blog-context-engineering
Anthropic Engineering — Effective context engineering for AI agents
URL: https://www.anthropic.com/engineering/effective-context-engineering-for-ai-agents Publisher: Anthropic Engineering Retrieved: 2026-07-08
Summary
Anthropic Engineering post framing context engineering as "the set of strategies for curating and maintaining the optimal set of tokens (information) during LLM inference" — a superset of prompt engineering that manages the whole context state (system instructions, tools, MCP, external data, message history). It treats context as a finite resource subject to "context rot" and an "attention budget," and prescribes finding the smallest set of high-signal tokens: system prompts at the "right altitude," minimal token-efficient tools, just-in-time retrieval over pre-loading, and long-horizon techniques — compaction, structured note-taking / external memory, and sub-agent architectures.