What is Context Engineering? The discipline of designing what context an LLM sees on each call (retrieved chunks, tool outputs, agent memory, system rules, examples) to produce reliable outputs. Context Engineering explained Term emerging in 2026 as the successor to prompt engineering. Prompt engineering tuned wording; context engineering tunes what goes into the context window: chunk format, retrieval order, memory compression, tool-output trimming, few-shot example selection. More important than prompt wording for production agents with long-running state. How Groovy Web uses Context Engineering Our agent team treats context engineering as the primary design lever. We layout context windows like a database schema: deterministic blocks, source-tagged, and length-budgeted. Explore our AI-First Product Engineering service → Context Engineering: common questions What is Context Engineering? The discipline of designing what context an LLM sees on each call (retrieved chunks, tool outputs, agent memory, system rules, examples) to produce reliable outputs. What should I know about Context Engineering? Term emerging in 2026 as the successor to prompt engineering. Prompt engineering tuned wording; context engineering tunes what goes into the context window: chunk format, retrieval order, memory compression, tool-output trimming, few-shot example selection. How does Groovy Web use Context Engineering? Our agent team treats context engineering as the primary design lever. We layout context windows like a database schema: deterministic blocks, source-tagged, and length-budgeted. Which terms are related to Context Engineering? Context Engineering is closely related to Prompt Engineering, Context Window, Retrieval-Augmented Generation (RAG) and AI Agent. Related terms Prompt Engineering Prompt engineering is the practice of designing and testing the instructions, examples and context given to a language model so it produces accurate, consistent and useful output. Context Window The maximum amount of text that a language model can consider when processing input, including both the user's prompt and the model's previous responses in a conversation. Retrieval-Augmented Generation (RAG) Retrieval-Augmented Generation (RAG) is an AI architecture that combines a language model with a search system to answer questions using your own data. AI Agent An AI agent is a software system that uses a language model to decide what to do next, calls tools such as APIs and databases, and works toward a goal with limited human supervision. Function Calling (AI) A capability where language models can request execution of specific functions or APIs by outputting structured specifications, enabling precise tool use and integrations. Tool Use (AI) The ability of AI agents to access and use external tools and systems to accomplish tasks, extending their capabilities beyond text generation to interact with the real world. ← More in Prompting & Model Control · All 107 glossary terms