# 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. ![tobi lutke on X: "I really like the term “context engineering” over prompt engineering. It describes the core skill better: the art of providing all the context for the task to be plausibly solvable by the LLM." / X](https://x.com/tobi/status/1935533422589399127) ![Ankur Goyal on X: "As models get more powerful, i find myself focusing more effort on context engineering, which is the task of bringing the right information (in the right format) to the LLM. Context engineering is hard because it is pervasive. You need to engineer every layer of the stack to" / X](https://x.com/ankrgyl/status/1913766591910842619) - 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)