Context Engineering
Context engineering is the discipline of deciding what a language model should know at inference time, including the source data, structure, and ordering of its working memory.
Context engineering is the successor to prompt engineering. Prompt engineering asked how to phrase the question. Context engineering asks what should be in the model's working memory when it reads the question. The shift matters because modern language models are less bottlenecked by prompt wording and more bottlenecked by the quality of the data they have access to.
The practice spans several layers. Selecting which documents enter the window. Structuring those documents into retrievable units. Defining relationships between entities (accounts, people, calls, objections). Ordering material so the most relevant content is closest to the question. Pruning redundant or low-signal material so the model is not drowning in noise.
Context engineering is now a first-class job function inside AI-native teams. It sits between data engineering and applied ML. The output is not a better prompt. The output is a better context layer that any prompt can draw from.
The Amdahl view
Context engineering is the new SEO. Every B2B company running AI in production will discover that model quality matters less than context quality. The winners invested early in structured context layers. The losers kept shipping prompt tweaks and wondering why their agents stayed mediocre. Amdahl's entire thesis rests on this: the team with the best customer context layer wins the GTM AI race, regardless of which model sits on top.
Frequently asked
Related terms
- AI InfrastructureContext WindowA context window is the maximum number of tokens a language model can process in a single request, covering both the input prompt and the generated output.
- AI InfrastructureContext BloatContext bloat is the degradation in model output that happens when too much raw or irrelevant data is stuffed into the context window, drowning the signal in noise.
- AI InfrastructureOntologyAn ontology is a structured map of the concepts, entities, and relationships in a domain, used to give a language model a consistent vocabulary and schema for reasoning about source data.
- AI InfrastructureRetrieval Augmented Generation (RAG)Retrieval Augmented Generation (RAG) is a pattern where a system retrieves relevant documents from an external source, injects them into the model's prompt, and has the model answer from the retrieved material rather than from parametric memory.
- AI InfrastructurePrompt engineeringPrompt engineering is the practice of phrasing requests to a language model to get better outputs.
See customer intelligence running on your own customer conversations.