Meridian wants a system that maintenance and dispatch staff can ask natural-language questions of, drawing on the airline's maintenance manuals and dispatch procedures, and receive a synthesized, readable answer rather than a list of document links. Which technology is an appropriate fit, and why?
Select an answer to reveal the explanation.
Short Explanation
GenAI is built to read a pile of manuals and hand back a plain-English answer — that's its home turf, not grouping documents or chasing a delay-prediction reward.
Full Explanation
This is a textbook fit for generative AI / LLM-based technology: LLMs excel at synthesizing natural-language answers from a body of text, which is exactly what "ask a question, get a readable answer drawn from the manuals" requires. Clustering is wrong because grouping documents into unlabeled segments does not answer a specific natural-language question — it organizes content, it doesn't respond to it. A reinforcement learning agent trained on flight-delay outcomes is wrong and a non-sequitur — that reward signal has nothing to do with answering documentation questions, and RL is not the right tool for this kind of language task. Keyword search alone is wrong because a keyword index returns matching documents or passages, not a synthesized natural-language answer — this is precisely the gap generative AI closes. Recognizing GenAI as the right pattern here is a Domain III enabler: matching an appropriate application to generative AI technology.