This post was originally published on this site

Today, we’re announcing two new capabilities for Amazon S3 Tables: support for the new Intelligent-Tiering storage class that automatically optimizes costs based on access patterns, and replication support to automatically maintain consistent Apache Iceberg table replicas across AWS Regions and accounts without manual sync.

Organizations working with tabular data face two common challenges. First, they need to manually manage storage costs as their datasets grow and access patterns change over time. Second, when maintaining replicas of Iceberg tables across Regions or accounts, they must build and maintain complex architectures to track updates, manage object replication, and handle metadata transformations.

S3 Tables Intelligent-Tiering storage class
With the S3 Tables Intelligent-Tiering storage class, data is automatically tiered to the most cost-effective access tier based on access patterns. Data is stored in three low-latency tiers: Frequent Access, Infrequent Access (40% lower cost than Frequent Access), and Archive Instant Access (68% lower cost compared to Infrequent Access). After 30 days without access, data moves to Infrequent Access, and after 90 days, it moves to Archive Instant Access. This happens without changes to your applications or impact on performance.

Table maintenance activities, including compaction, snapshot expiration, and unreferenced file removal, operate without affecting the data’s access tiers. Compaction automatically processes only data in the Frequent Access tier, optimizing performance for actively queried data while reducing maintenance costs by skipping colder files in lower-cost tiers.

By default, all existing tables use the Standard storage class. When creating new tables, you can specify Intelligent-Tiering as the storage class, or you can rely on the default storage class configured at the table bucket level. You can set Intelligent-Tiering as the default storage class for your table bucket to automatically store tables in Intelligent-Tiering when no storage class is specified during creation.

Let me show you how it works
You can use the AWS Command Line Interface (AWS CLI) and the put-table-bucket-storage-class and get-table-bucket-storage-class commands to change or verify the storage tier of your S3 table bucket.

# Change the storage class
aws s3tables put-table-bucket-storage-class 
   --table-bucket-arn $TABLE_BUCKET_ARN  
   --storage-class-configuration storageClass=INTELLIGENT_TIERING

# Verify the storage class
aws s3tables get-table-bucket-storage-class 
   --table-bucket-arn $TABLE_BUCKET_ARN  

{ "storageClassConfiguration":
   { 
      "storageClass": "INTELLIGENT_TIERING"
   }
}

S3 Tables replication support
The new S3 Tables replication support helps you maintain consistent read replicas of your tables across AWS Regions and accounts. You specify the destination table bucket and the service creates read-only replica tables. It replicates all updates chronologically while preserving parent-child snapshot relationships. Table replication helps you build global datasets to minimize query latency for geographically distributed teams, meet compliance requirements, and provide data protection.

You can now easily create replica tables that deliver similar query performance as their source tables. Replica tables are updated within minutes of source table updates and support independent encryption and retention policies from their source tables. Replica tables can be queried using Amazon SageMaker Unified Studio or any Iceberg-compatible engine including DuckDB, PyIceberg, Apache Spark, and Trino.

You can create and maintain replicas of your tables through the AWS Management Console or APIs and AWS SDKs. You specify one or more destination table buckets to replicate your source tables. When you turn on replication, S3 Tables automatically creates read-only replica tables in your destination table buckets, backfills them with the latest state of the source table, and continually monitors for new updates to keep replicas in sync. This helps you meet time-travel and audit requirements while maintaining multiple replicas of your data.

Let me show you how it works
To show you how it works, I proceed in three steps. First, I create an S3 table bucket, create an Iceberg table, and populate it with data. Second, I configure the replication. Third, I connect to the replicated table and query the data to show you that changes are replicated.

For this demo, the S3 team kindly gave me access to an Amazon EMR cluster already provisioned. You can follow the Amazon EMR documentation to create your own cluster. They also created two S3 table buckets, a source and a destination for the replication. Again, the S3 Tables documentation will help you to get started.

I take a note of the two S3 Tables bucket Amazon Resource Names (ARNs). In this demo, I refer to these as the environment variables SOURCE_TABLE_ARN and DEST_TABLE_ARN.

First step: Prepare the source database

I start a terminal, connect to the EMR cluster, start a Spark session, create a table, and insert a row of data. The commands I use in this demo are documented in Accessing tables using the Amazon S3 Tables Iceberg REST endpoint.

sudo spark-shell 
--packages "org.apache.iceberg:iceberg-spark-runtime-3.5_2.12:1.4.1,software.amazon.awssdk:bundle:2.20.160,software.amazon.awssdk:url-connection-client:2.20.160" 
--master "local[*]" 
--conf "spark.sql.extensions=org.apache.iceberg.spark.extensions.IcebergSparkSessionExtensions" 
--conf "spark.sql.defaultCatalog=spark_catalog" 
--conf "spark.sql.catalog.spark_catalog=org.apache.iceberg.spark.SparkCatalog" 
--conf "spark.sql.catalog.spark_catalog.type=rest" 
--conf "spark.sql.catalog.spark_catalog.uri=https://s3tables.us-east-1.amazonaws.com/iceberg" 
--conf "spark.sql.catalog.spark_catalog.warehouse=arn:aws:s3tables:us-east-1:012345678901:bucket/aws-news-blog-test" 
--conf "spark.sql.catalog.spark_catalog.rest.sigv4-enabled=true" 
--conf "spark.sql.catalog.spark_catalog.rest.signing-name=s3tables" 
--conf "spark.sql.catalog.spark_catalog.rest.signing-region=us-east-1" 
--conf "spark.sql.catalog.spark_catalog.io-impl=org.apache.iceberg.aws.s3.S3FileIO" 
--conf "spark.hadoop.fs.s3a.aws.credentials.provider=org.apache.hadoop.fs.s3a.SimpleAWSCredentialProvider" 
--conf "spark.sql.catalog.spark_catalog.rest-metrics-reporting-enabled=false"

spark.sql("""
CREATE TABLE s3tablesbucket.test.aws_news_blog (
customer_id STRING,
address STRING
) USING iceberg
""")

spark.sql("INSERT INTO s3tablesbucket.test.aws_news_blog VALUES ('cust1', 'val1')")

spark.sql("SELECT * FROM s3tablesbucket.test.aws_news_blog LIMIT 10").show()
+-----------+-------+
|customer_id|address|
+-----------+-------+
|      cust1|   val1|
+-----------+-------+

So far, so good.

Second step: Configure the replication for S3 Tables

Now, I use the CLI on my laptop to configure the S3 table bucket replication.

Before doing so, I create an AWS Identity and Access Management (IAM) policy to authorize the replication service to access my S3 table bucket and encryption keys. Refer to the S3 Tables replication documentation for the details. The permissions I used for this demo are:

{
    "Version": "2012-10-17",
    "Statement": [
        {
            "Effect": "Allow",
            "Action": [
                "s3:*",
                "s3tables:*",
                "kms:DescribeKey",
                "kms:GenerateDataKey",
                "kms:Decrypt"
            ],
            "Resource": "*"
        }
    ]
}

After having created this IAM policy, I can now proceed and configure the replication:

aws s3tables-replication put-table-replication 
--table-arn ${SOURCE_TABLE_ARN} 
--configuration  '{
    "role": "arn:aws:iam::<MY_ACCOUNT_NUMBER>:role/S3TableReplicationManualTestingRole", 
    "rules":[
        {
            "destinations": [
                {
                    "destinationTableBucketARN": "${DST_TABLE_ARN}"
                }]
        }
    ]

The replication starts automatically. Updates are typically replicated within minutes. The time it takes to complete depends on the volume of data in the source table.

Third step: Connect to the replicated table and query the data

Now, I connect to the EMR cluster again, and I start a second Spark session. This time, I use the destination table.

To verify the replication works, I insert a second row of data on the source table.

spark.sql("INSERT INTO s3tablesbucket.test.aws_news_blog VALUES ('cust2', 'val2')")

I wait a few minutes for the replication to trigger. I follow the status of the replication with the get-table-replication-status command.

aws s3tables-replication get-table-replication-status 
--table-arn ${SOURCE_TABLE_ARN} 
{
    "sourceTableArn": "arn:aws:s3tables:us-east-1:012345678901:bucket/manual-test/table/e0fce724-b758-4ee6-85f7-ca8bce556b41",
    "destinations": [
        {
            "replicationStatus": "pending",
            "destinationTableBucketArn": "arn:aws:s3tables:us-east-1:012345678901:bucket/manual-test-dst",
            "destinationTableArn": "arn:aws:s3tables:us-east-1:012345678901:bucket/manual-test-dst/table/5e3fb799-10dc-470d-a380-1a16d6716db0",
            "lastSuccessfulReplicatedUpdate": {
                "metadataLocation": "s3://e0fce724-b758-4ee6-8-i9tkzok34kum8fy6jpex5jn68cwf4use1b-s3alias/e0fce724-b758-4ee6-85f7-ca8bce556b41/metadata/00001-40a15eb3-d72d-43fe-a1cf-84b4b3934e4c.metadata.json",
                "timestamp": "2025-11-14T12:58:18.140281+00:00"
            }
        }
    ]
}

When replication status shows ready, I connect to the EMR cluster and I query the destination table. Without surprise, I see the new row of data.

Additional things to know
Here are a couple of additional points to pay attention to:

• Replication for S3 Tables supports both Apache Iceberg V2 and V3 table formats, giving you flexibility in your table format choice.
• You can configure replication at the table bucket level, making it straightforward to replicate all tables under that bucket without individual table configurations.
• Your replica tables maintain the storage class you choose for your destination tables, which means you can optimize for your specific cost and performance needs.
• Any Iceberg-compatible catalog can directly query your replica tables without additional coordination—they only need to point to the replica table location. This gives you flexibility in choosing query engines and tools.

Pricing and availability
You can track your storage usage by access tier through AWS Cost and Usage Reports and Amazon CloudWatch metrics. For replication monitoring, AWS CloudTrail logs provide events for each replicated object.

There are no additional charges to configure Intelligent-Tiering. You only pay for storage costs in each tier. Your tables continue to work as before, with automatic cost optimization based on your access patterns.

For S3 Tables replication, you pay the S3 Tables charges for storage in the destination table, for replication PUT requests, for table updates (commits), and for object monitoring on the replicated data. For cross-Region table replication, you also pay for inter-Region data transfer out from Amazon S3 to the destination Region based on the Region pair.

As usual, refer to the Amazon S3 pricing page for the details.

Both capabilities are available today in all AWS Regions where S3 Tables are supported.

To learn more about these new capabilities, visit the Amazon S3 Tables documentation or try them in the Amazon S3 console today. Share your feedback through AWS re:Post for Amazon S3 or through your AWS Support contacts.

— seb

This post was originally published on this site

Today, we’re announcing three new capabilities for Amazon S3 Storage Lens that give you deeper insights into your storage performance and usage patterns. With the addition of performance metrics, support for analyzing billions of prefixes, and direct export to Amazon S3 Tables, you have the tools you need to optimize application performance, reduce costs, and make data-driven decisions about your Amazon S3 storage strategy.

New performance metric categories
S3 Storage Lens now includes eight new performance metric categories that help identify and resolve performance constraints across your organization. These are available at organization, account, bucket, and prefix levels. For example, the service helps you identify small objects in a bucket or prefix that can  slow down application performance. This can be mitigated by batching small objects for using the Amazon S3 Express One Zone storage class for higher performance small object workloads.

To access the new performance metrics, you need to enable performance metrics in the S3 Storage Lens advanced tier when creating a new Storage Lens dashboard or editing an existing configuration.

Metric category	Details	Use case	Mitigation
Read request size	Distribution of read request sizes (GET) by day	Identify dataset with small read request patterns that slow down performance	Small request: Batch small objects or use Amazon S3 Express One Zone for high-performance small object workloads
Write request size	Distribution of write request sizes (PUT, POST, COPY, and UploadPart) by day	Identify dataset with small write request patterns that slow down performance	Large request: Parallelize requests, use MPU or use AWS CRT
Storage size	Distribution of object sizes	Identify dataset with small small objects that slow down performance	Small object sizes: Consider bundling small objects
Concurrent PUT 503 errors	Number of 503s due to concurrent PUT operation on same object	Identify prefixes with concurrent PUT throttling that slow down performance	For single writer, modify retry behavior or use Amazon S3 Express One Zone. For multiple writers, use consensus mechanism or use Amazon S3 Express One Zone
Cross-Region data transfer	Bytes transferred and requests sent across Region, in Region	Identify potential performance and cost degradation due to cross-Region data access	Co-locate compute with data in the same AWS Region
Unique objects accessed	Number or percentage of unique objects accessed per day	Identify datasets where small subset of objects are being frequently accessed. These can be moved to higher performance storage tier for better performance	Consider moving active data to Amazon S3 Express One Zone or other caching solutions
FirstByteLatency (existing Amazon CloudWatch metric)	Daily average of first byte latency metric	The daily average per-request time from the complete request being received to when the response starts to be returned
TotalRequestLatency (existing Amazon CloudWatch metric)	Daily average of Total Request Latency	The daily average elapsed per request time from the first byte received to the last byte sent

How it works
On the Amazon S3 console I choose Create Storage Lens dashboard to create a new dashboard. You can also edit an existing dashboard configuration. I then configure general settings such as providing a Dashboard name, Status, and the optional Tags. Then, I choose Next.

Next, I define the scope of the dashboard by selecting Include all Regions and Include all buckets and specifying the Regions and buckets to be included.

I opt in to the Advanced tier in the Storage Lens dashboard configuration, select Performance metrics, then choose Next.

Next, I select Prefix aggregation as an additional metrics aggregation, then leave the rest of the information as default before I choose Next.

I select the Default metrics report, then General purpose bucket as the bucket type, and then select the Amazon S3 bucket in my AWS account as the Destination bucket. I leave the rest of the information as default, then select Next.

I review all the information before I choose Submit to finalize the process.

After it’s enabled, I’ll receive daily performance metrics directly in the Storage Lens console dashboard. You can also choose to export report in CSV or Parquet format to any bucket in your account or publish to Amazon CloudWatch. The performance metrics are aggregated and published daily and will be available at multiple levels: organization, account, bucket, and prefix. In this dropdown menu, I choose the % concurrent PUT 503 error for the Metric, Last 30 days for the Date range, and 10 for the Top N buckets.

The Concurrent PUT 503 error count metric tracks the number of 503 errors generated by simultaneous PUT operations to the same object. Throttling errors can degrade application performance. For a single writer, modify retry behavior or use higher performance storage tier such as Amazon S3 Express One Zone to mitigate concurrent PUT 503 errors. For multiple writers scenario, use a consensus mechanism to avoid concurrent PUT 503 errors or use higher performance storage tier such as Amazon S3 Express One Zone.

Complete analytics for all prefixes in your S3 buckets
S3 Storage Lens now supports analytics for all prefixes in your S3 buckets through a new Expanded prefixes metrics report. This capability removes previous limitations that restricted analysis to prefixes meeting a 1% size threshold and a maximum depth of 10 levels. You can now track up to billions of prefixes per bucket for analysis at the most granular prefix level, regardless of size or depth.

The Expanded prefixes metrics report includes all existing S3 Storage Lens metric categories: storage usage, activity metrics (requests and bytes transferred), data protection metrics, and detailed status code metrics.

How to get started
I follow the same steps outlined in the How it works section to create or update the Storage Lens dashboard. In Step 4 on the console, where you select export options, you can select the new Expanded prefixes metrics report. Thereafter, I can export the expanded prefixes metrics report in CSV or Parquet format to any general purpose bucket in my account for efficient querying of my Storage Lens data.

Good to know
This enhancement addresses scenarios where organizations need granular visibility across their entire prefix structure. For example, you can identify prefixes with incomplete multipart uploads to reduce costs, track compliance across your entire prefix structure for encryption and replication requirements, and detect performance issues at the most granular level.

Export S3 Storage Lens metrics to S3 Tables
S3 Storage Lens metrics can now be automatically exported to S3 Tables, a fully managed feature on AWS with built-in Apache Iceberg support. This integration provides daily automatic delivery of metrics to AWS managed S3 Tables for immediate querying without requiring additional processing infrastructure.

How to get started
I start by following the process outlined in Step 5 on the console, where I choose the export destination. This time, I choose Expanded prefixes metrics report. In addition to General purpose bucket, I choose Table bucket.

The new Storage Lens metrics are exported to new tables in an AWS managed bucket aws-s3.

I select the expanded_prefixes_activity_metrics table to view API usage metrics for expanded prefix reports.

I can preview the table on the Amazon S3 console or use Amazon Athena to query the table.

Good to know
S3 Tables integration with S3 Storage Lens simplifies metric analysis using familiar SQL tools and AWS analytics services such as Amazon Athena, Amazon QuickSight, Amazon EMR, and Amazon Redshift, without requiring a data pipeline. The metrics are automatically organized for optimal querying, with custom retention and encryption options to suit your needs.

This integration enables cross-account and cross-Region analysis, custom dashboard creation, and data correlation with other AWS services. For example, you can combine Storage Lens metrics with S3 Metadata to analyze prefix-level activity patterns and identify objects in prefixes with cold data that are eligible for transition to lower-cost storage tiers.

For your agentic AI workflows, you can use natural language to query S3 Storage Lens metrics in S3 Tables with the S3 Tables MCP Server. Agents can ask questions such as ‘which buckets grew the most last month?’ or ‘show me storage costs by storage class’ and get instant insights from your observability data.

Now available
All three enhancements are available in all AWS Regions where S3 Storage Lens is currently offered (except the China Regions and AWS GovCloud (US)).

These features are included in the Amazon S3 Storage Lens Advanced tier at no additional charge beyond standard advanced tier pricing. For the S3 Tables export, you pay only for S3 Tables storage, maintenance, and queries. There is no additional charge for the export functionality itself.

To learn more about Amazon S3 Storage Lens performance metrics, support for billions of prefixes, and export to S3 Tables, refer to the Amazon S3 user guide. For pricing details, visit the Amazon S3 pricing page.

Veliswa Boya.

This post was originally published on this site

Today, we’re announcing new capabilities in Amazon Bedrock AgentCore to further remove barriers holding AI agents back from production. Organizations across industries are already building on AgentCore, the most advanced platform to build, deploy, and operate highly capable agents securely at any scale. In just 5 months since preview, the AgentCore SDK has been downloaded over 2 million times. For example:

• PGA TOUR, a pioneer and innovation leader in sports has built a multi-agent content generation system to create articles for their digital platforms. The new solution, built on AgentCore, enables the PGA TOUR to provide comprehensive coverage for every player in the field, by increasing content writing speed by 1,000 percent while achieving a 95 percent reduction in costs.
• Independent software vendors (ISVs) like Workday are building the software of the future on AgentCore. AgentCore Code Interpreter provides Workday Planning Agent with secure data protection and essential features for financial data exploration. Users can analyze financial and operational data through natural language queries, making financial planning intuitive and self-driven. This capability reduces time spent on routine planning analysis by 30 percent, saving approximately 100 hours per month.
• Grupo Elfa, a Brazilian distributor and retailer, relies on AgentCore Observability for complete audit traceability and real-time metrics of their agents, transforming their reactive processes into proactive operations. Using this unified platform, their sales team can handle thousands of daily price quotes while the organization maintains full visibility of agent decisions, helping achieve 100 percent traceability of agent decisions and interactions, and reduced problem resolution time by 50 percent.

As organizations scale their agent deployments, they face challenges around implementing the right boundaries and quality checks to confidently deploy agents. The autonomy that makes agents powerful also makes them hard to confidently deploy at scale, as they might access sensitive data inappropriately, make unauthorized decisions, or take unexpected actions. Development teams must balance enabling agent autonomy while ensuring they operate within acceptable boundaries and with the quality you require to put them in front of customers and employees.

The new capabilities available today take the guesswork out of this process and help you build and deploy trusted AI agents with confidence:

• Policy in AgentCore (Preview) – Defines clear boundaries for agent actions by intercepting AgentCore Gateway tool calls before they run using policies with fine-grained permissions.
• AgentCore Evaluations (Preview) – Monitors the quality of your agents based on real-world behavior using built-in evaluators for dimensions such as correctness and helpfulness, plus custom evaluators for business-specific requirements.

We’re also introducing features that expand what agents can do:

• Episodic functionality in AgentCore Memory – A new long-term strategy that helps agents learn from experiences and adapt solutions across similar situations for improved consistency and performance in similar future tasks.
• Bidirectional streaming in AgentCore Runtime – Deploys voice agents where both users and agents can speak simultaneously following a natural conversation flow.

Policy in AgentCore for precise agent control
Policy gives you control over the actions agents can take and are applied outside of the agent’s reasoning loop, treating agents as autonomous actors whose decisions require verification before reaching tools, systems, or data. It integrates with AgentCore Gateway to intercept tool calls as they happen, processing requests while maintaining operational speed, so workflows remain fast and responsive.

You can create policies using natural language or directly use Cedar—an open source policy language for fine-grained permissions—simplifying the process to set up, understand, and audit rules without writing custom code. This approach makes policy creation accessible to development, security, and compliance teams who can create, understand, and audit rules without specialized coding knowledge.

The policies operate independently of how the agent was built or which model it uses. You can define which tools and data agents can access—whether they are APIs, AWS Lambda functions, Model Context Protocol (MCP) servers, or third-party services—what actions they can perform, and under what conditions.

Teams can define clear policies once and apply them consistently across their organization. With policies in place, developers gain the freedom to create innovative agentic experiences, and organizations can deploy their agents to act autonomously while knowing they’ll stay within defined boundaries and compliance requirements.

Using Policy in AgentCore
You can start by creating a policy engine in the new Policy section of the AgentCore console and associate it with one or more AgentCore gateways.

A policy engine is a collection of policies that are evaluated at the gateway endpoint. When associating a gateway with a policy engine, you can choose whether to enforce the result of the policy—effectively permitting or denying access to a tool call—or to only emit logs. Using logs helps you test and validate a policy before enabling it in production.

Then, you can define the policies to apply to have granular control over access to the tools offered by the associated AgentCore gateways.

To create a policy, you can start with a natural language description (that should include information of the authentication claims to use) or directly edit Cedar code.

Natural language-based policy authoring provides a more accessible way for you to create fine-grained policies. Instead of writing formal policy code, you can describe rules in plain English. The system interprets your intent, generates candidate policies, validates them against the tool schema, and uses automated reasoning to check safety conditions—identifying prompts that are overly permissive, overly restrictive, or contain conditions that can never be satisfied.

Unlike generic large language model (LLM) translations, this feature understands the structure of your tools and generates policies that are both syntactically correct and semantically aligned with your intent, while flagging rules that cannot be enforced. It is also available as a Model Context Protocol (MCP) server, so you can author and validate policies directly in your preferred AI-assisted coding environment as part of your normal development workflow. This approach reduces onboarding time and helps you write high-quality authorization rules without needing Cedar expertise.

The following sample policy uses information from the OAuth claims in the JWT token used to authenticate to an AgentCore gateway (for the role) and the arguments passed to the tool call (context.input) to validate access to the tool processing a refund. Only an authenticated user with the refund-agent role can access the tool but for amounts (context.input.amount) lower than $200 USD.

permit(
  principal is AgentCore::OAuthUser,
  action == AgentCore::Action::"RefundTool__process_refund",
  resource == AgentCore::Gateway::"<GATEWAY_ARN>"
)
when {
  principal.hasTag("role") &&
  principal.getTag("role") == "refund-agent" &&
  context.input.amount < 200
};

AgentCore Evaluations for continuous, real-time quality intelligence
AgentCore Evaluations is a fully managed service that helps you continuously monitor and analyze agent performance based on real-world behavior. With AgentCore Evaluations, you can use built-in evaluators for common quality dimensions such as correctness, helpfulness, tool selection accuracy, safety, goal success rate, and context relevance. You can also create custom model-based scoring systems configured with your choice of prompt and model for business-tailored scoring while the service samples live agent interactions and scores them continuously.

All results from AgentCore Evaluations are visualized in Amazon CloudWatch alongside AgentCore Observability insights, providing one place for unified monitoring. You can also set up alerts and alarms on the evaluation scores to proactively monitor agent quality and respond when metrics fall outside acceptable thresholds.

You can use AgentCore Evaluations during the testing phase where you can check an agent against the baseline before deployment to stop faulty versions from reaching users, and in production for continuous improvement of your agents. When quality metrics drop below defined thresholds—such as a customer service agent satisfaction declining or politeness scores dropping by more than 10 percent over an 8-hour period—the system triggers immediate alerts, helping to detect and address quality issues faster.

Using AgentCore Evaluations
You can create an online evaluation in the new Evaluations section of the AgentCore console. You can use as data source an AgentCore agent endpoint or a CloudWatch log group used by an external agent. For example, I use here the same sample customer support agent I shared when we introduced AgentCore in preview.

Then, you can select the evaluators to use, including custom evaluators that you can define starting from the existing templates or build from scratch.

For example, for a customer support agent, you can select metrics such as:

• Correctness – Evaluates whether the information in the agent’s response is factually accurate
• Faithfulness – Evaluates whether information in the response is supported by provided context/sources
• Helpfulness – Evaluates from user’s perspective how useful and valuable the agent’s response is
• Harmfulness – Evaluates whether the response contains harmful content
• Stereotyping – Detects content that makes generalizations about individuals or groups

The evaluators for tool selection and tool parameter accuracy can help you understand if an agent is choosing the right tool for a task and extracting the correct parameters from the user queries.

To complete the creation of the evaluation, you can choose the sampling rate and optional filters. For permissions, you can create a new AWS Identity and Access Management (IAM) service role or pass an existing one.

The results are published, as they are evaluated, on Amazon CloudWatch in the AgentCore Observability dashboard. You can choose any of the bar chart sections to see the corresponding traces and gain deeper insight into the requests and responses behind that specific evaluation.

Because the results are in CloudWatch, you can use all of its feature to create, for example, alarms and automations.

Creating custom evaluators in AgentCore Evaluations
Custom evaluators allow you to define business-specific quality metrics tailored to your agent’s unique requirements. To create a custom evaluator, you provide the model to use as a judge, including inference parameters such as temperature and max output tokens, and a tailored prompt with the judging instructions. You can start from the prompt used by one of the built-in evaluators or enter a new one.

Then, you define the scale to produce in output. It can be either numeric values or custom text labels that you define. Finally, you configure whether the evaluation is computed by the model on single traces, full sessions, or for each tool call.

AgentCore Memory episodic functionality for experience-based learning
AgentCore Memory, a fully managed service that gives AI agents the ability to remember past interactions, now includes a new long-term memory strategy that gives agents the ability to learn from past experiences and apply those lessons to provide more helpful assistance in future interactions.

Consider booking travel with an agent: over time, the agent learns from your booking patterns—such as the fact that you often need to move flights to later times when traveling for work due to client meetings. When you start your next booking involving client meetings, the agent proactively suggests flexible return options based on these learned patterns. Just like an experienced assistant who learns your specific travel habits, agents with episodic memory can now recognize and adapt to your individual needs.

When you enable the new episodic functionality, AgentCore Memory captures structured episodes that record the context, reasoning process, actions taken, and outcomes of agent interactions, while a reflection agent analyzes these episodes to extract broader insights and patterns. When facing similar tasks, agents can retrieve these learnings to improve decision-making consistency and reduce processing time. This reduces the need for custom instructions by including in the agent context only the specific learnings an agent needs to complete a task instead of a long list of all possible suggestions.

AgentCore Runtime bidirectional streaming for more natural conversations
With AgentCore Runtime, you can deploy agentic applications with few lines of code. To simplify deploying conversational experiences that feel natural and responsive, AgentCore Runtime now supports bidirectional streaming. This capability enables voice agents to listen and adapt while users speak, so that people can interrupt agents mid-response and have the agent immediately adjust to the new context—without waiting for the agent to finish its current output. Rather than traditional turn-based interaction where users must wait for complete responses, bidirectional streaming creates flowing, natural conversations where agents dynamically change their response based on what the user is saying.

Building these conversational experiences from the ground up requires significant engineering effort to handle the complex flow of simultaneous communication. Bidirectional streaming simplifies this by managing the infrastructure needed for agents to process input while generating output, handling interruptions gracefully, and maintaining context throughout dynamic conversation shifts. You can now deploy agents that naturally adapt to the fluid nature of human conversation—supporting mid-thought interruptions, context switches, and clarifications without losing the thread of the interaction.

Things to know
Amazon Bedrock AgentCore, including the preview of Policy, is available in the US East (Ohio, N. Virginia), US West (Oregon), Asia Pacific (Mumbai, Singapore, Sydney, Tokyo), and Europe (Frankfurt, Ireland) AWS Regions . The preview of AgentCore Evaluations is available in the US East (Ohio, N. Virginia), US West (Oregon), Asia Pacific (Sydney), and Europe (Frankfurt) Regions. For Regional availability and future roadmap, visit AWS Capabilities by Region.

With AgentCore, you pay for what you use with no upfront commitments. For detailed pricing information, visit the Amazon Bedrock pricing page. AgentCore is also a part of the AWS Free Tier that new AWS customers can use to get started at no cost and explore key AWS services.

These new features work with any open source framework such as CrewAI, LangGraph, LlamaIndex, and Strands Agents, and with any foundation model. AgentCore services can be used together or independently, and you can get started using your favorite AI-assisted development environment with the AgentCore open source MCP server.

To learn more and get started quickly, visit the AgentCore Developer Guide.

— Danilo

This post was originally published on this site

Modern applications increasingly require complex and long-running coordination between services, such as multi-step payment processing, AI agent orchestration, or approval processes awaiting human decisions. Building these traditionally required significant effort to implement state management, handle failures, and integrate multiple infrastructure services.

Starting today, you can use AWS Lambda durable functions to build reliable multi-step applications directly within the familiar AWS Lambda experience. Durable functions are regular Lambda functions with the same event handler and integrations you already know. You write sequential code in your preferred programming language, and durable functions track progress, automatically retry on failures, and suspend execution for up to one year at defined points, without paying for idle compute during waits.

AWS Lambda durable functions use a checkpoint and replay mechanism, known as durable execution, to deliver these capabilities. After enabling a function for durable execution, you add the new open source durable execution SDK to your function code. You then use SDK primitives like “steps” to add automatic checkpointing and retries to your business logic and “waits” to efficiently suspend execution without compute charges. When execution terminates unexpectedly, Lambda resumes from the last checkpoint, replaying your event handler from the beginning while skipping completed operations.

Getting started with AWS Lambda durable functions
Let me walk you through how to use durable functions.

First, I create a new Lambda function in the console and select Author from scratch. In the Durable execution section, I select Enable. Note that, durable function setting can only be set during function creation and currently can’t be modified for existing Lambda functions.

After I create my Lambda durable function, I can get started with the provided code.

Lambda durable functions introduces two core primitives that handle state management and recovery:

• Steps—The context.step() method adds automatic retries and checkpointing to your business logic. After a step is completed, it will be skipped during replay.
• Wait—The context.wait() method pauses execution for a specified duration, terminating the function, suspending and resuming execution without compute charges.

Additionally, Lambda durable functions provides other operations for more complex patterns: create_callback() creates a callback that you can use to await results for external events like API responses or human approvals, wait_for_condition() pauses until a specific condition is met like polling a REST API for process completion, and parallel() or map() operations for advanced concurrency use cases.

Building a production-ready order processing workflow
Now let’s expand the default example to build a production-ready order processing workflow. This demonstrates how to use callbacks for external approvals, handle errors properly, and configure retry strategies. I keep the code intentionally concise to focus on these core concepts. In a full implementation, you could enhance the validation step with Amazon Bedrock to add AI-powered order analysis.

Here’s how the order processing workflow works:

• First, validate_order() checks order data to ensure all required fields are present.
• Next, send_for_approval() sends the order for external human approval and waits for a callback response, suspending execution without compute charges.
• Then, process_order() completes order processing.
• Throughout the workflow, try-catch error handling distinguishes between terminal errors that stop execution immediately and recoverable errors inside steps that trigger automatic retries.

Here’s the complete order processing workflow with step definitions and the main handler:

import random
from aws_durable_execution_sdk_python import (
    DurableContext,
    StepContext,
    durable_execution,
    durable_step,
)
from aws_durable_execution_sdk_python.config import (
    Duration,
    StepConfig,
    CallbackConfig,
)
from aws_durable_execution_sdk_python.retries import (
    RetryStrategyConfig,
    create_retry_strategy,
)


@durable_step
def validate_order(step_context: StepContext, order_id: str) -> dict:
    """Validates order data using AI."""
    step_context.logger.info(f"Validating order: {order_id}")
    # In production: calls Amazon Bedrock to validate order completeness and accuracy
    return {"order_id": order_id, "status": "validated"}


@durable_step
def send_for_approval(step_context: StepContext, callback_id: str, order_id: str) -> dict:
    """Sends order for approval using the provided callback token."""
    step_context.logger.info(f"Sending order {order_id} for approval with callback_id: {callback_id}")
    
    # In production: send callback_id to external approval system
    # The external system will call Lambda SendDurableExecutionCallbackSuccess or
    # SendDurableExecutionCallbackFailure APIs with this callback_id when approval is complete
    
    return {
        "order_id": order_id,
        "callback_id": callback_id,
        "status": "sent_for_approval"
    }


@durable_step
def process_order(step_context: StepContext, order_id: str) -> dict:
    """Processes the order with retry logic for transient failures."""
    step_context.logger.info(f"Processing order: {order_id}")
    # Simulate flaky API that sometimes fails
    if random.random() > 0.4:
        step_context.logger.info("Processing failed, will retry")
        raise Exception("Processing failed")
    return {
        "order_id": order_id,
        "status": "processed",
        "timestamp": "2025-11-27T10:00:00Z",
    }


@durable_execution
def lambda_handler(event: dict, context: DurableContext) -> dict:
    try:
        order_id = event.get("order_id")
        
        # Step 1: Validate the order
        validated = context.step(validate_order(order_id))
        if validated["status"] != "validated":
            raise Exception("Validation failed")  # Terminal error - stops execution
        context.logger.info(f"Order validated: {validated}")
        
        # Step 2: Create callback
        callback = context.create_callback(
            name="awaiting-approval",
            config=CallbackConfig(timeout=Duration.from_minutes(3))
        )
        context.logger.info(f"Created callback with id: {callback.callback_id}")
        
        # Step 3: Send for approval with the callback_id
        approval_request = context.step(send_for_approval(callback.callback_id, order_id))
        context.logger.info(f"Approval request sent: {approval_request}")
        
        # Step 4: Wait for the callback result
        # This blocks until external system calls SendDurableExecutionCallbackSuccess or SendDurableExecutionCallbackFailure
        approval_result = callback.result()
        context.logger.info(f"Approval received: {approval_result}")
        
        # Step 5: Process the order with custom retry strategy
        retry_config = RetryStrategyConfig(max_attempts=3, backoff_rate=2.0)
        processed = context.step(
            process_order(order_id),
            config=StepConfig(retry_strategy=create_retry_strategy(retry_config)),
        )
        if processed["status"] != "processed":
            raise Exception("Processing failed")  # Terminal error
        
        context.logger.info(f"Order successfully processed: {processed}")
        return processed
        
    except Exception as error:
        context.logger.error(f"Error processing order: {error}")
        raise error  # Re-raise to fail the execution

This code demonstrates several important concepts:

• Error handling—The try-catch block handles terminal errors. When an unhandled exception is thrown outside of a step (like the validation check), it terminates the execution immediately. This is useful when there’s no point in retrying, such as invalid order data.
• Step retries—Inside the process_order step, exceptions trigger automatic retries based on the default (step 1) or configured RetryStrategy (step 5). This handles transient failures like temporary API unavailability.
• Logging—I use context.logger for the main handler and step_context.logger inside steps. The context logger suppresses duplicate logs during replay.

Now I create a test event with order_id and invoke the function asynchronously to start the order workflow. I navigate to the Test tab and fill in the optional Durable execution name to identify this execution. Note that, durable functions provides built-in idempotency. If I invoke the function twice with the same execution name, the second invocation returns the existing execution result instead of creating a duplicate.

I can monitor the execution by navigating to the Durable executions tab in the Lambda console:

Here I can see each step’s status and timing. The execution shows CallbackStarted followed by InvocationCompleted, which indicates the function has terminated and execution is suspended to avoid idle charges while waiting for the approval callback.

I can now complete the callback directly from the console by choosing Send success or Send failure, or programmatically using the Lambda API.

I choose Send success.

After the callback completes, the execution resumes and processes the order. If the process_order step fails due to the simulated flaky API, it automatically retries based on the configured strategy. Once all retries succeed, the execution completes successfully.

Monitoring executions with Amazon EventBridge
You can also monitor durable function executions using Amazon EventBridge. Lambda automatically sends execution status change events to the default event bus, allowing you to build downstream workflows, send notifications, or integrate with other AWS services.

To receive these events, create an EventBridge rule on the default event bus with this pattern:

{
  "source": ["aws.lambda"],
  "detail-type": ["Durable Execution Status Change"]
}

Things to know
Here are key points to note:

• Availability—Lambda durable functions are now available in US East (Ohio) AWS Region. For the latest Region availability, visit the AWS Capabilities by Region page.
• Programming language support—At launch, AWS Lambda durable functions supports JavaScript/TypeScript (Node.js 22/24) and Python (3.13/3.14). We recommend bundling the durable execution SDK with your function code using your preferred package manager. The SDKs are fast-moving, so you can easily update dependencies as new features become available.
• Using Lambda versions—When deploying durable functions to production, use Lambda versions to ensure replay always happens on the same code version. If you update your function code while an execution is suspended, replay will use the version that started the execution, preventing inconsistencies from code changes during long-running workflows.
• Testing your durable functions—You can test durable functions locally without AWS credentials using the separate testing SDK with pytest integration and the AWS Serverless Application Model (AWS SAM) command line interface (CLI) for more complex integration testing.
• Open source SDKs—The durable execution SDKs are open source for JavaScript/TypeScript and Python. You can review the source code, contribute improvements, and stay updated with the latest features.
• Pricing—To learn more on AWS Lambda durable functions pricing, refer to the AWS Lambda pricing page.

Get started with AWS Lambda durable functions by visiting the AWS Lambda console. To learn more, refer to AWS Lambda durable functions documentation page.

Happy building!

— Donnie

This post was originally published on this site

Managing database environments demands a balance of resource efficiency and scalability. Organizations need flexible options across their entire database lifecycle, spanning development, testing, and production workloads with diverse storage and compute requirements.

To address these needs, we’re announcing four new capabilities for Amazon Relational Database Service (Amazon RDS) to help customers optimize their costs as well as improve efficiency and scalability for their Amazon RDS for Oracle and Amazon RDS for SQL Server databases. These enhancements include SQL Server Developer Edition support and expanded storage capabilities for both RDS for Oracle and RDS for SQL Server. Additionally, you can have CPU optimization options for RDS for SQL Server on M7i and R7i instances, which offer price reductions from previous generation instances and separately billed licensing fees.

Let’s explore what’s new.

SQL Server Developer Edition support
SQL Server Developer Edition is now available on RDS for SQL Server, offering a free SQL Server edition that includes all the Enterprise Edition functionalities. Developer Edition is licensed specifically for non-production workloads, so you can build and test applications without incurring SQL Server licensing costs in your development and testing environments.

This release brings significant cost savings to your development and testing environments, while maintaining consistency with your production configurations. You’ll have access to all Enterprise Edition features in your development environment, making it easier to test and validate your applications. Additionally, you’ll benefit from the full suite of Amazon RDS features, including automated backups, software updates, monitoring, and encryption capabilities throughout your development process.

To get started, upload your SQL Server binary files to Amazon Simple Storage Service (Amazon S3) and use them to create your Developer Edition instance. You can migrate existing data from your Enterprise or Standard Edition instances to Developer Edition instances using built-in SQL Server backup and restore operations.

M7i/R7i instances on RDS for SQL Server with support for optimize CPU
You can now use M7i and R7i instances on Amazon RDS for SQL Server to achieve several key benefits. These instances offer significant cost savings over previous generation instances. You also get improved transparency over your database costs with licensing fees and Amazon RDS DB instances costs billed separately.

RDS for SQL Server M7i/R7i instances offer up to 55% lower costs compared to previous generation instances.

Using the optimize CPU capability on these instances, you can customize the number of vCPUs on license-included RDS for SQL Server instances. This enhancement is particularly valuable for database workloads that require high memory and input/output operations per second (IOPS), but lower vCPU counts

This feature provides substantial benefits for your database operations. You can significantly reduce vCPU-based licensing costs while maintaining the same memory and IOPS performance levels your applications require. The capability supports higher memory-to-vCPU ratios and automatically disables hyperthreading while maintaining instance performance. Most importantly, you can fine-tune your CPU settings to precisely match your specific workload requirements, providing optimal resource utilization.

To get started, select SQL Server with an M7i or R7i instance type when creating a new database instance. Under Optimize CPU select Configure the number of vCPUs and set your desired vCPU count.

Additional storage volumes for RDS for Oracle and SQL Server
Amazon RDS for Oracle and Amazon RDS for SQL Server now support up to 256 TiB storage size, a fourfold increase in storage size per database instance, through the addition of up to three additional storage volumes.

The additional storage volumes provide extensive flexibility in managing your database storage needs. You can configure your volumes using both io2 and gp3 volumes to create an optimal storage strategy. You can store frequently accessed data on high-performance Provisioned IOPS SSD (io2) volumes while keeping historical data on cost-effective General Purpose SSD (gp3) volumes, which balances performance and cost. For temporary storage needs, such as month-end processing or data imports, you can add storage volumes as needed. After these operations are complete, you can empty the volumes and then remove them to reduce unnecessary storage costs.

These storage volumes offer operational flexibility with zero downtime and you can add or remove additional storage volumes without interrupting your database operations. You can also scale up multiple volumes in parallel to quickly meet growing storage demands. For Multi-AZ deployments, all additional storage volumes are automatically replicated to maintain high availability.

You can add storage volumes to new or existing database instances through the AWS Management Console, AWS Command Line Interface (AWS CLI), or AWS SDKs.

Let me show you a quick example. I’ll add a storage volume to an existing RDS for Oracle database instance.

First, I navigate to the RDS console, then to my RDS for Oracle database instance detail page. I look under Configuration and I find the Additional storage volumes section.

You can add up to three additional storage volumes and each must be named according to a naming convention. Storage volumes can’t have the same name and you must choose between rdsdbdata2, rdsdbdata3, and rdsdbdata4. For RDS for Oracle database instances, I can add additional storage volumes to the database instance with the primary storage volume size of 200 GiB or higher.

I’m going to add two volumes, so I choose Add additional storage volume and then fill in all the required information. I choose rdsdbdata2 as the volume name and give it 12000 GiB of allocated storage with 60000 provisioned IOPS on an io2 storage type. For my second additional storage volume, rdsdbdata3, I choose to have 2000 GiB on gp3 with 15000 provisioned IOPS.

After confirmation, I wait for Amazon RDS to process my request and then my additional volumes are available.

You can also use the AWS CLI to add volumes during creation of database instances or when modifying them.

Things to know
These capabilities are now available in all commercial AWS Regions and the AWS GovCloud (US) Regions where Amazon RDS for Oracle and Amazon RDS for SQL Server are offered.

You can learn more about each of these capabilities in the Amazon RDS documentation for Developer Edition, optimize CPU, additional storage volumes for RDS for Oracle and additional storage volumes for RDS for SQL Server.

To learn more about the unbundled pricing structure for M7i and R7i instances on RDS for SQL Server, visit the Amazon RDS for SQL Server pricing page.

To get started with any of these capabilities, go to the Amazon RDS console or learn more by visiting the Amazon RDS documentation.

This post was originally published on this site

Since Amazon Web Services (AWS) introduced Savings Plans, customers have been able to lower the cost of running sustained workloads while maintaining the flexibility to manage usage across accounts, resource types, and AWS Regions. Today, we’re extending this flexible pricing model to AWS managed database services with the launch of Database Savings Plans, which help customers reduce database costs by up to 35% when they commit to a consistent amount of usage ($/hour) over a 1-year term. Savings automatically apply each hour to eligible usage across supported database services, and any additional usage beyond the commitment is billed at on-demand rates.

As organizations build and manage data-driven and AI applications, they often use different database services, engines and deployment types, including instance-based and serverless options, to meet evolving business needs. Database Savings Plans provide the flexibility to choose how workloads run while maintaining cost efficiency. If customers are in the middle of a migration or modernization effort, they can switch database engines and adjust deployment types, such as from provisioned to serverless as part of ongoing cost optimization, while continuing to receive discounted rates. If a customer’s business expands globally, they can also shift usage across AWS Regions and continue to benefit from the same commitment. By applying a consistent hourly commitment, customers can maintain predictable spend even as usage patterns evolve and analyze coverage and utilization using familiar cost management tools.

New Savings Plans
Each plan defines where pricing applies, the range of available discounts, and the level of flexibility provided across supported database engines, instance families, sizes, deployment options, or AWS Regions.

The hourly commitment automatically applies to all eligible usage regardless of Region, with support for Amazon Aurora, Amazon Relational Database Service (Amazon RDS), Amazon DynamoDB, Amazon ElastiCache, Amazon DocumentDB (with MongoDB compatibility), Amazon Neptune, Amazon Keyspaces (for Apache Cassandra), Amazon Timestream, and AWS Database Migration Service (AWS DMS). As new eligible database offerings, instance types, or Regions become available, Savings Plans will automatically apply to that usage.

Discounts vary by deployment model and service type. Serverless deployments provide up to 35% savings compared to on-demand rates. Provisioned instances across supported database services deliver up to 20% savings. For Amazon DynamoDB and Amazon Keyspaces, on-demand throughput workloads receive up to 18% savings, and provisioned capacity offers up to 12%. Together, these savings help customers optimize costs while maintaining consistent coverage for database usage. To learn more about the pricing and eligible usage, visit the Database Savings Plans pricing page.

Purchasing Database Savings Plans
AWS Billing and Cost Management Console helps you choose Savings Plans and guides you through the purchase process. You can get started from the AWS Management Console or use the AWS Command Line Interface (AWS CLI) and the API. There are two ways to evaluate Database Savings Plans purchases, in the Recommendations view and in the Purchase Analyzer.

Recommendations – are automatically generated from your recent on-demand usage. To reach the Recommendations view in the Billing and Cost Management console, choose Savings and Commitments, Savings Plans, and Recommendations in the navigation pane. In the Recommendations view, select Database Savings Plans and configure the Recommendation options. AWS Savings Plans recommendations analyze your historical on-demand usage to identify the hourly commitment that delivers the highest overall savings.

The Purchase Analyzer – is designed for modeling custom commitment levels. If you want to purchase a different amount than the recommended commitment on the Purchase Analyzer page, select Database Savings Plans and configure Lookback period and Hourly commitment to simulate alternative commitment levels and see the projected impact on Cost, Coverage, and Utilization.

This way is preferred if your purchasing strategy includes smaller, incremental commitments over time or if you expect future usage changes that could affect your ideal purchase amount.

After reviewing the recommendations or running simulations in Savings Plans Recommendations or Savings Plans Purchase Analyzer, choose Add to cart to proceed with your chosen commitment. If you prefer to purchase directly, you can also navigate to the Purchase Savings Plans page. The console updates estimated discounts and coverage in real time as you adjust each setting, so you can evaluate the impact before completing your order.

You can learn more about how to choose and purchase Database Saving Plans by visiting the Savings Plans User Guide documents.

Now available
Database Savings Plans are available in all AWS Regions outside of China. Give them a try and start shaping your database strategy with more flexibility and predictable costs.

– Betty

This post was originally published on this site

Today we’re announcing serverless GPU acceleration and auto-optimization for vector index in Amazon OpenSearch Service that helps you build large-scale vector databases faster with lower costs and automatically optimize vector indexes for optimal trade-offs between search quality, speed, and cost.

Here are the new capabilities introduced today:

• GPU acceleration – You can build vector databases up to 10 times faster at a quarter of the indexing cost when compared to non-GPU acceleration, and you can create billion-scale vector databases in under an hour. With significant gains in cost saving and speed, you get an advantage in time-to-market, innovation velocity, and adoption of vector search at scale.
• Auto-optimization – You can find the best balance between search latency, quality, and memory requirements for your vector field without needing vector expertise. This optimization helps you achieve better cost-savings and recall rates when compared to default index configurations, while manual index tuning can take weeks to complete.

You can use these capabilities to build vector databases faster and more cost-effectively on OpenSearch Service. You can use them to power generative AI applications, search product catalogs and knowledge bases, and more. You can enable GPU acceleration and auto-optimization when you create a new OpenSearch domain or collection, as well as update an existing domain or collection.

Let’s go through how it works!

GPU acceleration for vector index
When you enable GPU acceleration on your OpenSearch Service domain or Serverless collection, OpenSearch Service automatically detects opportunities to accelerate your vector indexing workloads. This acceleration helps build the vector data structures in your OpenSearch Service domain or Serverless collection.

You don’t need to provision the GPU instances, manage their usage or pay for idle time. OpenSearch Service securely isolates your accelerated workloads to your domain’s or collection’s Amazon Virtual Private Cloud (Amazon VPC) within your account. You pay only for useful processing through the OpenSearch Compute Units (OCU) – Vector Acceleration pricing.

To enable GPU acceleration, go to the OpenSearch Service console and choose Enable GPU Acceleration in the Advanced features section when you create or update your OpenSearch Service domain or Serverless collection.

You can use the following AWS Command Line Interface (AWS CLI) command to enable GPU acceleration for an existing OpenSearch Service domain.

$ aws opensearch update-domain-config 
    --domain-name my-domain 
    --aiml-options '{"ServerlessVectorAcceleration": {"Enabled": true}}'

You can create a vector index optimized for GPU processing. This example index stores 768-dimensional vectors for text embeddings by enabling index.knn.remote_index_build.enabled.

PUT my-vector-index
{
    "settings": {
        "index.knn": true,
        "index.knn.remote_index_build.enabled": true
    },
    "mappings": {
        "properties": {
        "vector_field": {
        "type": "knn_vector",
        "dimension": 768,
      },
      "text": {
        "type": "text"
      }
    }
  }
}

Now you can add vector data and optimize your index using standard OpenSearch Service operations using the bulk API. The GPU acceleration is automatically applied to indexing and force-merge operations.

POST my-vector-index/_bulk
{"index": {"_id": "1"}}
{"vector_field": [0.1, 0.2, 0.3, ...], "text": "Sample document 1"}
{"index": {"_id": "2"}}
{"vector_field": [0.4, 0.5, 0.6, ...], "text": "Sample document 2"}

We ran index build benchmarks and observed speed gains from GPU acceleration ranging between 6.4 to 13.8 times. Stay tuned for more benchmarks and further details in upcoming posts.

To learn more, visit GPU acceleration for vector indexing in the Amazon OpenSearch Service Developer Guide.

Auto-optimizing vector databases
You can use the new vector ingestion feature to ingest documents from Amazon Simple Storage Service (Amazon S3), generate vector embeddings, optimize indexes automatically, and build large-scale vector indexes in minutes. During the ingestion, auto-optimization generates recommendations based on your vector fields and indexes of your OpenSearch Service domain or Serverless collection. You can choose one of these recommendations to quickly ingest and index your vector dataset instead of manually configuring these mappings.

To get started, choose Vector ingestion under the Ingestion menu in the left navigation pane of OpenSearch Service console.

You can create a new vector ingestion job with the following steps:

• Prepare dataset – Prepare OpenSearch Service parquet documents in an S3 bucket and choose a domain or collection for your destination.
• Configure index and automate optimizations – Auto-optimize your vector fields or manually configure them.
• Ingest and accelerate indexing – Use OpenSearch ingestion pipelines to load data from Amazon S3 into OpenSearch Service. Build large vector indexes up to 10 times faster at a quarter of the cost.

In Step 2, configure your vector index with auto-optimize vector field. Auto-optimize is currently limited to one vector field. Further index mappings can be input after the auto-optimization job has completed.

Your vector field optimization settings depend on your use case. For example, if you need high search quality (recall rate) and don’t need faster responses, then choose Modest for the Latency requirements (p90) and more than or equal to 0.9 for the Acceptable search quality (recall). When you create a job, it starts to ingest vector data and auto-optimize vector index. The processing time depends on the vector dimensionality.

To learn more, visit Auto-optimize vector index in the OpenSearch Service Developer Guide.

Now available
GPU acceleration in Amazon OpenSearch Service is now available in the US East (N. Virginia), US West (Oregon), Asia Pacific (Sydney), Asia Pacific (Tokyo), and Europe (Ireland) Regions. Auto-optimization in OpenSearch Service is now available in the US East (Ohio), US East (N. Virginia), US West (Oregon), Asia Pacific (Mumbai), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Europe (Frankfurt), and Europe (Ireland) Regions.

OpenSearch Service separately charges for used OCU – Vector Acceleration only to index your vector databases. For more information, visitOpenSearch Service pricing page.

Give it a try and send feedback to the AWS re:Post for Amazon OpenSearch Service or through your usual AWS Support contacts.

— Channy

This post was originally published on this site

Today, I’m excited to announce that Amazon S3 Vectors is now generally available with significantly increased scale and production-grade performance capabilities. S3 Vectors is the first cloud object storage with native support to store and query vector data. You can use it to help you reduce the total cost of storing and querying vectors by up to 90% when compared to specialized vector database solutions.

Since we announced the preview of S3 Vectors in July, I’ve been impressed by how quickly you adopted this new capability to store and query vector data. In just over four months, you created over 250,000 vector indexes and ingested more than 40 billion vectors, performing over 1 billion queries (as of November 28th).

You can now store and search across up to 2 billion vectors in a single index, that’s up to 20 trillion vectors in a vector bucket and a 40x increase from 50 million per index during preview. This means that you can consolidate your entire vector dataset into one index, removing the need to shard across multiple smaller indexes or implement complex query federation logic.

Query performance has been optimized. Infrequent queries continue to return results in under one second, with more frequent queries now resulting in latencies around 100ms or less, making it well-suited for interactive applications such as conversational AI and multi-agent workflows. You can also retrieve up to 100 search results per query, up from 30 previously, providing more comprehensive context for retrieval augmented generation (RAG) applications.

The write performance has also improved substantially, with support for up to 1,000 PUT transactions per second when streaming single-vector updates into your indexes, delivering significantly higher write throughput for small batch sizes. This higher throughput supports workloads where new data must be immediately searchable, helping you ingest small data corpora quickly or handle many concurrent sources writing simultaneously to the same index.

The fully serverless architecture removes infrastructure overhead—there’s no infrastructure to set up or resources to provision. You pay for what you use as you store and query vectors. This AI-ready storage provides you with quick access to any amount of vector data to support your complete AI development lifecycle, from initial experimentation and prototyping through to large-scale production deployments. S3 Vectors now provides the scale and performance needed for production workloads across AI agents, inference, semantic search, and RAG applications.

Two key integrations that were launched in preview are now generally available. You can use S3 Vectors as a vector storage engine for Amazon Bedrock Knowledge Base. In particular, you can use it to build RAG applications with production-grade scale and performance. Moreover, S3 Vectors integration with Amazon OpenSearch is now generally available, so that you can use S3 Vectors as your vector storage layer while using OpenSearch for search and analytics capabilities.

You can now use S3 Vectors in 14 AWS Regions, expanding from five AWS Regions during the preview.

Let’s see how it works
In this post, I demonstrate how to use S3 Vectors through the AWS Console and CLI.

First, I create an S3 Vector bucket and an index.

echo "Creating S3 Vector bucket..."
aws s3vectors create-vector-bucket 
    --vector-bucket-name "$BUCKET_NAME"

echo "Creating vector index..."
aws s3vectors create-index 
    --vector-bucket-name "$BUCKET_NAME" 
    --index-name "$INDEX_NAME" 
    --data-type "float32" 
    --dimension "$DIMENSIONS" 
    --distance-metric "$DISTANCE_METRIC" 
    --metadata-configuration "nonFilterableMetadataKeys=AMAZON_BEDROCK_TEXT,AMAZON_BEDROCK_METADATA"

The dimension metric must match the dimension of the model used to compute the vectors. The distance metric indicates to the algorithm to compute the distance between vectors. S3 Vectors supports cosine and euclidian distances.

I can also use the console to create the bucket. We’ve added the capability to configure encryption parameters at creation time. By default, indexes use the bucket-level encryption, but I can override bucket-level encryption at the index level with a custom AWS Key Management Service (AWS KMS) key.

I also can add tags for the vector bucket and vector index. Tags at the vector index help with access control and cost allocation.

And I can now manage Properties and Permissions directly in the console.

Similarly, I define Non-filterable metadata and I configure Encryption parameters for the vector index.

Next, I create and store the embeddings (vectors). For this demo, I ingest my constant companion: the AWS Style Guide. This is an 800-page document that describes how to write posts, technical documentation, and articles at AWS.

I use Amazon Bedrock Knowledge Bases to ingest the PDF document stored on a general purpose S3 bucket. Amazon Bedrock Knowledge Bases reads the document and splits it in pieces called chunks. Then, it computes the embeddings for each chunk with the Amazon Titan Text Embeddings model and it stores the vectors and their metadata on my newly created vector bucket. The detailed steps for that process are out of the scope of this post, but you can read the instructions in the documentation.

When querying vectors, you can store up to 50 metadata keys per vector, with up to 10 marked as non-filterable. You can use the filterable metadata keys to filter query results based on specific attributes. Therefore, you can combine vector similarity search with metadata conditions to narrow down results. You can also store more non-filterable metadata for larger contextual information. Amazon Bedrock Knowledge Bases computes and stores the vectors. It also adds large metadata (the chunk of the original text). I exclude this metadata from the searchable index.

There are other methods to ingest your vectors. You can try the S3 Vectors Embed CLI, a command line tool that helps you generate embeddings using Amazon Bedrock and store them in S3 Vectors through direct commands. You can also use S3 Vectors as a vector storage engine for OpenSearch.

Now I’m ready to query my vector index. Let’s imagine I wonder how to write “open source”. Is it “open-source”, with a hyphen, or “open source” without a hyphen? Should I use uppercase or not? I want to search the relevant sections of the AWS Style Guide relative to “open source.”

# 1. Create embedding request
echo '{"inputText":"Should I write open source or open-source"}' | base64 | tr -d 'n' > body_encoded.txt

# 2. Compute the embeddings with Amazon Titan Embed model
aws bedrock-runtime invoke-model 
  --model-id amazon.titan-embed-text-v2:0 
  --body "$(cat body_encoded.txt)" 
  embedding.json

# Search the S3 Vectors index for similar chunks
vector_array=$(cat embedding.json | jq '.embedding') && 
aws s3vectors query-vectors 
  --index-arn "$S3_VECTOR_INDEX_ARN" 
  --query-vector "{"float32": $vector_array}" 
  --top-k 3 
  --return-metadata 
  --return-distance | jq -r '.vectors[] | "Distance: (.distance) | Source: (.metadata."x-amz-bedrock-kb-source-uri" | split("/")[-1]) | Text: (.metadata.AMAZON_BEDROCK_TEXT[0:100])..."'

The first result shows this JSON:

        {
            "key": "348e0113-4521-4982-aecd-0ee786fa4d1d",
            "metadata": {
                "x-amz-bedrock-kb-data-source-id": "0SZY6GYPVS",
                "x-amz-bedrock-kb-source-uri": "s3://sst-aws-docs/awsstyleguide.pdf",
                "AMAZON_BEDROCK_METADATA": "{"createDate":"2025-10-21T07:49:38Z","modifiedDate":"2025-10-23T17:41:58Z","source":{"sourceLocation":"s3://sst-aws-docs/awsstyleguide.pdf"",
                "AMAZON_BEDROCK_TEXT": "[redacted] open source (adj., n.) Two words. Use open source as an adjective (for example, open source software), or as a noun (for example, the code throughout this tutorial is open source). Don't use open-source, opensource, or OpenSource. [redacted]",
                "x-amz-bedrock-kb-document-page-number": 98.0
            },
            "distance": 0.63120436668396
        }

It finds the relevant section in the AWS Style Guide. I must write “open source” without a hyphen. It even retrieved the page number in the original document to help me cross-check the suggestion with the relevant paragraph in the source document.

One more thing
S3 Vectors has also expanded its integration capabilities. You can now use AWS CloudFormation to deploy and manage your vector resources, AWS PrivateLink for private network connectivity, and resource tagging for cost allocation and access control.

Pricing and availability
S3 Vectors is now available in 14 AWS Regions, adding Asia Pacific (Mumbai, Seoul, Singapore, Tokyo), Canada (Central), and Europe (Ireland, London, Paris, Stockholm) to the existing five Regions from preview (US East (Ohio, N. Virginia), US West (Oregon), Asia Pacific (Sydney), and Europe (Frankfurt))

Amazon S3 Vectors pricing is based on three dimensions. PUT pricing is calculated based on the logical GB of vectors you upload, where each vector includes its logical vector data, metadata, and key. Storage costs are determined by the total logical storage across your indexes. Query charges include a per-API charge plus a $/TB charge based on your index size (excluding non-filterable metadata). As your index scales beyond 100,000 vectors, you benefit from lower $/TB pricing. As usual, the Amazon S3 pricing page has the details.

To get started with S3 Vectors, visit the Amazon S3 console. You can create vector indexes, start storing your embeddings, and begin building scalable AI applications. For more information, check out the Amazon S3 User Guide or the AWS CLI Command Reference.

I look forward to seeing what you build with these new capabilities. Please share your feedback through AWS re:Post or your usual AWS Support contacts.

— seb