A community-theater director wants to ask natural-language questions of ticket and concession tables and see dashboards. The director is not asking to train a new foundation model. Which AWS offering matches this job?
Select an answer to reveal the explanation.
Short Explanation
Think of asking ticket tables questions in English and seeing dashboards. That is Amazon Quick. The director is not training a vision model, routing FMs, or reading totals in an IDE.
Full Explanation
Amazon Quick matches a community-theater director who wants natural-language questions over ticket and concession tables plus dashboards. That is AI-assisted analytics and visibility on business data—not a request to train a new foundation model. The exam maps conversational analytics on organizational tables to Quick, which fits directors who need answers and charts without becoming ML engineers.
Amazon SageMaker AI for a custom vision model invents a computer-vision training job the director did not ask for; charts on tabular sales are not “train a vision model.” Amazon Bedrock AgentCore is about running and operating agents in production, not director-facing ticket dashboards. Kiro is a developer IDE for building prototypes; it is not where directors read concession totals day to day.
Exam caveat: conversational analytics still depends on governed data access—natural language does not bypass row-level permissions or PII rules on patron tables. Operational check: connect only approved ticket and concession datasets, verify dashboard answers against a known query, restrict who can ask questions that surface personal patron fields, and leave custom model training out of this path.