Applications of Foundation Models

Exam objectives are the official skill domains AWS Certified AI Practitioner tests. Below are the official AWS docs our questions on this objective cite — review them, then practise.

Practise these 37 questions →

Official references for this objective

Amazon Web Services — Implementing advanced prompt engineering with Amazon Bedrock | Artificial Intelligence

Prompt leaking occurs when an unauthorized user aims to leak the details or instructions from the original prompt.
Amazon Web Services — Amazon Bedrock Is Now Generally Available – Build and Scale Generative AI Applications with Foundation Models | AWS News Blog

The modelId parameter identifies the FM you want to use.
Amazon Web Services — Prompt engineering techniques and best practices: Learn by doing with Anthropic’s Claude 3 on Amazon Bedrock | Artificial Intelligence

Prefill Claude’s response – Claude tends to be chatty in its answers, and might add some extra sentences at the beginning of the answer
Amazon Web Services — Best practices for building robust generative AI applications with Amazon Bedrock Agents – Part 1 | Artificial Intelligence

Ground your data in real customer interactions that reflect actual use cases but be sure to de-identify and anonymize the data.
Amazon Web Services — Evaluate and improve performance of Amazon Bedrock Knowledge Bases | Artificial Intelligence

prioritize refining the retrieval mechanism before addressing generation. Upstream performance directly influences downstream metrics, making retrieval optimization critical.
Amazon Web Services — Dive deep into vector data stores using Amazon Bedrock Knowledge Bases | Artificial Intelligence

By using multilingual language models or cross-lingual embeddings, vector databases can facilitate effective retrieval across different languages
Amazon Web Services — Customize your model to improve its performance for your use case - Amazon Bedrock

You are charged for model training based on the number of tokens processed by the model (number of tokens in training data corpus × number
Amazon Web Services — Prompt injection security - Amazon Bedrock

This is a lightweight prompt that uses a foundation model to determine if user input is safe to be processed.
Amazon Web Services — Improve AI assistant response accuracy using Knowledge Bases for Amazon Bedrock and a reranking model | Artificial Intelligence

Reranking seeks to improve search relevance by reordering the result set returned by a retriever with a different model.