Andrew Ng on Tool Use as a Key Design Pattern in AI Agentic Workflows

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.