Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

Google Cloud

Agent Fundamentals

Google Cloud via edX

Go to class Write review
Destination Certification Ad

CISSP MasterClass with a true CAT exam simulator

Learn More → Boot.dev Ad

Learn Backend Development Part-Time, Online

Learn More →

Overview

Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates

This course introduces the fundamentals of AI agents, how they differ from LLM APIs, and where they add value in the real world. Based on Google's Agents Whitepaper, it provides the theoretical foundation needed before writing your first lines of agent code. It is ideal for developers, architects, and technical decision-makers who want to understand AI systems through the lens of autonomous, goal-directed behavior—not just text generation.

Agents Whitepaper: https://www.kaggle.com/whitepaper-agents

Join the community forum for questions and discussions.

Syllabus

  • Agents = LLMs + Autonomy + Tools + Orchestration.

  • Explain how AI agents pursue goals autonomously rather than simply responding to prompts.

  • Identify the five essential characteristics of AI agents: goal-directed behavior, autonomous operation, proactive initiative, environmental awareness, and tool use.

  • Explain the gap between knowing and doing that AI agents help bridge.

  • Describe the three core components of an AI agent: the model (centralized decision-maker), tools (the bridge to the external world), and orchestration (the cyclical process).

  • Explain the agent loop: Perceive → Think → Act → Check, repeated until the goal is achieved.

  • Identify examples of tools, including pre-built integrations, custom functions, and information retrieval.

  • Explain how models, tools, and orchestration work together to enable autonomous behavior.

  • Identify when AI agents are appropriate, such as for complex, multi-step, adaptive, or reasoning-intensive tasks.

  • Identify when AI agents are not appropriate, such as for simple Q&A, single-step operations, deterministic workflows, or real-time responses.

  • Apply an evaluation framework to determine whether an AI agent is the right solution by asking: Does the task require multiple steps, adaptation, or reasoning?

  • Explain why it is often best to start with a simple solution and add complexity only when it provides clear value.

Reviews

Start your review of Agent Fundamentals

Go to class

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.