Overview
Your organization has assessed its need and ability to implement one or more AI agents with minimal risk. Now it's just a matter of building those agents—that's where you come in.
In this course, you'll translate business requirements into a functional AI agent that can automate complex tasks and processes that would otherwise require significant human effort. Ultimately, this can lead to improved user productivity, a reduction in operational costs, and enhanced employee and customer satisfaction.
This is the second course in a series and is meant to build upon the foundation of the first course (AgenticAIBIZ) by giving technical practitioners the skills they need to successfully build agentic AI into their organizations. This course is designed for programmers, IT infrastructure personnel, DevOps/MLOps personnel, and any other technically minded professional who is responsible or may soon be responsible for implementing agentic solutions in their organization.
This course is also designed to assist you in preparing for the CertNexus® Agentic AI Builder™ (Exam AGB-110) credential. In this course, you will:
set up the agent development environment; assess LLM behavior in agent contexts; implement the agent reasoning loop; implement tools for the agent to use; add knowledge to an agent through retrieval-augmented generation (RAG); enforce structure, safety, and reliability in an agent; test the behavior and performance of an agent; and deploy a single-agent system to production.
NOTE:
In order to use the labs in this course as intended, you will need access to an OpenAI API key. This is a paid service, but your total costs should not exceed $5.
The course setup instructions provided in the first module of the course go into more detail about the API requirements.
Syllabus
- Setting Up the Agent Development Environment
Agentic systems are like any other software in that they must be developed and tested within a controlled environment. Setting up this environment is a necessary first step toward project completion. So, in this lesson, you'll configure a workspace and ensure you can access the resources necessary for the agent to get started.
- Assessing LLM Behavior in Agent Contexts
Connecting an LLM to the agentic system is just the first step. You need to understand how the LLM behaves in practice before you can effectively design the agent around the LLM. That way, there will be no surprises—you'll know exactly what the model is capable of doing, and where it may fall short. You'll then be able to put this assessment to good use by building an agent that takes advantage of the LLM and doesn't waste time or tokens on unrealistic behaviors.
- Implementing the Agent Reasoning Loop
Previously, you focused on connecting the agent to a large language model (LLM) and ensuring it uses that LLM effectively. Now, it's time to build the agent's workflow. This workflow will form an overall execution loop within which the agent will repeatedly reason and act. You need to make sure this loop is constructed properly so that it supports the agent's goals as well as your business objectives for the agentic initiative.
- Using Agent Tools
You've built your agent to reason effectively, and not only that, but to maintain an awareness of important context while it reasons. But this is really only half of the agentic equation. The other half is to ensure the agent can take actions in an environment. That's key to turning it into an actual automated system. And, the way you facilitate actions is by providing the agent with tools. So, that's what you'll do in this lesson.
- Adding Knowledge with Retrieval-Augmented Generation
Retrieval-augmented generation (RAG) is a supplemental, yet powerful way of making AI agents even more capable. Many agentic systems incorporate RAG to help mitigate the issue of limited memory and context windows in LLMs. An agent can still review and evaluate key pieces of information without having to be fed all of that information directly. In this lesson, you'll set up your agent for RAG so it can make more informed decisions based on extensive organizational documentation.
- Enforcing Structure, Safety, and Reliability in an Agent
An important part of building a capable agent is ensuring that it can perform its assigned tasks within acceptable boundaries. Until you incorporate these boundaries, the agent cannot be relied upon to produce safe and consistent results in a production environment. That's why, in this lesson, you'll employ various techniques to prevent mistakes from having a significant negative impact on the agentic system as a whole.
- Testing an Agent
Agentic AI is, fundamentally, software—and like any software, it must be tested prior to launch. If you're familiar with the world of software development, then you'll probably have some idea of how to approach testing an agent. But, there are also some key elements that distinguish testing an agent from testing a normal application. In this lesson, you'll employ various methods for testing agentic AI to ensure it is meeting expectations.
- Deploying a Single-Agent System
You've thoroughly developed and tested your agentic system, so naturally, the remaining step is to deploy it. But, deployment is not just a matter of flipping a switch and then walking away—it requires planning and design work, like any other aspect of the development process. You need to choose an interface through which to expose the agent to its users, and you need to make sure you're actually ready to deliver the agent to production instead of creating another prototype. In this lesson, you'll make sure you're truly prepared to deploy your agentic system.
- Completing the Course
You'll wrap things up and then validate what you've learned in this course by taking the credential exam.
Taught by
Bill Rosenthal
Subjects
Artificial Intelligence
