MCQ | Gen AI Academy APAC Edition | Hack2skill
Data is moving faster than ever—and tools like BigQuery and AI are evolving to keep up. From real-time processing and event-driven pipelines to vector search and generative modeling, understanding these concepts is becoming essential for modern data workflows.In this quick quiz-style guide, we break down key concepts across BigQuery, AI agents, and machine learning—making it easy to test your knowledge and sharpen your understanding in just a few minutes.
Q1. In BigQuery Continuous Queries, which type of processing is supported?
- Aggregations with GROUP BY
- ✔ Stateless row-level transformations
- Multi-table JOIN operations
- Window functions with partitions
Q2. Which operation is commonly used in Continuous Queries to write processed results?
- SELECT INTO
- ✔ INSERT INTO
- MERGE TABLE
- UPDATE STREAM
Q3. In an event-driven pipeline using BigQuery, what typically triggers processing?
- A scheduled cron job
- A manual query execution
- ✔ Arrival of new data in the source
- Completion of a dashboard refresh
Q4. In the ADK-based Data Analyst Agent, what defines the agent’s behavior?
- The database schema only
- ✔ The agent’s prompt, purpose, and instructions
- The size of the dataset
- The cloud region
Q5. Why does a schema-aware agent produce more reliable SQL queries?
- It memorizes previous queries
- It generates queries without validation
- ✔ It understands the actual structure of tables before generating queries
- It avoids using SQL entirely
Q6. What is the primary advantage of connecting an AI agent to BigQuery instead of using static datasets?
- Faster internet speed
- ✔ Access to dynamically updated, large-scale datasets
- Elimination of query costs
- Removal of schema requirements
Q7. In the multimodal workflow, what is the role of feature extraction from images?
- Compressing image size
- ✔ Converting images into structured attributes for analysis
- Deleting irrelevant images
- Improving network speed
Q8. In BigQuery ML, what is the purpose of using K-means clustering?
- Predicting future values
- ✔ Grouping similar data points without predefined labels
- Cleaning missing data
- Joining multiple tables
Q9. In a vector-based search system, how are similarity results typically determined?
- Exact keyword matching
- Sorting by timestamp
- ✔ Distance between vector embeddings
- File size comparison
Q10. When using generative AI to create a data science model from a prompt, what is the key benefit?
- Eliminates need for any validation
- ✔ Automatically generates model logic based on high-level intent
- Removes need for data
- Guarantees perfect accuracy