A software company's internal helpdesk assistant, built in Microsoft Foundry, answers routine questions about VPN setup and password resets. During testing, the team asks the exact same question multiple times and notices the wording, and sometimes even the recommended steps, change each time. For this use case they want the assistant to give the same, predictable answer whenever the input is identical. Which setting should they adjust to achieve this?

Lowering the temperature setting used when generating responses is correct because temperature controls how much randomness the model injects when choosing its next words; lowering it makes the model favor its highest-probability response each time, which produces the consistent, repeatable wording and steps this helpdesk assistant needs for identical questions. Increasing the maximum token limit for each response is incorrect because the max token limit only caps how long a response can be; it does not make repeated answers more similar to one another. Switching to a model with a larger context window is incorrect because context window size determines how much conversation or document text the model can consider at once, not how deterministic its wording is from one run to the next. Raising the severity threshold on the content safety filter is incorrect because content safety severity thresholds govern whether potentially harmful content is blocked or allowed through, which has nothing to do with variability in phrasing or steps for a benign VPN or password question. Since the reported problem is inconsistent phrasing and inconsistent steps for the same factual query, the fix belongs to the parameter that governs randomness in generation, not to length limits, context capacity, or safety filtering.