Learning Objectives:

Learn how AI agents interact with external tools, maintain memory, and retrieve information from enterprise knowledge sources to perform complex, context-aware tasks.

Develop AI agents capable of interacting with enterprise systems while preserving context and leveraging persistent memory.

Topics:

• Tool Calling
• Tool Selection
• Tool Error Handling
• Short-Term Memory
• Long-Term Memory
• Embeddings
• Vector Databases
• Semantic Search

Hands-on Lab

Build an intelligent AI agent capable of using external tools while maintaining conversational memory.

Learning Objectives:

Master Retrieval-Augmented Generation (RAG) techniques that enable AI agents to access enterprise knowledge, reduce hallucinations, and deliver grounded, context-aware responses.

Design enterprise-grade retrieval systems that significantly improve the accuracy and reliability of AI agents.

Topics:

• RAG Architecture
• Document Chunking
• Embedding Pipelines
• Retrieval Strategies
• Re-ranking
• Hybrid Search
• Agentic RAG
• Knowledge Grounding

Hands-on Lab

Build a production-ready enterprise RAG application using vector search and semantic retrieval.

Learning Objectives:

Learn how to use LangChain to develop modular AI applications that integrate prompts, memory, tools, and retrieval into scalable enterprise workflows.

Build production-ready AI applications using LangChain's engineering framework.

Topics:

• LangChain Architecture
• LCEL
• Chains
• Agents
• Memory
• Callbacks
• Tool Integration
• Prompt Templates

Hands-on Lab

Develop an enterprise AI assistant using LangChain components and modular workflows.

Learning Objectives:

Build stateful AI agents capable of handling long-running workflows, conditional logic, and human approvals using LangGraph's graph-based orchestration framework.

Develop durable, stateful AI agents using graph-based orchestration techniques.

Topics:

• LangGraph Fundamentals
• Stateful Workflows
• Nodes & Edges
• Conditional Routing
• Human-in-the-Loop
• Interrupts
• Streaming Responses

Hands-on Lab

Create a stateful AI agent capable of managing complex multi-step enterprise workflows.

Learning Objectives:

Learn how multiple specialized AI agents collaborate to solve complex business problems using CrewAI's role-based orchestration framework.

Develop role-based multi-agent systems capable of executing complex collaborative workflows.

Topics:

• CrewAI Fundamentals
• Crews
• Roles
• Tasks
• Flows
• Hierarchical Teams
• Collaborative Agent Design

Hands-on Lab

Build a collaborative research team consisting of multiple AI agents with specialized responsibilities.

Learning Objectives:

Learn a comprehensive engineering framework for building reliable production-ready AI agents by combining prompts, memory, retrieval, orchestration, runtime, reasoning, guardrails, observability, evaluation, and governance.

Engineer modular, scalable, secure, and production-ready AI agents using Agent Harness Engineering principles.

Topics:

• Prompt
• Memory
• Tools
• Orchestration
• Retrieval
• Runtime
• Reasoning
• Guardrails
• Observability
• Evaluation
• Human-in-the-Loop
• Identity
• Security
• Governance

Hands-on Lab

Design and implement a reusable Agent Harness architecture for an enterprise AI assistant.

Learning Objectives:

Explore proven architectural patterns used by enterprises to coordinate multiple AI agents, enabling specialization, collaboration, scalability, and intelligent task delegation.

Design scalable multi-agent architectures suitable for enterprise AI applications.

Topics:

• Orchestrator Pattern
• Planner-Executor Pattern
• Critique-Refine Pattern
• Debate Pattern
• Hierarchical Agents
• Agent Communication
• Task Delegation
• Workflow Coordination

Hands-on Lab

Build a multi-agent enterprise workflow using orchestration and delegation patterns.

Learning Objectives:

Learn how to monitor, debug, evaluate, and continuously improve AI agents using modern observability frameworks and evaluation methodologies.

Implement comprehensive monitoring, debugging, and evaluation strategies for enterprise AI agents.

Topics:

• Agent Tracing
• LangSmith
• Logging
• Evaluation Frameworks
• Debugging Agent Workflows
• Performance Monitoring
• Cost Analysis
• Error Diagnosis

Hands-on Lab

Monitor, evaluate, and debug a production AI agent using LangSmith observability tools.

Learning Objectives:

Learn how enterprise AI agents are deployed, tested, secured, and maintained in production environments using modern deployment architectures and engineering best practices.

Deploy secure, scalable, and production-grade Agentic AI applications following enterprise engineering standards.

Topics:

• FastAPI Deployment
• Docker
• API Deployment
• Testing AI Agents
• Version Control
• CI/CD Concepts
• Performance Optimization
• Production Best Practices

Hands-on Lab

Deploy a production-ready AI agent with API endpoints, monitoring, and automated testing.