Context Engineering

Claude's Tool Calling Paradigm Shift: A Deep Dive into Programmatic Tool Calling and Dynamic Filtering

2026-06-13·更新于: 2026-07-30·2655 words· 13 min

Agent Engineering Claude AI Agent Agent Architecture Tool Calling Context Engineering Programmatic Tool Calling Dynamic Filtering Code Execution

The important change is not “two more tool features.” It is the movement of multi-step orchestration into a code-execution environment, with only a compact result returning to model context. Background: The Cost Problem in Agent Tool Calling # In traditional agent tool-calling, every tool invocation requires a full cycle of “model inference → tool execution → result return → model re-inference.” This seemingly natural loop breaks down at scale in three ways:

RAG vs LLM Wiki vs Plain Text — A Decision Framework for Agent Long-Term Memory

2026-05-11·更新于: 2026-07-30·1299 words· 7 min

Agent Engineering AI Agent Memory RAG Context Engineering

Every Agent builder hits this question eventually: where do I store user data so the agent remembers it next session? Three approaches dominate the landscape: RAG (vector retrieval), LLM Wiki (structured knowledge injection), and plain-text context memory (the CLAUDE.md / Cursor Rules pattern). Each has vocal advocates. But picking wrong is expensive — do RAG too light and it’s a noise generator; do plain text too heavy and it’s a token incinerator.

↑