A multi-agent media pipeline includes (1) language detection on short strings, (2) multi-hop legal reasoning over contracts, and (3) creative storyboard prose. The architect must assign model families without overspending. Which matching strategy is most appropriate?
Select an answer to reveal the explanation.
Short Explanation
The correct answer is D. Match capacity to the job: tiny/efficient for language detection, heavy reasoning for multi-hop legal work, generative strength for storyboards. One giant model for detection wastes money. Regex alone will not do multi-hop legal reasoning. Embedding-only models do not write storyboards.
Full Explanation
Option D is correct. Architect skills include matching task demands to model family capacities. Heterogeneous multi-agent pipelines should route simple classification/detection to efficient models and reserve frontier reasoning or generative capacity for tasks that need them.
Option A is incorrect because using the largest reasoning model for trivial detection inflates cost and latency without quality benefit.
Option B is incorrect because regular expressions cannot perform multi-hop legal reasoning over unstructured contracts.
Option C is incorrect because embedding-only models do not generate creative storyboard prose.