AWS shares 8 best practices for writing Denied Topics in Bedrock Guardrails

AWS ML Blog · rss · 2026-11-16

AWS ML Blog published a practical guide to authoring Denied Topics in Amazon Bedrock Guardrails, where topics described in plain language match by meaning rather than keyword — and often over-block, e.g. a "Finance" topic catching "When does my direct deposit clear?"

Four common failure modes

Core practices

Structure: each topic has a name (≤100 chars), definition (≤1000 chars, 100–300 sweet spot), and up to 5 examples (≤100 chars each); guardrails hold up to 30 topics, and results are not fully deterministic.

Original post →

More from coding & agent

coding & agent channel →