From the course: Hands-On AI: Building Agents with the Google Agent Development Toolkit (ADK)

Unlock this course with a free trial

Join today to access over 24,900 courses taught by industry experts.

Building LLM agents: From basic prompts to tool-enabled power

Building LLM agents: From basic prompts to tool-enabled power

From the course: Hands-On AI: Building Agents with the Google Agent Development Toolkit (ADK)

Start my 1-month free trial Buy for my team

Building LLM agents: From basic prompts to tool-enabled power

“

- [Instructor] Let's learn how to build and extend LLM agents in ADK, just like in the Wander Wise app. We'll start with a basic agent, then make it smarter with real-time tools and session management. Feel free to modify the code to create your own agent, as well. Don't feel constrained by the app we are creating as an example. By the end, you'll have the skills to create your own intelligent, production-ready agents. As we saw, an LLM agent is powered by a large language model like Gemini or Llama. It can read, understand, and generate text, answer questions, and make decisions based on your input and context. Think of it as a super smart assistant that can chat, research, and reason all in one. Now, let's get hands-on. In your notebook, you'll define a packing list agent with its name, the model, a description, and detailed instructions. This instruction set is crucial. It tells the agent, "You are a helpful travel assistant. When the user provides a destination and trip duration…

Contents