A financial services firm wants its Foundry-hosted assistant to answer employee questions about the exact figures in this quarter's internal earnings report, which is replaced with new numbers every three months. The team is deciding how to give the model access to these figures so answers stay accurate as the report changes each quarter, without retraining a model every time. Which approach best fits this need?
Select an answer to reveal the explanation.
Short Explanation
You need the assistant to look up the current earnings report each time, not memorize it. Retrieval-augmented generation with Azure AI Search lets it fetch the live document at query time, so a new quarter just means updating the index. Retraining or tweaking output length or randomness won't keep the figures current.
Full Explanation
The retrieval-augmented generation approach using Azure AI Search is the best fit because it lets the assistant pull the actual text of the current quarter's report from an index at the moment a question is asked, so the model answers from the live document rather than from what it happened to memorize during training. When the report changes next quarter, the team only needs to update the index, not retrain anything. The fine-tuning approach is incorrect because training on this quarter's numbers bakes them into model weights that go stale the moment a new report is issued, requiring a costly retraining cycle every three months just to stay current. The larger maximum output token limit approach is incorrect because output token limits control how long a response can be, not whether the model has access to accurate source figures; a longer response built on a model's guesswork is still inaccurate. The higher temperature approach is incorrect because raising temperature increases the randomness and creativity of wording, which works against precise numeric recall rather than improving it, and could make the assistant less consistent on exactly the figures that must be exact. Grounding the assistant in the current report through retrieval is the approach that keeps answers accurate as the source data changes on its own schedule.