CCDV-F practice › Applications & Integration · Question 34 of 92
Applications & Integration
An app must process scanned insurance cards that patients photograph with their phones. Which capability is required?
Show answer and explanation
Answer: A — Vision — images as input
Vision accepts images as input for document and screenshot understanding. The other three are about latency, reasoning depth, and cost — none of them let the model read a photograph.
Keep going
More Applications & Integration questions
- A team wants to reduce cost on a workload where the same 8,000-token clinical guidelines…
- Which statement about the Message Batches API is correct?
- A refactor moves the system prompt from a hardcoded string into a versioned file with…
- Two users of a multi-tenant assistant occasionally see fragments of each other's…
- Where does the CLAUDE.md file sit in a team's configuration, and what is it for?