# Context engineering

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: context management, context design

Deciding what information, [instructions](https://ecosystem.samcarlton.com/prompt), examples and tools to put in front of an [AI model](https://ecosystem.samcarlton.com/model) for each task, and what to leave out. It goes beyond writing a single prompt.

**For example:** Instead of pasting the whole wiki, a team [feeds](https://ecosystem.samcarlton.com/rss) the [agent](https://ecosystem.samcarlton.com/ai-agent) only the three relevant pages plus its [style guide](https://ecosystem.samcarlton.com/design-system), and answers get better.

## Connects to (6)

- [Prompt](https://ecosystem.samcarlton.com/prompt): The instructions or question you give an AI tool in everyday words.
- [Context window](https://ecosystem.samcarlton.com/context-window): How much text an LLM can take into account at one time.
- [RAG](https://ecosystem.samcarlton.com/rag): Retrieval-augmented generation.
- [Agent skills](https://ecosystem.samcarlton.com/agent-skills): A packaged set of instructions, sometimes with scripts, that an agent loads when a task calls for it, such as how to write a press release…
- [System prompt](https://ecosystem.samcarlton.com/system-prompt): Standing instructions that the builder of an AI product gives the model before any user types.
- [Few-shot prompting](https://ecosystem.samcarlton.com/few-shot-prompting): Including a few worked examples in a prompt so the model copies the pattern.

Map view: https://ecosystem.samcarlton.com/context-engineering