Skip to content

Best Practices for Writing Denied Topics in Amazon Bedrock Guardrails

AWS Machine Learning BlogFrom the source· Jian Zhang·· 9 hours agoPicksBest practices for writing Denied Topics in Amazon Bedrock Guardrails
Original
Image: AWS Machine Learning Blog
Who
AWS
What
explains best practices for authoring denied topics Amazon Bedrock Guardrails
Quote
The rest of this post is a practical guide to avoiding these patterns.

What happened

AWS authors present eight practices for writing Denied Topics in Amazon Bedrock Guardrails, using a fictional bank assistant to show how broad subject labels can block legitimate requests. They recommend action-scoped names and definitions, varied boundary examples, careful management of overlapping topics, and using other Guardrails policies for signals such as prompt attacks or exact terms. Results can still vary for borderline inputs and when the topic list changes.

Why it matters

Teams can reduce false blocks and missed matches by defining denied topics around user actions, using varied boundary examples, and managing overlap; repeated tests still matter because results can vary for borderline inputs and when topic lists change.

Read next

See the full storyAWS Details Best Practices for Writing Denied Topics in Amazon Bedrock Guardrails

The story so far

AWS published a guide on the AWS Machine Learning Blog outlining eight best practices for writing Denied Topics in Amazon Bedrock Guardrails. Using a fictional bank assistant as an example, the authors showed how broad subject labels can inadvertently block legitimate user requests. To prevent over-blocking, the authors recommend using action-scoped topic names and definitions, providing varied boundary examples, and carefully managing overlapping topics. They also advise using other Guardrails policies to handle signals such as prompt attacks or exact terms, noting that results can still vary for borderline inputs and when the topic list changes.

This story is in 11/17 AI DailyRead the whole issue