From the course: Agentic AI for Developers: Concepts and Application for Enterprises
Join today to access over 24,700 courses taught by industry experts.
Goals in agentic AI
From the course: Agentic AI for Developers: Concepts and Application for Enterprises
Goals in agentic AI
- [Instructor] Let's dive deeper into goals in Agentic AI in this video. A goal represents the result that an agentic AI system is expected to achieve. It can be a simple question for which an answer is required, or a complex task that involves a workflow across multiple systems. What are some of the characteristics of goals? Goals can be considered similar to prompts in GenAI, and they look very similar, but goals typically require a multi-step process across multiple tools to achieve the end result. Goals are typically provided in natural language format, like a question or a work order. They may include other media types too. Goals typically originate from an end user or from a client application. Based on how the agent is set up, they typically require multiple steps or tasks to achieve. Each instance of the goal is different and may require a different set of steps or sequences to achieve them. The LLM decides on what steps are needed for each specific goal. A goal may result in…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.