AI Assistants

In this learning path, you will gain a fundamental understanding of Large Language Model (LLM) security. Through a series of articles and videos you will explore topics like what is an LLM, data security risks, the OWASP Top 10 for LLMs, strategies for defending LLM systems, and the critical role users play in maintaining security.

Generative AI is a cutting-edge technology that has been making waves across various industries in recent years. Unlike traditional AI systems that are designed to analyze and interpret existing data, generative AI has the remarkable ability to create entirely new content, from text and images to music and even code. This revolutionary technology leverages complex machine learning algorithms and neural networks to understand patterns and structures in vast amounts of data, enabling it to generate original and often highly realistic outputs. As generative AI continues to evolve and improve, it promises to transform creative processes, problem-solving, and innovation across numerous fields, from art and entertainment to scientific research and product development. Learn about what Generative AI is and how it works, in this Learning Path.

The Artificial Intelligence (AI) Driver's License is a new WWT initiative aimed at ensuring we are using AI safely and effectively for our customers. The Driver's License is a way for us to validate and certify that our employees have mastered basic AI competencies and are leveraging current AI best practices in all of our client engagements. This is WWT's public version of the AI Drivers License learning path and is encouraged to be shared with others!

RAG, or Retrieval-Augmented Generation, is an AI solution that combines the power of Generative AI with external data sources to provide more accurate and up-to-date responses. This Learning Path explains the concept of RAG, its origins, and how it addresses key limitations of traditional GenAI systems. You'll learn about the benefits of RAG, including enhanced accuracy, reduced hallucinations, and its flexibility in integrating real-time information without the need for constant model retraining.