ModelRefs / Context Stuffing — AI Glossary
Context Stuffing — AI Glossary
Filling the context window with relevant reference material so the model can answer without retrieval or parametric memory.
Overview
Context stuffing passes full documents, API specs, or codebases directly in the prompt. With models at 128K–1M context, entire repositories or policy documents fit in a single request. Trade-off: cost scales with context length; 'lost-in-the-middle' degradation affects long contexts. Often preferred over RAG for simplicity when context fits.
Reference details
| Topic | prompting |
|---|---|
| Also known as | context filling, long-context prompting |
| Last reviewed | 2026-06-24 |
Related terms
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Context Stuffing — AI Glossary.
Frequently asked questions
What is Context Stuffing?
Filling the context window with relevant reference material so the model can answer without retrieval or parametric memory.
Is Context Stuffing the same as context filling?
Yes — context filling, long-context prompting are common aliases for Context Stuffing.
What concepts are related to Context Stuffing?
Closely related concepts include long context, lost in the middle, rag.