What is the difference between prompt, context, and memory engineering?

1. Prompt engineering: the wording

This is the instruction you hand the model. The phrasing, the examples, the format you ask for. It is the most visible layer and the one everyone started with, which is exactly why it is the least differentiated today. The models got good enough that clever wording stopped being a moat. Useful, still necessary, but it is table stakes now.

2. Context engineering: the workspace

This is everything you load into the model’s context window for one task: the relevant documents, the recent history, the tools it can call. Aishwarya Srinivasan describes the shift from prompt to context engineering as the moment you stop treating the model as a magic box and start treating the thing around it as a software system. Jerry Liu goes further and calls context quality the durable moat as the models themselves commoditize. Compacting or summarizing what is in that window to make it fit is still context engineering.

3. Memory engineering: the persistence

This is what survives after the task ends. Richmond Alake draws the cleanest line on it: if you are summarizing the context window to make it fit, that is context engineering. The moment you move information out to an external store and give the agent a way to retrieve it later by ID, you are doing memory engineering. Now you own retrieval speed, decay, organization, and storage. It is its own discipline, sitting at the intersection of data engineering and agent engineering.

The one-line test

Shrinking what is in the window right now? Context engineering. Saving something to pull back next time? Memory engineering. Writing the instruction itself? Prompt engineering.

Why it matters

As frontier models converge, the work moves down this list. Prompt wording matters less every quarter. What you feed the model, and what it remembers, is the part you actually control. Richmond’s framing: memory is the one layer where a single developer can still outbuild the big labs.