Episode Description
We dig into how to make that magic reliable, sharing a practical blueprint for building trustworthy AI on Microsoft Foundry with guest Microsoft AI MVP, Liji Thomas.
From there, we tour Microsoft Foundry’s control plane and show how to configure guardrails at model and agent levels to block PII, reduce jailbreaks, and filter harmful or protected content. We explore observability and evaluations for groundedness, coherence, and relevance, plus why an evaluation-driven approach matters most after deployment.