Built-in with overrides strategy

For advanced or domain-specific use cases, you can create a built-in with overrides strategy to gain fine-grained control over the long-term memory process. Built-in with overrides strategies let you override the default behavior of the built-in strategies by providing your own instructions and selecting a specific foundation model for the extraction and consolidation steps.

When to use a built-in with overrides strategy

Choose a built-in with overrides strategy when you need to tailor the memory logic to your specific requirements. Common use cases include:

How to customize a strategy

You can configure a Built-in with overrides strategy by providing a model ID and your own set of instructions that will be added to the system prompt for both extraction and consolidation.

Pre-requisite: Since built-in with overrides strategies override the behavior of the built-in strategies - to effectively override a strategy you should first understand its built-in (default) behavior.

To use a built-in with overrides strategy, use the CreateMemory operation or the UpdateMemory operation.

The model ID can be provided modelId field when you configure a built-in with overrides strategy. To use a model, first enable access for that model in your AWS account. For more information, see Add or remove access to Amazon Bedrock foundation models. Also, obtain sufficient Amazon Bedrock capacity. For more information, see Amazon Bedrock capacity for built-in with overrides strategies.

The instructions are passed in the appendToPrompt field when you configure the strategy via the API. This field replaces the default instructions part of the system prompt in the built-in strategies, letting you guide the model's behavior, while the Output Schema remains unchanged.

You set the modelId and appendToPrompt fields in the semanticOverride, summaryOverride, or userPreferenceOverride fields found through the the memoryStrategies (MemoryStrategyInput) field of CreateMemory and UpdateMemory.

For example, you can modify the extraction instruction for semantic memory strategy to add new instructions when customizing it.

Built-in semantic memory strategy instructions

The following shows the built-in instructions for the semantic memory strategy:

You are a long-term memory extraction agent supporting a lifelong learning system. Your
task is to identify and extract meaningful information about the users from a given
list of messages.
  
Analyze the conversation and extract structured information about the user according to
the schema below. Only include details that are explicitly stated or can be logically
inferred from the conversation.
  
- Extract information ONLY from the user messages. You should use assistant messages
only as supporting context.
- If the conversation contains no relevant or noteworthy information, return an empty
list.
  
- Do NOT extract anything from prior conversation history, even if provided. Use it
solely for context.
- Do NOT incorporate external knowledge.
- Avoid duplicate extractions.
  
IMPORTANT: Maintain the original language of the user's conversation. If the user 
communicates in a specific language, extract and format the extracted information 
in that same language.
        

You could append a new rule to these instructions, such as:

- Focus exclusively on extracting facts related to travel and booking preferences.
         

or edit an existing rule such as:

IMPORTANT: Always extract memories in English irrespective of the original language of the user's conversation.
        

All instructions you can update

You can update the following instructions:

Best practices for customization

Important considerations

To maintain the reliability of the memory pipeline, please adhere to the following guidelines:

For full control over the end-to-end memory process, including the output schema, see Self-managed strategy.

Execution role

When using built-in with overrides strategies you are also required to provide a memoryExecutionRoleArn in the CreateMemory API. Bedrock Amazon Bedrock AgentCore will assume this role to call the bedrock models in your AWS account for extraction and consolidation.