Amazon Bedrock AgentCore Memory now supports metadata on long-term memory (LTM) records, enabling agents to tag, filter, and retrieve memories using structured attributes alongside semantic search. You can define up to ten indexed keys per memory resource – with support for STRING, NUMBER, and STRING_LIST types – and use different operator types to filter retrieval results.
Metadata can be attached to events at ingestion time or inferred automatically by the LLM based on extraction instructions you define on the memory resource. During ingestion, the LLM processes all events and determines how metadata is applied to the resulting memory records.
You define a metadata schema on the memory resource that includes indexed key definitions (key name, type, and optional allowed values) along with extraction instructions that guide the LLM on how to generate metadata from conversation content. With metadata filters on retrieval – agents can retrieve records by structured attributes like ticket number, priority, or date – eliminating irrelevant context and improving response accuracy.
To get started, see the Amazon Bedrock AgentCore Memory documentation. This feature is available today in all AWS Regions where Amazon Bedrock AgentCore Memory is supported.
Categories:
Source: Amazon Web Services
Latest Posts
- (Updated) Copilot Cowork generally available today [MC1393471]
- (Updated) Collect Diagnostics change to Get Diagnostics for Outlook Mobile and Mac [MC1308855]
- (Updated) Smart Calendar available in Classic Outlook for Microsoft 365 Copilot users [MC1181279]
- Amazon Bedrock Guardrails announces a new API targeting agentic AI workflows
