A team must expand evaluation coverage for a multi-agent benefits advisor before open enrollment. Real labeled production transcripts are scarce because of privacy constraints. They need diverse scenarios (edge cases, adversarial phrasings, multi-turn tool paths) to test prompts, tools, and memory. Which continuous-improvement technique best addresses the gap?
Select an answer to reveal the explanation.
Short Explanation
Privacy limits real transcripts, so synthetic data generation fills coverage—including edge and adversarial cases—then you evaluate memory, tools, prompts, and knowledge systematically. Three happy paths forever miss risk. Shipping blind is reckless. One executive demo is not a test strategy. C is the technique.
Full Explanation
Correct answer: C. Continuous improvement includes synthetic data generation to broaden evaluation coverage when real labeled data is limited. Evaluations should span memory, knowledge, tools, and prompts—the exam’s evaluation surface for multi-agent solutions—using privacy-safe synthetic and adversarial cases.
A is incorrect because tiny static happy-path sets fail to detect regressions on edge and multi-turn tool paths.
B is incorrect because waiting for production incidents is not an evaluation strategy.
D is incorrect because informal demo clicks lack coverage, repeatability, and scoring rigor.
Exam focus: synthetic data enables scalable multi-agent eval under data constraints.