Gen AI Leader cheat sheet

Exam at a glance

Domain weightings

How much of the exam each domain covers. Spend your study time in proportion — the heavier the domain, the more questions you'll see.

Key terms

Generative AI

Generative AI is a class of AI that creates new content — text, images, code, audio — from patterns learned during training. The Gen AI Leader exam covers its fundamentals and business value.

Foundation model

A foundation model is a large model pre-trained on broad data that can be adapted to many downstream tasks. The Gen AI Leader exam covers foundation and multimodal models as gen AI fundamentals.

Large language model

A large language model (LLM) is a foundation model trained on text to understand and generate natural language. The Gen AI Leader exam covers LLM concepts such as prompts, tokens, and context windows.

Gemini

Gemini is Google's family of multimodal generative AI models, offered through the Gemini app and across Google Cloud and Workspace. The Gen AI Leader exam covers Gemini as a core Google Cloud gen AI offering.

Vertex AI

Vertex AI is Google Cloud's unified platform for building, tuning, deploying, and managing machine learning and generative AI models. The Gen AI Leader exam covers Vertex AI, Model Garden, and Agent Builder.

Token

A token is a chunk of text — roughly a word or word-piece — that a language model processes, and tokens are the unit used to measure context length and cost. The Gen AI Leader exam covers tokens as a gen AI fundamental.

Context window

A context window is the maximum amount of text, measured in tokens, a model can consider at once. The Gen AI Leader exam covers the context window as a core concept affecting gen AI solutions.

Prompt engineering

Prompt engineering is the practice of designing inputs to guide a model's output, using techniques such as zero-shot, few-shot, and chain-of-thought. The Gen AI Leader exam covers it as a technique to improve output.

Grounding

Grounding connects a model's responses to authoritative or real-time data sources to improve accuracy and reduce hallucinations. The Gen AI Leader exam covers grounding and RAG as output-improvement techniques.

Retrieval Augmented Generation

Retrieval Augmented Generation (RAG) is a technique that retrieves relevant external data and supplies it to a model so its output is grounded in that data. The Gen AI Leader exam covers RAG to improve model output.

Hallucination

A hallucination is a confident but incorrect or fabricated response from a generative model. The Gen AI Leader exam covers hallucinations as a limitation and how grounding and RAG reduce them.

Responsible AI

Responsible AI is the practice of developing and using AI in ways that are fair, transparent, private, and safe. The Gen AI Leader exam covers Responsible AI as both a fundamental and a business-governance concern.

Model tuning

Model tuning customizes a foundation model for a specific task or domain, for example through fine-tuning or adapters. The Gen AI Leader exam covers tuning as a technique to improve gen AI output.