A team has finished prototyping a Foundry-hosted chatbot for internal HR questions and is preparing to move it into production for all employees. Before launch, which two actions should they take? (Select TWO.)
Select all correct answers, then click Submit.
Short Explanation
When you're moving a prototype into production, you need to prove it works and put guardrails on it. Run the evaluation tools against real HR questions to check groundedness and relevance, and turn on content safety filtering so it doesn't go off the rails. Don't delete logging entirely, and don't shove the key into client-side JavaScript where anyone can grab it.
Full Explanation
The correct actions are running Foundry's built-in evaluation tools against representative HR questions and configuring content safety filtering on the deployment. Evaluation measures whether the chatbot's answers are grounded in the intended source material and relevant to what employees actually ask, catching quality problems before a companywide rollout, and content safety filtering reduces the risk that the deployment produces harmful or inappropriate output once every employee can reach it. Both are standard readiness steps before widening access to a production audience. Removing all logging is incorrect because it does not improve quality or safety; it instead strips the team of the diagnostic trail needed to investigate reported problems after launch, and reasonable logging can coexist with privacy safeguards rather than requiring its complete elimination. Hardcoding the deployment's API key directly into client-side JavaScript served to every employee's browser is incorrect because embedding an API key in client-side code exposes that key to anyone who inspects the page, letting it be extracted and misused outside the intended application; API keys belong in a protected backend, not shipped to end-user browsers.