What you will learn

  • Learn the basics and key ideas behind building effective agentic systems

  • Apply industry best practices to build and systematically improve AI agents

  • Learn key insights and practical tips from building real-world use cases

Course curriculum

    1. Orientation and Preparations

    1. Prompting Engineering for AI Agents

    1. Building LLM Workflows

    1. Building Agentic Workflows

    1. Building Multi-Agent Systems

    1. Debugging & Evaluating AI Agents

About this course

  • Live course
  • May 22 - July 10, 2025
  • Earn a Certificate of Completion

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.

More about the course

OVERVIEW

This live course will involve live build sessions where you will build and deploy agentic systems. 

After completing this course, you will have a systematic framework for building powerful products and projects with AI agents that you can apply to your personal and professional settings.

This course is built for anyone interested in building agentic systems. We welcome devs and professionals (without coding backgrounds) interested in building with AI agents. 

SYLLABUS

Session 1: Orientation & Preparation

  • Learn the basics of using n8n, such as JSON, API, nodes, and workflows

  • Load and execute a single-agent search system

Session 2: Prompt Engineering for AI Agents

  • Learn the most important prompt engineering techniques and tips for building advanced agentic systems.

Session 3: Building LLM Workflows

  • Learn to build with the most effective LLM workflows (e.g., prompt chaining, parallelization, routing, etc.) to enable robust, reliable, and efficient agentic systems

  • Build agentic systems for customer service, human-in-the-loop agents, and data analysis

Session 4: Building Agentic Workflows

  • Overview of augmented LLMs, tools, function calling, structured outputs, reasoning, memory, and other important techniques to build effective agentic systems

  • Learn how to build basic agentic systems with core ideas, components, and design patterns (looping, sequential, parallel, hierarchical)

  • Build agentic systems for deep research, content creation, and productivity

Session 5: Building Multi-Agent Systems

  • Build a real-world advanced multi-agent system using everything learned so far

  • Students will select and build a final project from a list of suggested agentic systems

Session 6: Debugging & Evaluating AI Agents

  • Learn how to monitor and debug your agentic systems and the benefits of doing so

  • Learn key evaluation techniques and tips for evaluating AI agents (e.g., LLM-as-a-Judge, heuristic metrics)

  • Build robust evaluation pipelines to systematically improve your agentic systems

Session 7: Deploying Agentic Applications

  • Learn important considerations for deploying production-grade agentic systems, like latency, cost, security, privacy, deployment solutions, etc. 

  • Discuss options for how to build a front-end application for your agentic systems, how to enhance user experience, and other considerations

  • Prepare your agentic systems to be deployed live for user testing and feedback

Session 8: Demo Day

  • Build an agentic application that would help either for work or for personal use

  • Students will present their final project and receive feedback

PREREQUISITES & TOOLS

There will be little theory in this course, and we will provide all the support and guidance to better prepare students for the live build sessions.

While not required, we recommend that students complete the following courses to better prepare for this live course:


Tech stack:

  • We will be using n8n as the main tool for orchestrating agentic systems. Students will use the n8n cloud version. Students will get free access to n8n (courtesy of n8n). 
  • Other integrations and tools will be used, such as the web search tool called Exa. We will provide more details about all the tools that will be used before the preparation session.  
  • The main LLMs you will use are Gemini and OpenAI models. We recommend that everyone have a paid account for each of these providers. Alternatively, you can set up an account on OpenRouter to get access to the models from one service (https://openrouter.ai/). The expected cost for token use will be relatively low.


OTHER IMPORTANT DETAILS

This live course starts on May 22, 2025, and is expected to last at least two months. We will have build sessions every week until demo day (tentative date: July 10, 2025). 

We will run one session every week for 8 weeks.  Each session will be every Thursday from 9:00 am to 10:00 am (Pacific Time). 

We are also hosting office hours each week to address questions, provide support, and have deeper discussions. 

This course is only available to Pro subscribers. You will need an active subscription to get access to all future live sessions. We believe it's still very affordable compared to prices for live courses out there (usually in the thousands).

All sessions will be recorded and provided immediately after every session. More details coming soon!

Reach out to [email protected] if you have any questions. Contact us if you have a team; we are happy to onboard them. If you are a student, reach out for our discount options. 

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.