Question 1

Which AWS service lets you build generative AI applications using foundation models through a single API, without managing infrastructure?

Accepted Answer

Amazon Bedrock Amazon Bedrock provides serverless access to foundation models from multiple providers via one API. SageMaker is for building and training your own ML models.

Question 2

Which technique reduces hallucinations by grounding a model's answers in your own trusted documents at query time?

Accepted Answer

Retrieval-Augmented Generation (RAG) RAG retrieves relevant content from your data and supplies it to the model as context, grounding responses in facts. Fine-tuning changes the model itself and is heavier and slower.

Question 3

Ensuring an AI model does not systematically disadvantage particular groups of people relates to which responsible-AI dimension?

Accepted Answer

Fairness and bias Fairness and bias concern whether a model treats groups equitably. It's a core responsible-AI dimension the exam expects you to recognise, alongside transparency and safety.

Question 4

What is the primary benefit of Retrieval Augmented Generation (RAG)?

Accepted Answer

It grounds model responses in external, up-to-date knowledge RAG retrieves relevant information from an external knowledge base at inference time and adds it to the prompt context, grounding responses in current, factual data without retraining the model.

Question 5

What is dataset augmentation in the context of ML?

Accepted Answer

Creating modified versions of existing data to increase training set size and diversity Data augmentation creates new training samples by transforming existing data — rotating images, adding noise, paraphrasing text — to increase dataset size and diversity without collecting new data, helping prevent overfitting.

Question 6

What is a foundation model?

Accepted Answer

A large model pre-trained on broad data that can be adapted to many tasks A foundation model is a large-scale model pre-trained on vast, diverse data that serves as a base for many downstream tasks through fine-tuning or prompting — unlike narrow, task-specific models.

Free AWS AI Practitioner (AIF-C01) questions

What these free questions cover

Lila Wolke Creator