A team building a Foundry-hosted loan-eligibility assistant plans to roll it out to loan officers across the country. Before launch, they want to check whether the assistant's approval recommendations are less accurate for some demographic groups of applicants than others, so that no group experiences a systematically higher error rate. Which practice directly addresses this concern?

The correct practice is performing a fairness assessment that compares the model's performance across demographic subgroups. A fairness assessment specifically measures whether a model's accuracy, error rates, or outcomes differ across demographic groups such as age, gender, or ethnicity, which is exactly the risk this loan-eligibility team is worried about before a nationwide launch. The option that lowers the temperature is incorrect because temperature only affects how varied the wording of a response is; it does nothing to reveal or correct differences in decision accuracy between groups. The option that increases the context window is incorrect because a larger context window lets the model consider more input text per request, but it does not measure or fix uneven error rates across populations of applicants. The option that adds a content safety filter is incorrect because content safety filtering targets harmful or offensive language in generated text, which is a separate concern from whether the underlying loan decisions are equitable across groups. Since the team's stated goal is confirming that no demographic group is disproportionately disadvantaged by the model's recommendations, the responsible AI practice built for exactly that purpose, a fairness assessment across subgroups, is the appropriate step before production release.