AWS bedrock-agentcore documentation change
Summary
Updated documentation structure and content for AgentCore Memory, adding sections about memory types, benefits, use cases, and implementation details while removing specific technical examples
Security assessment
The changes focus on improving feature documentation and user experience descriptions. While memory systems handle sensitive data like user preferences, there is no explicit discussion of security controls, data protection mechanisms, or vulnerability mitigations in the diff. The updates are functional/architectural rather than security-focused.
Diff
diff --git a/bedrock-agentcore/latest/devguide/memory.md b/bedrock-agentcore/latest/devguide/memory.md index 392442f3e..701879964 100644 --- a//bedrock-agentcore/latest/devguide/memory.md +++ b//bedrock-agentcore/latest/devguide/memory.md @@ -5 +5 @@ -Amazon Bedrock AgentCore is in preview release and is subject to change. +Memory typesMemory key benefitsCommon use cases of memory @@ -7 +7 @@ Amazon Bedrock AgentCore is in preview release and is subject to change. -# Add memory to your AI agent +# Add memory to your Amazon Bedrock AgentCore agent @@ -9 +9 @@ Amazon Bedrock AgentCore is in preview release and is subject to change. -AgentCore Memory lets your AI agents deliver intelligent, context-aware, and personalized interactions by maintaining both immediate and long-term knowledge. AgentCore Memory offers two types of memory: +AgentCore Memory is a fully managed service that gives your AI agents the ability to remember past interactions, enabling them to provide more intelligent, context-aware, and personalized conversations. It provides a simple and powerful way to handle both short-term context and long-term knowledge retention without the need to build or manage complex infrastructure. @@ -11 +11 @@ AgentCore Memory lets your AI agents deliver intelligent, context-aware, and per - * **Short-term memory** : Stores conversations to keep track of immediate context. +AgentCore Memory addresses a fundamental challenge in agentic AI: statelessness. Without memory capabilities, AI agents treat each interaction as a new instance with no knowledge of previous conversations. AgentCore Memory provides this critical capability, allowing your agent to build a coherent understanding of users over time. @@ -13 +13 @@ AgentCore Memory lets your AI agents deliver intelligent, context-aware, and per -For example, imagine your coding agent is helping you debug. During the session, you ask it to check variable names, correct syntax errors, and find unused imports. The agent stores the interactions as short term events in AgentCore Memory. Later the agent can retrieve the events so that it can converse without you having to repeat previous information. + @@ -15 +15 @@ For example, imagine your coding agent is helping you debug. During the session, -Short-term memory captures raw interaction events, maintains immediate context, powers real-time conversations, enriches long-term memory systems, and enables building advanced contextual solutions such as multi-step task completion, in-session knowledge accumulation, and context-aware decision making. +AgentCore Memory supports a variety of SDKs and agent frameworks. For examples, see [Amazon Bedrock AgentCore Memory examples](./memory-examples.html). @@ -17 +17 @@ Short-term memory captures raw interaction events, maintains immediate context, - * **Long-term memory** : Stores extracted insights - such as user preferences, semantic facts, and summaries - for knowledge retention across sessions. +## Memory types @@ -19 +19 @@ Short-term memory captures raw interaction events, maintains immediate context, - * **User Preferences** – Think of your coding agent which uses AgentCore Memory as your long-time coding partner. Over many days, it notices you always write clean code with comments, prefer snake_case naming, use pandas for data analysis, and test functions before finalizing them. Next time, even after many sessions, when you ask it to write a data analysis function, it automatically follows these preferences stored in AgentCore Memory without you telling it again. +AgentCore Memory offers [two types](./memory-types.html) of memory that work together to create intelligent, context-aware AI agents: @@ -21 +21 @@ Short-term memory captures raw interaction events, maintains immediate context, - * **Semantic facts** – The coding agent also remembers that “Pandas is a Python Library for data analysis and handling tables”. When you ask, “Which library is best for table data?”, it immediately suggests Pandas because it understands what Pandas are from the semantic memory. +**Short-term memory** @@ -23 +22,0 @@ Short-term memory captures raw interaction events, maintains immediate context, - * **Summary** – The coding agent generates session summaries such as “During this interaction, you created a data cleaning function, fixed two syntax errors, and tested your linear regression model.” These summaries both track completed work and compress conversation context, enabling efficient reference to past activities while optimizing context window usage. @@ -24,0 +24 @@ Short-term memory captures raw interaction events, maintains immediate context, +Short-term memory captures turn-by-turn interactions within a single session. This lets agents maintain immediate context without requiring users to repeat information. @@ -25,0 +26 @@ Short-term memory captures raw interaction events, maintains immediate context, +**Example:** When a user asks, "What's the weather like in Seattle?" and follows up with "What about tomorrow?", the agent relies on recent conversation history to understand that "tomorrow" refers to the weather in Seattle. @@ -26,0 +28,14 @@ Short-term memory captures raw interaction events, maintains immediate context, +**Long-term memory** + + +Long-term memory automatically extracts and stores key insights from conversations across multiple sessions, including user preferences, important facts, and session summaries — for persistent knowledge retention across multiple sessions. + +**Example:** If a customer mentions they prefer window seats during flight booking, the agent stores this preference in long-term memory. In future interactions, the agent can proactively offer window seats, creating a personalized experience. + +## Memory key benefits + + * **Create more natural conversations:** By remembering previous turns in a conversation, agents can understand context, resolve ambiguous statements, and interact in a way that feels more human. + + * **Deliver personalized experiences:** Retain user preferences, historical data, and key facts across sessions to tailor responses and actions to individual users. + + * **Reduce development complexity:** Offload the undifferentiated heavy lifting of managing conversational state and memory, allowing you to focus on building your agent's core business logic. @@ -28 +42,0 @@ Short-term memory captures raw interaction events, maintains immediate context, - @@ -30 +43,0 @@ Short-term memory captures raw interaction events, maintains immediate context, -You can use AgentCore Memory with the AWS SDK or with any popular agent framework, such as Strands Agents. For code examples, see [https://github.com/awslabs/amazon-bedrock-agentcore-samples/tree/main/01-tutorials/04-AgentCore-memory](https://github.com/awslabs/amazon-bedrock-agentcore-samples/tree/main/01-tutorials/04-AgentCore-memory). @@ -32 +44,0 @@ You can use AgentCore Memory with the AWS SDK or with any popular agent framewor -###### Topics @@ -34 +46 @@ You can use AgentCore Memory with the AWS SDK or with any popular agent framewor - * [How it works](./memory-overview.html) +## Common use cases of memory @@ -36 +48 @@ You can use AgentCore Memory with the AWS SDK or with any popular agent framewor - * [Getting started with AgentCore Memory](./memory-getting-started.html) + * **Conversational agents:** A customer support chatbot remembers a user's previous issues and preferences, enabling it to provide more relevant assistance in future interactions. @@ -38 +50 @@ You can use AgentCore Memory with the AWS SDK or with any popular agent framewor - * [Configure AgentCore Memory](./configure-memory.html) + * **Task-oriented / workflow agents:** An AI agent orchestrating a multi-step business process, such as invoice approval, uses memory to track the status of each step and maintain workflow progress. @@ -40 +52 @@ You can use AgentCore Memory with the AWS SDK or with any popular agent framewor - * [Store and use short-term memory](./short-term-memory-operations.html) + * **Multi-agent systems:** A team of AI agents managing a supply chain shares memory to synchronize inventory levels, anticipate demand, and optimize logistics. @@ -42 +54 @@ You can use AgentCore Memory with the AWS SDK or with any popular agent framewor - * [Store and use long-term memory](./long-term-memory-operations.html) + * **Autonomous or planning agents:** An autonomous vehicle uses memory to plan routes, adjust to traffic conditions, and learn from past experiences to improve future driving decisions.