Guardrails
ThinkWork uses Amazon Bedrock Guardrails as the primary enforcement layer for managed agents.
What guardrails do
Section titled “What guardrails do”Guardrails are evaluated around model invocation and can:
- block disallowed topics
- filter unsafe content
- detect or redact PII
- apply grounding checks
- enforce word or phrase filters
Where they are configured
Section titled “Where they are configured”Guardrails are referenced from agent templates, which lets you apply the same safety boundary across a fleet of agents.
That keeps enforcement in one place instead of scattering it across prompts.
What happens on a guardrail hit
Section titled “What happens on a guardrail hit”When a guardrail blocks or alters a response, the resulting event is visible in ThinkWork’s thread and control surfaces.
This matters for debugging because you can distinguish:
- model behavior
- tool behavior
- policy enforcement