AWS bedrock-agentcore documentation change
Summary
Restructured memory strategies documentation with new sections for built-in overrides and self-managed strategies, added cost/comparison details, and reorganized strategy implementation guidance
Security assessment
Changes focus on architectural implementation details, strategy types, and cost considerations rather than security controls. No mention of vulnerabilities, access controls, encryption, or security best practices. The modifications primarily clarify operational aspects of memory management strategies.
Diff
diff --git a/bedrock-agentcore/latest/devguide/memory-strategies.md b/bedrock-agentcore/latest/devguide/memory-strategies.md index b9030b7a1..d580566bf 100644 --- a//bedrock-agentcore/latest/devguide/memory-strategies.md +++ b//bedrock-agentcore/latest/devguide/memory-strategies.md @@ -5 +5 @@ -Amazon Bedrock AgentCore is in preview release and is subject to change. +Built-in strategiesBuilt-in overrides Self-managed strategies: @@ -9 +9 @@ Amazon Bedrock AgentCore is in preview release and is subject to change. -Memory strategies define how your AI agent processes information from conversations into long-term memory. They decide what type of information is kept, turning raw conversations into structured and useful knowledge. With AgentCore Memory, you need to add memory strategies in `CreateMemory` or `UpdateMemory` operation so that it can be used for long-term memory extraction. You can choose: +In AgentCore Memory, you can add memory strategies to your memory resource. These strategies determine what types of information to extract from raw conversations. Strategies are configurations that intelligently capture and persist key concepts from interactions, sent as events in the [CreateEvent](https://docs.aws.amazon.com/bedrock-agentcore/latest/APIReference/API_CreateEvent.html) operation. You can add strategies to the memory resource as part of [CreateMemory](https://docs.aws.amazon.com/bedrock-agentcore-control/latest/APIReference/API_CreateMemory.html) or [UpdateMemory](https://docs.aws.amazon.com/bedrock-agentcore-control/latest/APIReference/API_UpdateMemory.html) operations. Once enabled, these strategies are automatically executed on raw conversation events associated with that memory resource to extract long-term memories. @@ -11 +11 @@ Memory strategies define how your AI agent processes information from conversati - * **Built-in strategies** : AgentCore Memory allows you to add the following built-in memory strategies: +If no strategies are specified, long-term memory records will not be extracted for that memory. @@ -13 +13 @@ Memory strategies define how your AI agent processes information from conversati - * _SemanticMemoryStrategy_ : Stores facts and knowledge mentioned in the conversation for future reference +AgentCore Memory supports a variety of memory strategies: @@ -15 +15 @@ Memory strategies define how your AI agent processes information from conversati - * _SummaryMemoryStrategy_ : Stores a running summary of a conversation, capturing main points and decisions, scoped to a session (through namespace). +## Built-in strategies @@ -17 +17 @@ Memory strategies define how your AI agent processes information from conversati - * _UserPreferenceMemoryStrategy_ : Stores user preferences, choices, or styles (e.g., preferred coding style, or shopping brand) +AgentCore handles all memory extraction and consolidation automatically with predefined algorithms. @@ -19 +19 @@ Memory strategies define how your AI agent processes information from conversati -###### Note + * AgentCore handles all memory extraction and consolidation automatically @@ -21 +21 @@ Memory strategies define how your AI agent processes information from conversati -When using built-in strategies, all extraction and consolidation processes are managed by AgentCore Memory itself in a service-managed account. No extra setup is required from your side. + * No configuration required beyond basic trigger settings @@ -23 +23 @@ When using built-in strategies, all extraction and consolidation processes are m -###### Note + * Uses predefined algorithms optimized and benchmarked for common use cases @@ -25 +25 @@ When using built-in strategies, all extraction and consolidation processes are m -Built-in strategies may use cross-region inference. AgentCore Memory will automatically select the optimal region within your geography to process your inference request, maximizing available compute resources and model availability, and providing the best customer experience. There's no additional cost for using cross-region inference. + * Suitable for standard conversational AI applications @@ -27 +27 @@ Built-in strategies may use cross-region inference. AgentCore Memory will automa - * **Custom strategies** : Custom memory strategy (CustomMemoryStrategy) lets you override the prompts and choose the LLM to tailor the memory extraction and consolidation to your specific domain or use case. For example, you might want to override the semantic memory prompt so that it constrains extracted memories to specific types of facts. + * Limited customization options @@ -29 +29 @@ Built-in strategies may use cross-region inference. AgentCore Memory will automa -###### Note + * Higher cost for storage @@ -31 +31,46 @@ Built-in strategies may use cross-region inference. AgentCore Memory will automa -When using custom strategies, the LLM usage for extraction and consolidation will be charged separately to your AWS account, and additional charges may apply. + + + +## Built-in overrides + +Extends built-in strategies with targeted customization while using an AgentCore managed extraction pipeline. + + * Extends built-in strategies with targetted customization + + * Allows modification of prompts while still using AgentCore managed extraction pipeline + + * Provides support for bedrock models (invoked in your account) + + * Lower cost for storage than built-ins + + + + +## Self-managed strategies: + +You have complete ownership of memory processing pipeline with custom extraction and consolidation algorithms. + + * Complete ownership of memory processing pipeline + + * Custom extraction and consolidation algorithms using any model, prompts, etc. + + * Full control over memory record schemas, namespaces etc. + + * Integration with external systems and databases + + * Requires infrastructure setup and maintenance + + * Lower cost for storage than built-in strategies + + + + +A single memory resource can be configured to utilize both built-in and custom strategies simultaneously, providing flexibility to address diverse memory requirements. + +###### Topics + + * [Built-in strategies](./built-in-strategies.html) + + * [Built-in with overrides strategy](./memory-custom-strategy.html) + + * [Self-managed strategy](./memory-self-managed-strategies.html) @@ -42 +87 @@ To use the Amazon Web Services Documentation, Javascript must be enabled. Please -Memory scoping with namespaces +Memory types @@ -44 +89 @@ Memory scoping with namespaces -Prompts for custom memory strategies +Built-in strategies