# Context Engineering
## What is the Context?
![[context.png]]
from [The New Skill in AI is Not Prompting, It's Context Engineering](https://www.philschmid.de/context-engineering)
Context:
- Instructions / System Prompt
- User Prompt
- State / History (short-term Memory)
- Long-Term Memory
- Retrieved Information (RAG)
- Available Tools
- Structured Output
Context Exgineering:
- A System, Not a String
- Dynamic
- About the right information, tools at the right time
- Where the format matters
> It’s a cross-functional challenge that involves understanding your business use case, defining your outputs, and structuring all the necessary information so that an LLM can “accomplish the task.
## The rise of "context engineering"
[The rise of "context engineering"](https://blog.langchain.com/the-rise-of-context-engineering/)
> Context engineering is building dynamic systems to provide the right information and tools in the right format such that the LLM can plausibly accomplish the task.


- Context engineering is a system
- prompt engin
-
Some basic examples of good context engineering include:
- Tool use
- Short term memory
- Long term memory
- Prompt Engineering
- Retrieval
## References
- [手触り感のあるContext Engineering - LayerX エンジニアブログ](https://tech.layerx.co.jp/entry/2025/09/09/200738)