Artificial Intelligence1 min read

Customize answers per tenant in Amazon Bedrock Managed Knowledge Base

By · Published by Everything Blog

In short

Amazon Bedrock Managed Knowledge Base has introduced retrieval instructions that govern how responses are shaped for different tenant groups. The instructions are managed and versioned within an AWS account and Region using four configurable fields: persona, answerFormat, retrievalGuidance, and answerPolicy. Furthermore, queries utilizing agentic retrieval can search across up to five knowledge bases concurrently under a single tenant instruction set.

Key points

  • Centralized retrieval instructions replace the need to manually build custom prompts acro…: Centralized retrieval instructions replace the need to manually build custom prompts across disconnected external applications.
  • Retrieval instructions govern response presentation and tone rather than acting as a data…: Retrieval instructions govern response presentation and tone rather than acting as a data security boundary.
  • Administrators must rely on metadata filters or segregated knowledge bases to enforce str…: Administrators must rely on metadata filters or segregated knowledge bases to enforce strict tenant data isolation.

Sources checked by our analysis pipeline: 1

Artificial Intelligence

Customize answers per tenant in Amazon Bedrock Managed Knowledge Base

With retrieval instructions in Amazon Bedrock Managed Knowledge Base, you can customize answers per tenant. The same product and policy documents often serve several audiences, such as customers in different regions or internal teams, and each audience needs its own answer. You set the voice, format, retrieval guidance, and answer policy that agentic retrieval applies to each request. Before this feature, you couldn’t set the answer style, so agentic retrieval could use a different style from one request to the next. For a fixed voice or structured output, you had to turn off response generation, call a model yourself, and maintain the prompt in every application.

Now you write that guidance once, as a managed, versioned Amazon Bedrock resource, and each request references it. When you change an instruction, you can pin a version so that each application switches to the new version when you’re ready.

Take AnyCompany Smart Home, a fictitious company that sells a home controller and room sensors in three sales regions. Its customer assistant…

Artificial Intelligence