In this module, you’ll be introduced to AgentOps, its importance, and its relevance to modern enterprise AI systems. We will cover the basics of Agent Architecture—the roles of the model, tools, and orchestration layer—and how these components come together to form autonomous agents. You’ll also learn how AgentOps fits into the larger ecosystem of GenAIOps, and its dependency on frameworks like MLOps and DevOps for successful deployment.

Key Topics:

• What is AgentOps and why is it important?
• Components of Agent Architecture: Model, Tools, and Orchestration
• AgentOps vs. GenAIOps, MLOps, and DevOps
• Practical examples of AgentOps in action

In this hands-on module, you will learn how to build intelligent agents using LangChain and LangGraph. We will start by creating a basic QA Agent, where the agent uses external APIs to retrieve data and answer user queries. By the end of this module, you'll understand how to structure an agent’s tools, memory, and decision-making process.

Key Topics:

• Introduction to LangChain & LangGraph frameworks
• Creating a basic agent with external tool integration (e.g., an API or database)
• Managing agent memory for multi-turn conversations
• Task decomposition and reasoning loops (simple agents vs. complex multi-step workflows)

This module will focus on how agents manage context and memory, which is critical for more sophisticated interactions. You will also learn about the Orchestration Layer, which governs how an agent makes decisions, reasons through tasks, and interacts with the environment. Practical examples will showcase the Chain-of-Thought (CoT) and ReAct reasoning techniques.

Key Topics:

• Memory Management: short-term and long-term memory
• Orchestrating complex workflows with agents
• Using Chain-of-Thought (CoT) and ReAct reasoning frameworks
• Example: Building a travel assistant agent that remembers user preferences

In this module, you will learn how to set up multi-agent systems where agents collaborate to solve complex tasks. We will cover multi-agent design patterns such as hierarchical, collaborative, and peer-to-peer approaches, and demonstrate how agents communicate and delegate tasks. You will build a small multi-agent environment using LangChain and LangGraph.

Key Topics:

• Designing multi-agent systems
• Collaborative and hierarchical agent patterns
• Agent-to-agent communication and task delegation
• Example: An automotive AI system where different agents (e.g., navigation, weather, entertainment) collaborate to assist a user

In this advanced module, you will learn about Agentic RAG, a cutting-edge approach to combining information retrieval with generative models. You will see how agents can dynamically retrieve relevant data, refine their search, and generate meaningful responses based on real-time context. This module includes a hands-on demo where you will build an agent capable of answering complex, multi-faceted queries by refining its information retrieval strategy.

Key Topics:

• Introduction to Agentic RAG and its importance
• Building a multi-step agent that adapts its query to improve the retrieval process
• Example: A research assistant agent that gathers relevant articles and synthesizes a report

Evaluation is a crucial part of AgentOps to ensure agents perform effectively in real-world environments. In this module, you will learn how to evaluate your agents using various metrics, including goal completion, trajectory analysis, and final response quality. You will also explore the role of Human-in-the-Loop (HITL) evaluation to fine-tune agent behavior.

Key Topics:

• Setting up agent evaluation metrics: success rates, trajectory evaluation
• Using LLM-based evaluation methods (LLM-as-a-judge)
• Human-in-the-loop feedback and iterative improvement
• Example: Evaluating a financial agent’s task completion in real-time

In this capstone module, you will build a fully functioning Financial Research Assistant that integrates everything learned throughout the workshop. The agent will perform tasks like retrieving financial data, analyzing trends, and generating reports. This example will demonstrate the application of AgentOps principles for real-world enterprise use cases, showing you how agents can be deployed to solve specific business challenges.

Key Topics:

• Integrating multiple tools and agents to solve complex business problems
• Using memory and task orchestration in real-world tasks
• Final testing, evaluation, and deployment of an enterprise-grade agent

• Basic understanding of AI/ML and LLMs (Large Language Models)
• Familiarity with Python programming and using frameworks like LangChain or LangGraph
• Experience with APIs and web-based tool integrations (e.g., basic knowledge of calling external APIs)
• Familiarity with cloud-based environments (e.g., AWS, Google Cloud) is a plus, but not required