Skip to content

Glossary · Agents

Context engineering

Context engineering is designing everything that goes into a model's context window, instructions, tools, retrieved documents, memory and history, so an agent has the information it needs and little else.

Reviewed 15 November 2026

Anthropic describes context as a finite resource with diminishing returns: as it grows, models recall less of it, so the aim is the smallest set of high-signal tokens. Techniques include just-in-time retrieval, summarising or compacting history, and structured notes outside the window.

It extends prompt engineering from a single prompt to the whole state a long-running agent sees.

Learn more on Kojen

Sources

  1. [1]Anthropic. Effective context engineering for AI agents

All 31 terms

Put the definitions to work.

Kojen evaluates, tunes and red-teams your agents with these methods built in: Wilson intervals, pass^k, LLM judges with visible components. Free to start.

Start training free