Agents
Context Engineering
Context engineering decides what occupies a model's context window at every step, and in what order.
That includes tool definitions, retrieved content, conversation history, and the task itself, well beyond the system prompt.
It treats the window as a fixed, competed-for resource: one slice's tokens are tokens unavailable to another.
The allocation must be a deliberate decision, not whatever is left over once everything else is assembled.
Prompt engineering is one input to it, not the whole discipline.
← Back to the full glossaryRelated terms
Context Window The context window is the maximum text, measured in tokens, a model can consider at once. Context Rot Context rot is a model's declining ability to use context well as it fills with stale material. Compaction Compaction summarizes or drops older context to make room in a filling window. Context Isolation Context isolation gives each delegated unit of work its own scoped context window.
More in Agents
Agent (Agentic AI) An agent is an LLM given a loop, memory, and tools it can call. Tool Calling Tool calling lets a model request a structured action instead of only generating text. Model Context Protocol (MCP) MCP is an open standard for connecting LLM applications to tools and data sources. Tool Contract A tool contract is the schema a tool exposes to a model.