Andrew Ng discusses tool use as a key design pattern in AI agentic workflows. He explains that tool use involves giving an LLM access to functions it can request to call for purposes such as gathering information, taking actions, or manipulating data. Common examples include LLM-based systems that can perform web searches or execute code. The post is part of Ng's broader series on agentic AI design patterns, highlighting how tool use enables AI agents to extend their capabilities beyond pure text generation by interacting with external systems and APIs.

Turing Post outlines the two primary ways AI agents interact with external tools and apps: UI-based interactions and API-based interactions. In the UI-based approach, an agent operates software by simulating human behavior — clicking buttons, typing into forms, and reading on-screen content, effectively mimicking how a person would use an application.

The post appears to be part of a broader educational thread explaining the mechanics of AI agent tool use, which is a foundational concept in the growing field of agentic AI. Understanding these two interaction paradigms is important as AI agents become more capable of autonomously completing complex tasks across multiple applications.