Ethics & Safety · Advanced
Amazon Bedrock Guardrails: Filters, PII, Grounding and Automated Reasoning
Configurable safeguards that sit between your users and any model — including a formal-methods check that can prove a response contradicts your policy.
- 45 min lesson
- intermediate level
- AWS AI Track
- Narrated presentation
What you’ll learn
- Attaching guardrails at inference vs the standalone ApplyGuardrail API
- Content filters, denied topics, word filters, sensitive information filters
- Contextual grounding checks against retrieved sources
- Automated Reasoning checks: formal rules over probabilistic scoring
- Standard tier extending detection into code elements
- Input tagging for selective evaluation; guardrail versioning and red-team sets
Inside this lesson
A narrated, slide-by-slide presentation with 1 prediction exercise, 1 knowledge check, 4 videos. You answer as you go, and the platform checks your work.