Start here, then follow the comparisons into the choices.
Prompt engineering optimized a string. Context engineering manages a finite, decaying budget — because the context window is not a bucket you fill, it is attention that rots as it fills.
Prompt engineering tuned the words. Context engineering managed the window. The discipline that decides whether an agent ships is the deterministic code around the model — and it is older than it looks.
The agent libraries that mattered in 2024 told the model what to do next. The ones that matter now assume it already knows — and sell you the restraints and the trace instead.
A million-token window is not a million usable tokens. Models degrade non-uniformly as input grows — sometimes performing worse than with no documents at all. The lever for agents isn't a bigger window; it's a cleaner one.
A model that solves a task 61% of the time can be reliable only 25% of the time. The gap between those two numbers is where production agents go to die.
A deep agent is not a new model or a framework breakthrough — it's four cheap, known ingredients that let a plain tool-calling loop survive a long task instead of drifting.