10-question AI Practitioner diagnostic

Fundamentals of Generative AI

An insurance company wants an application where claims adjusters upload a photo of vehicle damage together with a text question such as "Describe the damaged parts and estimate severity," and receive a natural-language answer that reasons over both the photo and the question. Which type of foundation model does this require?

• AA text-only large language model
• BA multimodal model that accepts both image and text input
• CA text embeddings model
• DA text-to-image generation model