AWS publishes guide on writing denied topics for Bedrock Guardrails
Understand this story
AWS publishes a summary of eight best practices for writing Denied Topics in Amazon Bedrock Guardrails, saying over-blocking or missed blocking usually stems from four types of writing: defining by topic domain rather than user intent, using keyword lists instead of semantic descriptions, examples that teach the wrong boundary, and overlapping definitions across multiple topics. The article targets users configuring denied topics with Bedrock Guardrails and offers writing advice; it does not publish measured results such as blocking accuracy.
AI overview based on source reports · Updated 1 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- AWS Machine Learning BlogBest practices for writing Denied Topics in Amazon Bedrock Guardrails
This post explains why Denied Topics in Amazon Bedrock Guardrails can block too much or too little, attributing failures to four authoring patterns: domain-framed topics, keyword-list definitions, paraphrased examples, and overlapping topics. It presents eight best practices—framing topics around user intention, choosing actionable names, writing action-scoped definitions, using boundary examples, anchoring ambiguous concepts, and managing topic overlap and count—illustrated with a running AnyCompany Bank customer-assistant scenario. It notes that results are not fully deterministic regardless of how well the practices are followed.
Activity for this story
- Current comparable activity
- 4
- Peak comparable activity
- 10Nov 17 01:00
- Change in the past 24 hours
- -51%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.