HomeCoursesAgentic System Design
AI Powered
Save

Agentic System Design

Learn to design the next generation of AI systems. Explore the architectures and strategies behind autonomous agents that solve complex, real-world problems.

4.5
39 Lessons
2 Breakout Sessions
6h
Updated 1 week ago
Join 2.9 million developers at
Join 2.9 million developers at
LEARNING OBJECTIVES
  • An understanding of AI agents and how they differ from AI models
  • The ability to identify and explain core AI agent components and memory systems
  • An explanation of different agent orchestration patterns and how to choose among them
  • Hands-on experience designing and implementing AI agent safety guardrails
  • Knowledge of integrating human oversight into agent workflows
  • Understanding and applying strategies to overcome challenges in agentic systems
  • Hands-on experience deconstructing real-world AI agent case studies
  • Understanding the design and architecture of adaptive and robust AI agent systems

Learning Roadmap

39 Lessons5 Quizzes

2.

Multi-Agent Conversational Recommender System (MACRS)

Multi-Agent Conversational Recommender System (MACRS)

Explore MACRS, a multi-agent system for goal-directed conversational recommendations. See how it plans, uses reflection, and achieves superior performance.

3.

Nvidia Eureka Learning Agent

Nvidia Eureka Learning Agent

6 Lessons

6 Lessons

Dive into Eureka, an LLM-powered agent that autonomously designs and refines RL reward functions.

4.

Implementing a Eureka-Like Reward Learning Agent with Google ADK

Implementing a Eureka-Like Reward Learning Agent with Google ADK

5 Lessons

5 Lessons

Implement a Eureka-like reward learning system using ADK: generate, evaluate, select, reflect, and iterate reward functions end-to-end.

6.

Designing an AI Agent for Generating LLM Pipelines

Designing an AI Agent for Generating LLM Pipelines

4 Lessons

4 Lessons

Explore ChainBuddy’s innovative solutions for efficient LLM evaluation and workflow generation.

7.

Designing a Web Agent

Designing a Web Agent

5 Lessons

5 Lessons

Explore the development of advanced multimodal web agents for enhanced task performance.

8.

Designing a Multimodal-LLM Agent for Multi-Object Diffusion

Designing a Multimodal-LLM Agent for Multi-Object Diffusion

4 Lessons

4 Lessons

Explore MuLan's innovative approach to enhancing text-to-image generation through interactive, multi-step processes.
Certificate of Completion
Showcase your accomplishment by sharing your certificate of completion.
Author NameAgentic System Design
Developed by MAANG Engineers
Every Educative lesson is designed by a team of ex-MAANG software engineers and PhD computer science educators, and developed in consultation with developers and data scientists working at Meta, Google, and more. Our mission is to get you hands-on with the necessary skills to stay ahead in a constantly changing industry. No video, no fluff. Just interactive, project-based learning with personalized feedback that adapts to your goals and experience.

Trusted by 2.9 million developers working at companies

Built for 10x Developers

No Passive Learning
Learn by building with project-based lessons and in-browser code editor
Learn by Doing
Personalized Roadmaps
The platform adapts to your strengths & skills gaps as you go
Learn by Doing
Future-proof Your Career
Get hands-on with in-demand skills
Learn by Doing
AI Code Mentor
Write better code with AI feedback, smart debugging, and "Ask AI"
Learn by Doing
Learn by Doing
MAANG+ Interview Prep
AI Mock Interviews simulate every technical loop at top companies
Learn by Doing

Free Resources

FOR TEAMS

Interested in this course for your business or team?

Unlock this course (and 1,000+ more) for your entire org with DevPath