People who need to get current with modern AI before taking more intensive technical courses start with Agentic Systems Introduction, a one-day primer. The course provides a practical, light-touch tour of the concepts behind LLM-powered applications and agentic systems, without assuming deep AI or machine learning experience. Participants learn how models process tokens, use context, generate outputs, connect to tools, retrieve information, and support increasingly capable agent workflows. The course also introduces the vocabulary and mental models needed to understand MCP, RAG, embeddings, multi-agent systems, model training, inference, quantization, safety, and evaluation. Through guided labs and demos, participants build intuition for what modern AI systems can do and where they fail. They also see how more advanced courses fit together.
Labs anchor each module in a concrete exercise. Attendees compare model outputs across prompts, settings, and task types to build intuition for sampling and temperature. They then build a lightweight RAG-style question answering workflow covering chunking, reranking, and source quality. A third lab connects a simple agent workflow to a tool or simulated MCP-style service. It works through observe-reason-act loops and basic permission and sandboxing concerns. The day closes by mapping a real AI use case to the right course path. Attendees weigh whether a single agent, a workflow, or a multi-agent system fits the problem. They also review what evaluation, observability, and human-in-the-loop review look like once a project moves toward production.
Who Should Attend
Developers, analysts, architects, technical managers, product teams, and AI adopters
What Attendees Will Learn
Upon completing Agentic Systems Introduction, participants will be able to:
- Explain the basic concepts behind generative AI, LLMs, and agentic systems
- Describe how tokens, context windows, embeddings, inference, training, and quantization fit together
- Understand the difference between LLM applications, agents, workflows, and multi-agent systems
- Recognize common patterns for tools, MCP, RAG, structured output, and context management
- Identify practical opportunities, risks, and limitations for agentic AI systems
- Prepare for deeper technical courses in agentic development, multi-agent systems, RAG, and AI operations
Prerequisites
No AI or machine learning experience is required. General technical literacy is helpful, but the course is designed for participants who may have been out of the AI loop and need a concise, current foundation.