A financial services company has an assistant that already answers customer questions reasonably well through prompt engineering, but compliance reviewers keep flagging that responses inconsistently use the company's exact required disclosure wording across thousands of daily conversations. Adjusting the prompt has not fixed the inconsistency. Which next step in Microsoft Foundry is most appropriate?

Fine-tuning the model on a large set of example conversations that consistently pair questions with the correctly worded disclosures is the most appropriate next step because it trains the model's weights on many labeled examples that consistently pair customer questions with the exact required disclosure wording. This addresses a pattern the team needs enforced across thousands of interactions in a way that prompt adjustments alone have failed to achieve. Lowering the model's temperature to zero is incorrect because it reduces randomness in phrasing but does not teach the model the specific disclosure language it is missing; a deterministic model can still be deterministically wrong. Switching to a smaller, cheaper model is incorrect because it addresses cost, not consistency, and a smaller model is not inherently more likely to include specific required wording; it may in fact perform worse without additional training. Adding the disclosure text to the system prompt in even larger font is incorrect because font size is a formatting concept with no effect on a language model, which does not perceive visual emphasis in a system prompt; the underlying instruction is processed as plain text regardless of styling. Since the problem is a recurring pattern that prompt engineering has not resolved, fine-tuning on representative examples is the tool built to bake that pattern into the model's behavior.