Prompting & context · Glossary term

What is Context Engineering?

Designing the full information environment supplied to a model at each step, including instructions, selected files, retrieved evidence, tool results, examples, state, and output constraints.

Why does Context Engineering matter?

Model performance often fails because relevant evidence is missing, stale, badly ordered, or overwhelmed by noise.

Context Engineering in practice

Build a compact task packet with the goal, repository rules, relevant interfaces, recent tool output, and unresolved decisions, then update it as state changes.

What is the common confusion about Context Engineering?

Prompt engineering focuses on instruction wording. Context engineering also decides what evidence and state enter the model's working context.

Learn Context Engineering in the course

Start with

Taught in Phase 11: LLM Engineering.

  • Context WindowThe maximum token capacity available to one model inference under a specific model and API contract.
  • Progressive DisclosureSupplying a person or model with the minimum useful context first, then revealing deeper detail when the task or evidence requires it.
  • Agent StateThe explicit data an agent carries across steps, such as the current objective, completed actions, tool results, open questions, budgets,…
  • Repository MapA compact, maintained description of a repository's important directories, ownership boundaries, entry points, build commands, tests,…
  • Agent MemoryInformation stored outside the model and selected for use in later agent steps, such as prior decisions, user preferences, task episodes,…
  • Context CompressionReducing the token footprint of source material while attempting to preserve the information required for a later model decision.
  • Data MinimizationFor personal data, limiting what is collected, processed, exposed, and retained to what is necessary for a specified purpose.
  • Lost in the MiddleA long-context failure pattern in which model performance changes with evidence position and can degrade when relevant information sits…
  • Prompt EngineeringDesigning model-facing instructions, examples, constraints, and output requirements to improve behavior on a defined task.
  • System PromptA provider-defined instruction message or configuration supplied by the application to establish behavior and constraints within that…
  • Token BudgetAn explicit allocation of token capacity across instructions, evidence, history, tool results, reasoning or working space, and output.

More terms in Prompting & context

Open the Prompting & context list in the glossary

This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.