What you will learn

  • Learn to build agentic systems from scratch with Python

  • Apply best practices and effective design patterns to build complex agentic workflows

  • Build and orchestrate advanced multi-agent systems

Course curriculum

    1. Course Introduction

    2. Course Objectives

    3. Course Tips

    4. Tools & Setup

    1. What is an agent?

    2. What are agents made up of?

    1. What are Augmented LLMs

    2. Components of Augmented LLMs

    3. Building a Single-Agent Search System

    1. What are LLM Workflows?

    2. Overview of Prompt Chaining

    3. Document Generator

    1. What is LLM Routing

    2. Routing Customer Service Requests

    1. What is Parallelization in LLMs?

    2. Optimizing LLM Guardrails with Parallelization

About this course

  • 37 lessons
  • 4.5 hours of video content
  • Certificate of Completion
  • Projects to apply learnings
  • Advanced

Join Pro to Get Started

Get unlimited access to all our AI courses, special tutorials, certificates, live webinars, workshops, office hours, dedicated support, and community discussions.

Instructor(s)

Elvis Saravia, Ph.D.

Founder and Lead Instructor

Elvis is a co-founder of DAIR.AI, where he leads all AI research, education, and engineering efforts. Elvis holds a Ph.D. in computer science, specializing in NLP and language models. His primary interests are training and evaluating large language models and developing scalable applications with LLMs. He co-created the Galactica LLM at Meta AI and supported and advised world-class teams like FAIR, PyTorch, and Papers with Code. Prior to this, he was an education architect at Elastic where he developed technical curriculum and courses on solutions such as Elasticsearch, Kibana, and Logstash.

OVERVIEW

Advanced AI Agents is a course focused on learning how to design and implement advanced agentic systems. 

After completing this course, students will know how to apply best practices and understand the latest design patterns and architectures for building agentic systems.

PREREQUISITES

This course leverages the Python programming language, so it requires basic knowledge of Python. 

We primarily use the OpenAI SDK for model access, so you are required to have a paid developer account with OpenAI (any tier should work). We are also leveraging a series of tools like Exa APIs to augment your agentic systems. 

TOPICS

Throughout the course, students will use Python and external tools to build a wide range of effective agentic systems:

  • Learn the foundations and important definitions to build effective agentic systems.
  • Learn about the fundamental building blocks for building agents, such as augmented LLMs.
  • Design and build with powerful and effective workflows such as prompt chaining and routing for a variety of common use cases.
  • Building multi-agent systems for open-ended and complex tasks such as search and evaluation.
  • Apply best practices to effectively orchestrate multi-agent systems across different use cases and requirements.
  • Learn how to evaluate agentic systems and how to debug them using tracing tools.
  • Building applications using everything learned in the course about how to build effective agentic systems.


Here's a subset of companies whose employees have benefited from our courses:

Accrete, Airbnb, Alston & Bird, Amazon, Apple, Arm, Asana, Bank of America, Belong For Me, Biogen, Brilliant, Carebound, CDM, CentralReach, Centric Software, Chime, Coinbase, Digital Green, DoHQ, Elekta, Fidelity Investments, Fivecast, Fulcrum Labs, Google, Guru, Gretel, Harrison Insights, Intel, Intuit, Jina AI, JPMorgan Chase & Co, Khan Academy, KnowBe4, Lawyer.com, LinkedIn, LionSentry, MagmaLabs, MasterClass, Meta, Metopio, Microsoft, Moneta Health, Oracle, OpenAI, Rechat AI, RingCentral, Salesforce, Scale AI, Scribd, Space-O Technologies, Sun Life, TD Bank, TELUS Corporations, Trilogy, TTEC Digital, UniCredit, VaxCalc Labs, Vendr, Walmart, Wolfram Alpha, Zemoso Technologies, Zeplin 

Reach out to [email protected] with any questions and for team/student discounts.

Join Pro to Get Started

Get unlimited access to all our AI courses, special tutorials, certificates, live webinars, workshops, office hours, dedicated support, and community discussions.

What people are saying

“This course gave me valuable insights into routing and parallelization of LLMs, which were key for building efficient AI agents. I also found the concept of an evaluator-optimizer agent particularly interesting for improving application performance.”

Rahul Jain | Co-Founder & CEO at Pixeldust Technologies

“DAIR.AI Academy was my best choice for learning about AI in 2025! Elvis is a very competent teacher, and the content is extremely useful. Prompt Engineering, Agents, and so many other topics were covered that I don't need any other resources. Thank you for bringing this knowledge to us!”

Felipe Fontoura | Senior Consultant at 2Fx Tech

Explore More Courses

Stay Updated!

Be the first to know about what's new in our Academy.

Thank You