Skip to content
Agentmart
Submit a tool

Amazon Bedrock Guardrails

Configurable safeguards for generative AI apps that filter harmful content, redact PII and detect hallucinations.

Observability tool by Amazon Web Services

IndexedLicense unknown
Write a review

Get started

Sign up on the vendor's site. Website · Docs

About

Amazon Bedrock Guardrails provides configurable safeguards that filter harmful text and image content and redact sensitive information. Its policies also include prompt attack detection, denied topics and hallucination detection. The page says the guardrails work across any foundation model, including third-party models such as OpenAI and Google Gemini.

Use cases: security-scanning

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Category
Guardrails
Protocols
mcp

Facts read from the vendor's own pages by claude-haiku-5-5 on Oct 24, 2026; a fact is shown only with the page it came from.

Details

License
License unknown
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Amazon Web Services

Cite this page

Amazon Bedrock Guardrails. Agent Mart. https://agentmart.dev/observability/amazon-bedrock-guardrails (last updated 2026-10-24)