With Denied Topics in Amazon Bedrock Guardrails, you block a content category by describing it in plain language, and the guardrail applies that description to every request by meaning rather than by keyword. That same mechanism can also match more than you intend. A topic named Finance, meant to keep an assistant out of investment advice, also blocks “When does my direct deposit clear?”. Inputs close in meaning to the topic can get caught, not only the requests you intended.
When Denied Topics blocks too much or too little, the cause is usually one of four authoring patterns:
The rest of this post is a practical guide to avoiding these patterns. It presents eight best practices for describing a topic precisely enough that the guardrail blocks what you mean and passes what you don’t.
To ground the following practices in something concrete, we use one running example throughout this post: a fictional bank we call AnyCompany Bank. AnyCompany Bank is two weeks from launching its first customer-facing AI assistant, and its first pass at the Denied Topics policy is blocking the wrong things.
Application: AnyCompany Bank’s chatbot is embedded in the AnyCompany Bank mobile and web app. It answers questions about accounts, statements, transfers, cards, and mortgages. It hands off to a human for account changes, dispute filings, and questions outside its scope.
Against that target, AnyCompany Bank’s team first drafted four topics, all of them currently blocking legitimate queries:
Every one of these topics names a subject domain the assistant works in, rather than the intention the bank needs to refuse.
Source link







