AI Practitioner Practice Questions
Prepare for AIF-C01 with more than an answer.
- Exam fee
- $100 USD
- Level
- Foundational
- Valid for
- 3 years
Domains covered on the exam 5
- Fundamentals of AI and ML20%
- Fundamentals of Generative AI24%
- Applications of Foundation Models28%
- Guidelines for Responsible AI14%
- Security, Compliance, and Governance for AI Solutions14%
- 1
A financial services company is building a customer service chatbot using a Large Language Model (LLM) on Amazon Bedrock. The company requires that the chatbot strictly answers questions based only on the provided internal policy documents and must not use outside knowledge or hallucinate facts. Which architectural pattern should the developers implement to meet this requirement?
Show answer details
Correct answer: B
Retrieval Augmented Generation (RAG) allows the model to retrieve relevant information from a trusted knowledge base (the internal policy documents) and generate an answer based solely on that context. This significantly reduces hallucinations and ensures answers are grounded in company data.
flowchart LR User[User Question] --> Ret[Retriever] KB[(Knowledge Base)] --> Ret Ret --> Context[Context + Prompt] Context --> LLM[LLM] LLM --> Answer[Grounded Answer] - 2
A data scientist is preparing a dataset for a supervised machine learning model to predict housing prices. The dataset contains features such as 'square footage', 'number of bedrooms', and 'zip code'. The 'zip code' feature is categorical but represented as numbers. How should the data scientist process the 'zip code' feature for the model to interpret it correctly?
Show answer details
Correct answer: B
Zip codes are nominal categorical data where the numerical magnitude has no mathematical meaning (e.g., zip code 90210 is not 'greater than' 10001). One-Hot Encoding converts these categories into binary vectors, allowing the model to treat them as distinct groups without inferring an ordinal relationship.
- 3
A healthcare organization is building a generative AI application to summarize patient records. They are concerned that the model might inadvertently reveal Personally Identifiable Information (PII) in its output. Which Amazon Bedrock feature should they configure to automatically detect and block PII from appearing in the model's responses?
Show answer details
Correct answer: B
Guardrails for Amazon Bedrock allows users to define policies that filter undesirable content, including PII redaction. You can configure it to detect and mask or block PII entities such as names, email addresses, and phone numbers in both prompts and responses.
- 4
True or False: In a Retrieval Augmented Generation (RAG) architecture, the 'Retrieval' step occurs after the Large Language Model (LLM) has generated its response.
Show answer details
Correct answer: B
False. In RAG, retrieval happens before generation. The system first retrieves relevant documents based on the user's query, augments the prompt with this context, and then sends it to the LLM to generate the response.
- 5
An e-commerce company wants to build a recommendation engine that suggests products based on a user's past purchase history. The model needs to predict a specific numeric value: the probability (between 0 and 1) that a user will buy a specific item. Which type of Machine Learning problem is this?
Show answer details
Correct answer: B
Predicting whether a user will buy an item is a binary outcome (Buy/No Buy). While the output is a probability score (0 to 1), the fundamental task is Binary Classification. If the goal was to predict a continuous value like 'total spend amount', it would be regression.
- 6
A developer is designing a solution to process customer support emails. The system needs to analyze the sentiment of the email (Positive, Negative, Neutral) and extract key entities like 'Order Number' and 'Product Name'. Which AWS service is BEST suited for this task without requiring custom model training?
Show answer details
Correct answer: B
Amazon Comprehend is a Natural Language Processing (NLP) service that uses machine learning to uncover insights in text. It specifically provides pre-trained APIs for Sentiment Analysis and Entity Recognition, meeting the requirements without custom training.
- 7
A company makes forecasts each quarter to decide how to optimize operations to meet expected demand. The company uses ML models to make these forecasts.An AI practitioner is writing a report about the trained ML models to provide transparency and explainability to company stakeholders.What should the AI practitioner include in the report to meet the transparency and explainability requirements?
Show answer details
Correct answer: B
- 8
A law firm wants to build an AI application by using large language models (LLMs). The application will read legal documents and extract key points from the documents.Which solution meets these requirements?
Show answer details
Correct answer: C
