Hands-on playbook · 55 min
Cloud AI Guardrails Playbook: Bedrock Guardrails, Azure Prompt Shields and Model Armor in Detect Mode, Then Enforced
A hands-on guide to the three big clouds' guardrail services, checked against their documentation and AWS's API models: a Bedrock guardrail validated against the service model, ApplyGuardrail and grounding checks, Prompt Shields for documents, Model Armor templates and floor settings, and the gaps each leaves open.
- A Bedrock guardrail in detect mode, validated against AWS's own API model
- What Bedrock does not inspect: tool results, tool definitions and untagged prompts
- Prompt Shields for retrieved documents: five documents, 10K characters, true or false
- Model Armor templates, inspect-only mode and floor settings for the organisation
- Why Model Armor can say NO_MATCH_FOUND when nothing ran, and how to catch it
- One tested function that turns three providers' answers into one decision
- Forcing callers to use a guardrail with IAM, and a 90-day rollout
- 01Under the hood
- 02Hands-on lab
- 03Recipes
- 04Rollout runbook
- 05Troubleshooting
- 06Interview drill
- 07Sources
Every worked answer in all 17 topics, every lesson in every course, the full concept curriculum, hands-on tool playbooks, the complete practice-test bank, and the downloadable security field guides.
6 months · One payment · No auto-renewal
An independent playbook for interview preparation and learning. AISecurityInterviews is not affiliated with or endorsed by Amazon Web Services, Microsoft, Google Cloud, and product names are trademarks of their owners. Use these procedures only on systems you own or are authorised to test, and check the vendor's documentation before changing production.