Module 1: Generative Models Overview

- AI, ML, and Generative AI fundamentals
- Capabilities and limitations of LLMs
- Hallucinations and model variability
- Lab: Getting started with generative models

Module 2: Prompt Engineering Techniques for LLMs

- Prompt structure: task, context, role, format
- Zero-shot, one-shot, and few-shot prompting
- Specificity and refinement techniques
- Structured outputs (JSON, tables, formatted data)
- Prompting for consistency and reliability
- Understanding model-specific prompting guidance across providers
- LAB: Techniques for Improving Text Output Quality

Module 3: Prompt Engineering for Text-to-Image Models

- Prompting for image generation (subject, style, lighting, composition)
- Iterative refinement and prompt expansion
- Using templates and examples
- LAB: Producing Images from Text Input Using Generative AI

Module 4: Advanced Prompting and Tool-Augmented Workflows

- Chain-of-thought and stepwise prompting
- Prompt chaining and multi-step workflows
- LLMs as orchestrators of tools and actions
- Designing prompts for tool usage (function calling patterns)
- Prompt → tool → result → response workflows
- Using tools to improve accuracy and reduce hallucinations
- High-level overview of Model Context Protocol (MCP)
- Standardizing tool and data access
- Connecting LLMs to external systems
- LAB: Refining Output and Building Tool-Driven Workflows

Generative AI Prompt Engineering (RXM401)

Stay Up to Date