Effective Context Engineering for AI Agents

aid: context-engineering:anthropic-guide
name: Effective Context Engineering for AI Agents
description: Anthropic's engineering guide to context engineering, framing context as a finite attention
  budget and walking through system prompts, tool design, few-shot examples, just-in-time retrieval, compaction,
  structured note taking, and multi-agent architectures.
humanURL: https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents
baseURL: https://www.anthropic.com
tags:
- Anthropic
- Best Practices
- Engineering
properties:
- type: Documentation
  url: https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents
- type: Reference
  url: https://docs.anthropic.com/en/docs/agents-and-tools/agent-best-practices
x-features:
- Frames context as a finite attention budget
- Distinguishes context engineering from prompt engineering
- Covers system prompts, tools, few-shot, and retrieval
- Long-horizon strategies (compaction, notes, sub-agents)
x-useCases:
- Building production AI agents and assistants
- Tuning system prompts and toolsets for reliability
- Designing memory and compaction for long-running agents