Foundations of Agentic AI

Course Summary

The Foundations of Agentic AI course focuses on building real-world chatbots and autonomous problem-solving agents using open-source toolsincluding Hugging Face TransformersLlamaIndexand OpenAI Gym. Participants will gain hands-on experience designingbuildingand deploying intelligent agents capable of reasoning and interacting in natural languagepowered by Hugging Face’s free pre-trained models. An optional 3rd-day hackathon allows teams to apply their knowledge to tackle realistic AI challenges using real-world datasets and APIs.

Prerequisites
In order to succeed in this courseyou will need:

A basic understanding of machine learning and natural language processing
Proficiency in Python programming

Purpose	Gain experience designingbuildingand deploying intelligent agents capable of reasoning and interacting in natural language
Audience	Those looking to designbuildand deploy conversational and problem-solving agents
Role	Software Developers \| Data Scientists \| Data Engineers \| AI/ML Developers
Skill level	Intermediate
Style	Lecture \| Hands-on Activities \| Labs
Duration	2 days (3 days with optional hackathon)
Related technologies	AI/ML \| Gen AI \| Hugging Face \| Python

Course objectives

Understand how to leverage Hugging Face models for building conversational and problem-solving agents
Build practical agentic AI systems using Python-based tools and frameworks
Integrate free and open-source libraries like LlamaIndex and OpenAI Gym for agent design
Deploy fully functional chatbots and agents without reliance on paid APIs

What you'll learn:

In this Foundations of Agentic AI courseyou'll learn:

Foundations of Chatbots and Intelligent Agents

Introduction to Agentic AI and Hugging Face
- What is Agentic AI?
  - Overview of agentsautonomyand decision-making
- Hugging Face Ecosystem
  - Introduction to Transformerspipelinesand pre-trained models
- Exploring a pre-built chatbot using Hugging Face's models

Building Chatbots with Hugging Face Transformers
- Transformers for NLP Tasks: Understanding how Hugging Face’s models handle tasks like text generation Q&Aand summarization
  - Loading a pre-trained conversational model (e.g.DialoGPT or BlenderBot)
  - Fine-tuning the chatbot on a custom dataset (e.g.customer service FAQs)
  - Testing the chatbot’s responses and improve performance

Augmenting Chatbots with LlamaIndex
- Connecting Chatbots to External Data
  - Making chatbots more intelligent with LlamaIndex
  - Retrieval-Augmented Generation (RAG)
- - Answering queries with real-time information
- Building a chatbot knowledge base (e.g.FAQscompany policies)
  - Testing the chatbot on domain-specific questions

Introduction to Simulated Environments with OpenAI Gym
- Simulating Tasks for Intelligent Agents
  - Why simulations are essential for agent training
- Customizing OpenAI Gym Environments
  - Designing environments for specific tasks
- Setting up a basic OpenAI Gym environment (e.g.Taxi-v3)
  - Building a rule-based agent to solve a simple navigation task

Advanced Agent Design and Real-World Applications

Multi-Modal Agents and Advanced Integrations
- Multi-Modal Inputs for Agents
  - Combining textimagesand structured data
- Integrating Hugging Face models for text and vision tasks (e.g.image captioning with CLIP or BLIP)
  - Creating a multi-modal chatbot that processes both text and images

Problem-Solving Agents with OpenAI Gym
- Reinforcement Learning Primer: Basics of Q-learning and policy optimization
- Training a reinforcement learning agent in a custom Gym environment (e.g.resource allocation or delivery)
  - Comparing a rule-based agent’s performance with an RL-based agent

Deploying Agentic AI Systems
- Deploying Chatbots and Agents Locally or on Cloud Platforms
  - Tools and best practices
- Deploying a chatbot locally using Flask or FastAPI
  - Build a simple front-end to interact with the deployed agent

Foundations of Agentic AI

Real-World Content

Project-focused demos and labs using your tool stack and environmentnot some canned "training room" lab.

Expert Practitioners

Industry experts that bring their battle scars into the classroom.

Experiential Learning

More coding than lecturecoupled with architectural and design discussions.

Tailored Outlines

Once-size-fits-all doesn't apply to training teams. That's where we come in!

Dive in and learn more

When transforming your workforceit’s important to have expert advice and tailored solutions. We can help. Tell us your unique needs and we'll explore ways to address them.

Let's chat

First name*

Last name*

Business email*

Company*

Job title*

Phone*

Country*

Tell us about what you’re looking to accomplish:

By clicking submityou agree to our Privacy Policy and Terms of Useand consent to receive marketing emails from Pluralsight.

Foundations of Agentic AI

Course Summary

Purpose

Audience

Role

Skill level

Style

Duration

Related technologies

Course objectives

What you'll learn:

In this Foundations of Agentic AI courseyou'll learn:

Foundations of Agentic AI

Real-World Content

Expert Practitioners

Experiential Learning

Tailored Outlines

Dive in and learn more