Agentic AI
Master the art of building sophisticated AI agents. This comprehensive course covers foundational LLM concepts, advanced prompt engineering, and the full spectrum of agentic AI patterns. Get hands-on with LangChain and LangGraph for crafting intelligent workflows, and learn to integrate powerful proprietary models like Claude, GPT, and Gemini to create robust, autonomous AI applications.
What will I learn?
- Explain the fundamentals of LLMs and apply effective prompt engineering techniques.
- Differentiate between various agentic AI patterns (ReAct, Reflection, Multi-agent) and their appropriate use cases.
- Design, build, and debug complex AI agents using LangChain and LangGraph.
- Integrate and leverage proprietary LLMs (Claude, GPT, Gemini) within agentic systems.
- Utilize LangSmith for tracing, monitoring, and evaluating agent workflows.
- Understand the trade-offs between open-source and proprietary LLMs for agentic applications.
Curriculum
Foundations of LLM Applications
Covers the basics of Large Language Models (LLMs), their types, and essential prompt engineering techniques for effective interaction.
Introduction to Agentic AI
Explores the core concepts of AI agents, various agentic patterns like ReAct and Reflection, and the design of multi-agent systems.
LangChain, LangGraph and LangSmith for Agentic AI
Provides hands-on experience with LangChain for building LLM applications, LangGraph for stateful agent workflows, and LangSmith for observability.
Proprietary LLMs for Agentic AI
Examines the capabilities and integration of leading proprietary LLMs (Claude, GPT, Gemini) within agentic frameworks.
Why Edlitera?
Build the coding, data and AI skills you need, online, on your own schedule. From learning to code as a beginner to mastering cutting-edge data science, machine learning and AI techniques.
Learning for the real world
Our courses are made with the input and feedback of top teams at Fortune 500 companies in Silicon Valley and on Wall Street.
No-fluff learning
Each minute of each course is packed full of insight, best practices and real-world experience from our expert instructors.
Learn by doing
Start writing code on your computer from Day One. Practice on hundreds of exercises. Apply your skills in mini-projects. Get instant feedback from video solutions.
Complete learning tracks
With over 150 hours of video lectures and hundreds of practice exercises and projects, our learning tracks will help you level up your skills whether you are a novice or an advanced learner.
What people are saying
"I walked into the bootcamp with some basic Python syntax and walked out with a much stronger, contextualized grasp of Python, an understanding of common mistakes, the ability to solve basic coding problems, and confidence in my ability to learn more."
Randi S., Edlitera Student
"I wanted to learn Python and be able to process data without being tied and limited by Excel and macros. These classes gave me all the tools to do so and beyond. The materials provided, the engagement of the class by the tutors and their availability to help us were excellent."
Gaston G., Edlitera Student
Course Syllabus
1. Foundations of LLM Applications
1.1 Introduction to Large Language Models
- What are LLMs and how do they work
- Modern LLMs
- Different types of frameworks for working with LLMs
- Open-source vs proprietary LLMs
1.2 Prompt Engineering Fundamentals
- Prompt templates and their importance
- Prompting techniques
- Output parsing and structured responses
2. Introduction to Agentic AI
2.1 What is an agent?
- Define agents, environments, goals, and degrees of autonomy
- Distinguish agentic systems from tool-like uses of large language models
- Explain when autonomy is appropriate and when it is risky
2.2 ReAct Agents
- Understanding ReAct: Reason + Act framework
- Thought, Action, Observation loop
- Verbalized chain-of-thought reasoning in agents
- Tool-calling
2.3 Reflection Agents
- Introduction to reflection
- Iterative improvement through self-critique
- How to implement reflection
2.4 Multiagent systems
- Introduction to collaborative multi-agent systems
- Agent communication patterns and message passing
- Hierarchical and sequential agent workflows
- Coordinating multiple specialized agents for complex tasks
2.5 Advanced agent patterns
- Language Agent Tree Search (LATS)
- Combining agents with RAGs
- Self-improving agents with memory and learning
3. LangChain, LangGraph and LangSmith for Agentic AI
3.1 LangChain fundamentals
- LangChain architecture and core modules
- Chains and sequences
- Memory systems
- Tools and tool calling
- Retrieval Augmented Generation (RAG)
3.2 Introduction to LangGraph
- What is LangGraph and when to use it vs LangChain
- Core concepts: graphs, nodes, edges, state, compilation
- StateGraph with Annotated state patterns
- State management and reducers
- Control flow: normal, conditional, and entry/exit edges
- Cycles and loops for iterative agents
- Graph visualization and debugging
3.3 Tools and ReACT Agents
- Integrating tools with LangGraph workflows
- Creating context-aware tools
- Parallel tool execution and error handling
- Building ReACT agents
- Custom tool schemas with Pydantic validation
3.4 Memory, Persistence, and Streaming
- Short-term memory
- Checkpointers
- Thread management for multi-user applications
- Long-term memory with Store
- Streaming modes
- Async patterns for production workflows
- Memory optimization and cost analysis
3.5 Human-in-the-Loop Workflows
- Standard patterns
- State Update API for manual modifications
- Building approval workflows for sensitive operations
- Timeout handling and escalation patterns
- Feedback loops for iterative improvement
- Branching decisions and A/B testing
- Audit trails for compliance
3.6 Multi-Agent Systems
- Multi-agent architecture patterns
- Handoff protocols between specialized agents
- Subgraphs for modular agent components
- Parallel agent execution and load balancing
- Agent communication protocols and conflict resolution
- Dynamic agent spawning for complex tasks
3.7 Advanced Patterns and Testing
- Self-reflection and critique loops
- Plan-and-execute pattern for complex reasoning
- Unit testing nodes and integration testing graphs
- Mocking LLM responses for deterministic tests
- Property-based testing with Hypothesis
- Performance profiling and optimization
3.8 Production Deployment
- Security: input validation, prompt injection prevention, output filtering
- Error handling hierarchy and retry strategies with circuit breakers
- Cost optimization
- Monitoring with LangSmith
- Deployment options
- Scaling strategies
4. Proprietary LLMs for Agentic AI
4.1 Introduction to Proprietary LLMs
- Capability trade-offs between proprietary and open-source models
- When to use proprietary vs open-source models
4.2 Claude Family (Anthropic)
- Introduction to the Claude series of models
- Model capabilities
- Agentic AI with Claude Code
4.3 GPT Family (OpenAI)
- Introduction to the GPT series of models
- Model capabilities
- Agentic AI with GPT-5 Codex
4.4 Gemini Family (Google)
- Introduction to the Gemini series of models
- Model capabilities
- Agentic AI with Google Antigravity
5. Final project
Have a question?
Contact us any time, we'd love to hear from you!