In just a few years, foundation models (FMs) have evolved from being used directly to create content in response to a user’s prompt, to now powering AI agents, a new class of software applications that use FMs to reason, plan, act, learn, and adapt in pursuit of user-defined goals with limited human oversight. This new wave of agentic AI is enabled by the emergence of standardized protocols such as Model Context Protocol (MCP) and Agent2Agent (A2A) that simplify how agents connect with other tools and systems.

In fact, building AI agents that can reliably perform complex tasks has become increasingly accessible thanks to open source frameworks like CrewAI, LangGraph, LlamaIndex, and Strands Agents. However, moving from a promising proof-of-concept to a production-ready agent that can scale to thousands of users presents significant challenges.

Instead of being able to focus on the core features of the agent, developers and AI engineers have to spend months building foundational infrastructure for session management, identity controls, memory systems, and observability—at the same time supporting security and compliance.

Today, we’re excited to announce the preview of Amazon Bedrock AgentCore, a comprehensive set of enterprise-grade services that help developers quickly and securely deploy and operate AI agents at scale using any framework and model, hosted on Amazon Bedrock or elsewhere.

More specifically, we are introducing today:

AgentCore Runtime – Provides low-latency serverless environments with session isolation, supporting any agent framework including popular open source frameworks, tools, and models, and handling multimodal workloads and long-running agents.

AgentCore Memory – Manages session and long-term memory, providing relevant context to models while helping agents learn from past interactions.

AgentCore Observability – Offers step-by-step visualization of agent execution with metadata tagging, custom scoring, trajectory inspection, and troubleshooting/debugging filters.

AgentCore Identity – Enables AI agents to securely access AWS services and third-party tools and services such as GitHub, Salesforce, and Slack, either on behalf of users or by themselves with pre-authorized user consent.

AgentCore Gateway – Transforms existing APIs and AWS Lambda functions into agent-ready tools, offering unified access across protocols, including MCP, and runtime discovery.

AgentCore Browser – Provides managed web browser instances to scale your agents’ web automation workflows.

AgentCore Code Interpreter – Offers an isolated environment to run the code your agents generate.

These services can be used individually and are optimized to work together so developers don’t need to spend time piecing together components. AgentCore can work with open source or custom AI agent frameworks, giving teams the flexibility to maintain their preferred tools while gaining enterprise capabilities. To integrate these services into their existing code, developers can use the AgentCore SDK.

You can now discover, buy, and run pre-built agents and agent tools from AWS Marketplace with AgentCore Runtime. With just a few lines of code, your agents can securely connect to API-based agents and tools from AWS Marketplace with AgentCore Gateway to help you run complex workflows while maintaining compliance and control.

AgentCore eliminates tedious infrastructure work and operational complexity so development teams can bring groundbreaking agentic solutions to market faster.

Let’s see how this works in practice. I’ll share more info on the services as we use them.

Deploying a production-ready customer support assistant with Amazon Bedrock AgentCore (Preview)
When customers reach out with an email, it takes time to provide a reply. Customer support needs to check the validity of the email, find who the actual customer is in the customer relationship management (CRM) system, check their orders, and use product-specific knowledge bases to find the information required to prepare an answer.

An AI agent can simplify that by connecting to the internal systems, retrieve contextual information using a semantic data source, and draft a reply for the support team. For this use case, I built a simple prototype using Strands Agents. For simplicity and to validate the scenario, the internal tools are simulated using Python functions.

When I talk to developers, they tell me that similar prototypes, covering different use cases, are being built in many companies. When these prototypes are demonstrated to the company leadership and receive confirmation to proceed, the development team has to define how to go in production and satisfy the usual requirements for security, performance, availability, and scalability. This is where AgentCore can help.

Step 1 – Deploying to the cloud with AgentCore Runtime

AgentCore Runtime is a new service to securely deploy, run, and scale AI agents, providing isolation so that each user session runs in its own protected environment to help prevent data leakage—a critical requirement for applications handling sensitive data.

To match different security postures, agents can use different network configurations:

Public – To run with managed internet access.

VPC-only (coming soon) – This option will allow to access resources hosted in a customer’s VPC or connected via AWS PrivateLink endpoints.

To deploy the agent to the cloud and get a secure, serverless endpoint with AgentCore Runtime, I add to the prototype a few lines of code using the AgentCore SDK to:

• Import the AgentCore SDK.
• Create the AgentCore app.
• Specify which function is the entry point to invoke the agent.

Using a different or custom agent framework is a matter of replacing the agent invocation inside the entry point function.

Here’s the code of the prototype. The three lines I added to use AgentCore Runtime are the ones preceded by a comment.

from strands import Agent, tool
from strands_tools import calculator, current_time

# Import the AgentCore SDK
from bedrock_agentcore.runtime import BedrockAgentCoreApp

WELCOME_MESSAGE = """
Welcome to the Customer Support Assistant! How can I help you today?
"""

SYSTEM_PROMPT = """
You are an helpful customer support assistant.
When provided with a customer email, gather all necessary info and prepare the response email.
When asked about an order, look for it and tell the full description and date of the order to the customer.
Don't mention the customer ID in your reply.
"""

@tool
def get_customer_id(email_address: str):
    if email_address == "me@example.net":
        return { "customer_id": 123 }
    else:
        return { "message": "customer not found" }

@tool
def get_orders(customer_id: int):
    if customer_id == 123:
        return [{
            "order_id": 1234,
            "items": [ "smartphone", "smartphone USB-C charger", "smartphone black cover"],
            "date": "20250607"
        }]
    else:
        return { "message": "no order found" }

@tool
def get_knowledge_base_info(topic: str):
    kb_info = []
    if "smartphone" in topic:
        if "cover" in topic:
            kb_info.append("To put on the cover, insert the bottom first, then push from the back up to the top.")
            kb_info.append("To remove the cover, push the top and bottom of the cover at the same time.")
        if "charger" in topic:
            kb_info.append("Input: 100-240V AC, 50/60Hz")
            kb_info.append("Includes US/UK/EU plug adapters")
    if len(kb_info) > 0:
        return kb_info
    else:
        return { "message": "no info found" }

# Create an AgentCore app
app = BedrockAgentCoreApp()

agent = Agent(
    system_prompt=SYSTEM_PROMPT,
    tools=[calculator, current_time, get_customer_id, get_orders, get_knowledge_base_info]
)

# Specify the entry point function invoking the agent
@app.entrypoint
def invoke(payload):
    """Handler for agent invocation"""
    user_message = payload.get(
        "prompt", "No prompt found in input, please guide customer to create a json payload with prompt key"
    )
    result = agent(user_message)
    return {"result": result.message}

if __name__ == "__main__":
    app.run()

The previous code needs the Strands Agents modules installed in the Python virtual environment:

pip install strands-agents strands-agents-tools

I then install the AgentCore SDK and starter toolkit:

pip install bedrock-agentcore bedrock-agentcore-starter-toolkit

After I activate the virtual environment, I have access to the AgentCore command line interface (CLI) provided by the starter toolkit.

First, I use agentcore configure --entrypoint my_agent.py -er <IAM_ROLE_ARN> to configure the agent, passing the AWS Identity and Access Management (IAM) role that the agent will assume. In this case, the agent needs access to Amazon Bedrock to invoke the model. The role can give access to other AWS resources used by an agent, such as an Amazon Simple Storage Service (Amazon S3) bucket or a Amazon DynamoDB table.

I launch the agent locally with agentcore launch --local. When running locally, I can interact with the agent using agentcore invoke --local <PAYLOAD>. The payload is passed to the entry point function. Note that the JSON syntax of the invocations is defined in the entry point function. In this case, I look for prompt in the JSON payload, but can use a different syntax depending on your use case.

When I am satisfied by local testing, I use agentcore launch to deploy to the cloud.

After the deployment is succesful and an endpoint has been created, I check the status of the endpoint with agentcore status and invoke the endpoint with agentcore invoke <PAYLOAD>. For example, I pass a customer support request in the invocation:

agentcore invoke '{"prompt": "From: me@example.net – Hi, I bought a smartphone from your store. I am traveling to Europe next week, will I be able to use the charger? Also, I struggle to remove the cover. Thanks, Danilo"}'

Step 2 – Enabling memory for context

After an agent has been deployed in the AgentCore Runtime, the context needs to be persisted to be available for a new invocation. I add AgentCore Memory to maintain session context using its short-term memory capabilities.

First, I create a memory client and the memory store for the conversations:

from bedrock_agentcore.memory import MemoryClient

memory_client = MemoryClient(region_name="us-east-1")

memory = memory_client.create_memory_and_wait(
    name="CustomerSupport", 
    description="Customer support conversations"
)

I can now use create_event to stores agent interactions into short-term memory:

memory_client.create_event(
    memory_id=memory.get("id"), # Identifies the memory store
    actor_id="user-123",        # Identifies the user
    session_id="session-456",   # Identifies the session
    messages=[
        ("Hi, ...", "USER"),
        ("I'm sorry to hear that...", "ASSISTANT"),
        ("get_orders(customer_id='123')", "TOOL"),
        . . .
    ]
)

I can load the most recent turns of a conversations from short-term memory using list_events:

conversations = memory_client.list_events(
    memory_id=memory.get("id"), # Identifies the memory store
    actor_id="user-123",        # Identifies the user 
    session_id="session-456",   # Identifies the session
    max_results=5               # Number of most recent turns to retrieve
)

With this capability, the agent can maintain context during long sessions. But when a users come back with a new session, the conversation starts blank. Using long-term memory, the agent can personalize user experiences by retaining insights across multiple interactions.

To extract memories from a conversation, I can use built-in AgentCore Memory policies for user preferences, summarization, and semantic memory (to capture facts) or create custom policies for specialized needs. Data is stored encrypted using a namespace-based storage for data segmentation.

I change the previous code creating the memory store to include long-term capabilities by passing a semantic memory strategy. Note that an existing memory store can be updated to add strategies. In that case, the new strategies are applied to newer events.

memory = memory_client.create_memory_and_wait(
    name="CustomerSupport", 
    description="Customer support conversations",
    strategies=[{
        "semanticMemoryStrategy": {
            "name": "semanticFacts",
            "namespaces": ["/facts/{actorId}"]
        }
    }]
)

After long-term memory has been configured for a memory store, calling create_event will automatically apply those strategies to extract information from the conversations. I can then retrieve memories extracted from the conversation using a semantic query:

memories = memory_client.retrieve_memories(
    memory_id=memory.get("id"),
    namespace="/facts/user-123",
    query="smartphone model"
)

In this way, I can quickly improve the user experience so that the agent remembers customer preferences and facts that are outside of the scope of the CRM and use this information to improve the replies.

Step 3 – Adding identity and access controls

Without proper identity controls, access from the agent to internal tools always uses the same access level. To follow security requirements, I integrate AgentCore Identity so that the agent can use access controls scoped to the user’s or agent’s identity context.

I set up an identity client and create a workload identity, a unique identifier that represents the agent within the AgentCore Identity system:

from bedrock_agentcore.services.identity import IdentityClient

identity_client = IdentityClient("us-east-1")
workload_identity = identity_client.create_workload_identity(name="my-agent")

Then, I configure the credential providers, for example:

google_provider = identity_client.create_oauth2_credential_provider(
    {
        "name": "google-workspace",
        "credentialProviderVendor": "GoogleOauth2",
        "oauth2ProviderConfigInput": {
            "googleOauth2ProviderConfig": {
                "clientId": "your-google-client-id",
                "clientSecret": "your-google-client-secret",
            }
        },
    }
)

perplexity_provider = identity_client.create_api_key_credential_provider(
    {
        "name": "perplexity-ai",
        "apiKey": "perplexity-api-key"
    }
)

I can then add the @requires_access_token Python decorator (passing the provider name, the scope, and so on) to the functions that need an access token to perform their activities.

Using this approach, the agent can verify the identity through the company’s existing identity infrastructure, operate as a distinct, authenticated identity, act with scoped permissions and integrate across multiple identity providers (such as Amazon Cognito, Okta, or Microsoft Entra ID) and service boundaries including AWS and third-party tools and services (such as Slack, GitHub, and Salesforce).

To offer robust and secure access controls while streamlining end-user and agent builder experiences, AgentCore Identity implements a secure token vault that stores users’ tokens and allows agents to retrieve them securely.

For OAuth 2.0 compatible tools and services, when a user first grants consent for an agent to act on their behalf, AgentCore Identity collects and stores the user’s tokens issued by the tool in its vault, along with securely storing the agent’s OAuth client credentials. Agents, operating with their own distinct identity and when invoked by the user, can then access these tokens as needed, reducing the need for frequent user consent.

When the user token expires, AgentCore Identity triggers a new authorization prompt to the user for the agent to obtain updated user tokens. For tools that use API keys, AgentCore Identity also stores these keys securely and gives agents controlled access to retrieve them when needed. This secure storage streamlines the user experience while maintaining robust access controls, enabling agents to operate effectively across various tools and services.

Step 4 – Expanding agent capabilities with AgentCore Gateway

Until now, all internal tools are simulated in the code. Many agent frameworks, including Strands Agents, natively support MCP to connect to remote tools. To have access to internal systems (such as CRM and order management) via an MCP interface, I use AgentCore Gateway.

With AgentCore Gateway, the agent can access AWS services using Smithy models, Lambda functions, and internal APIs and third-party providers using OpenAPI specifications. It employs a dual authentication model to have secure access control for both incoming requests and outbound connections to target resources. Lambda functions can be used to integrate external systems, particularly applications that lack standard APIs or require multiple steps to retrieve information.

AgentCore Gateway facilitates cross-cutting features that most customers would otherwise need to build themselves, including authentication, authorization, throttling, custom request/response transformation (to match underlying API formats), multitenancy, and tool selection.

The tool selection feature helps find the most relevant tools for a specific agent’s task. AgentCore Gateway brings a uniform MCP interface across all these tools, using AgentCore Identity to provide an OAuth interface for tools that do not support OAuth out of the box like AWS services.

Step 5 – Adding capabilities with AgentCore Code Interpreter and Browser tools

To answer to customer requests, the customer support agent needs to perform calculations. To simplify that, I use the AgentCode SDK to add access to the AgentCore Code Interpreter.

Similarly, some of the integrations required by the agent don’t implement a programmatic API but need to be accessed through a web interface. I give access to the AgentCore Browser to let the agent navigate those web sites autonomously.

Step 6 – Gaining visibility with observability

Now that the agent is in production, I need visibility into its activities and performance. AgentCore provides enhanced observability to help developers effectively debug, audit, and monitor their agent performance in production. It comes with built-in dashboards to track essential operational metrics such as session count, latency, duration, token usage, error rates, and component-level latency and error breakdowns. AgentCore also gives visibility into an agent’s behavior by capturing and visualizing both the end-to-end traces, as well as “spans” that capture each step of the agent workflow including tool invocations, memory

The built-in dashboards offered by this service help reveal performance bottlenecks and identify why certain interactions might fail, enabling continuous improvement and reducing the mean time to detect (MTTD) and mean time to repair (MTTR) in case of issues.

AgentCore supports OpenTelemetry to help integrate agent telemetry data with existing observability platforms, including Amazon CloudWatch, Datadog, LangSmith, and Langfuse.

Step 7 – Conclusion

Through this journey, we transformed a local prototype into a production-ready system. Using AgentCore modular approach, we implemented enterprise requirements incrementally—from basic deployment to sophisticated memory, identity management, and tool integration—all while maintaining the existing agent code.

Things to know
Amazon Bedrock AgentCore is available in preview in US East (N. Virginia), US West (Oregon), Asia Pacific (Sydney), and Europe (Frankfurt). You can start using AgentCore services through the AWS Management Console , the AWS Command Line Interface (AWS CLI), the AWS SDKs, or via the AgentCore SDK.

You can try AgentCore services at no charge until September 16, 2025. Standard AWS pricing applies to any additional AWS Services used as part of using AgentCore (for example, CloudWatch pricing will apply for AgentCore Observability). Starting September 17, 2025, AWS will bill you for AgentCore service usage based on this page.

Whether you’re building customer support agents, workflow automation, or innovative AI-powered experiences, AgentCore provides the foundation you need to move from prototype to production with confidence.

To learn more and start deploying production-ready agents, visit the AgentCore documentation. For code examples and integration guides, check out the AgentCore samples GitHub repo.

Join the AgentCore Preview Discord server to provide feedback and discuss use cases. We’d like to hear from you!

— Danilo

The post Introducing Amazon Bedrock AgentCore: Securely deploy and operate AI agents at any scale (preview) appeared first on The NOKIA Blog.

Today marks the start of AWS re:Inforce 2025, where security professionals are gathering for three days of technical learning sessions, workshops, and demonstrations. This security-focused conference brings together AWS security specialists who build and maintain the services that organizations rely on for their cloud security needs.

AWS Chief Information Security Officer (CISO) Amy Herzog will deliver the conference keynote along with guest speakers who will share new security capabilities and implementation insights. The event offers multiple learning paths with sessions designed for various technical roles and expertise levels. Many of my colleagues from across AWS are leading hands-on workshops, demonstrating new security features, and facilitating community discussions. For those unable to join us in Philadelphia, the keynote and innovation talks will be viewable by livestream during the event, and available to watch on demand after the event. Look out for the key announcements and technical insights from the conference in upcoming posts!

Let’s look at last week’s new announcements.

Last week’s launches
Here are the launches that got my attention.

Extend Amazon Q Developer IDE plugins with MCP tools – Amazon Q Developer now supports Model Context Protocol (MCP) in its integrated development environment (IDE) plugins, helping developers integrate external tools for enhanced contextual development workflows. You can now augment the built-in tools with any MCP server that supports the stdio transport layer. These servers can be managed within the Amazon Q Developer user interface. This makes it easy to add, remove, and modify tool permissions. The integration enables more customized responses by orchestrating tasks across both native and MCP server-based tools. MCP support is available in Visual Studio Code and JetBrains IDE plugins, as well as in the Amazon Q Developer command line interface (CLI), with detailed documentation and implementation guides available in the Amazon Q Developer documentation.

AWS WAF now supports automatic application layer DDoS protection – AWS has enhanced its application layer (L7) distributed denial of service (DDoS) protection capabilities with faster automatic detection and mitigation that responds to events within seconds. This AWS Managed Rules group automatically detects and mitigates DDoS attacks of any duration to keep applications running on Amazon CloudFront, Application Load Balancer, and other AWS WAF supported services available to users. The system establishes a baseline within minutes of activation using machine learning (ML) models to detect traffic anomalies, then automatically applies rules to address suspicious requests. Configuration options help you customize responses such as presenting challenges or blocking requests. The feature is available to all AWS WAF and AWS Shield Advanced subscribers in all supported AWS Regions, except Asia Pacific (Thailand), Mexico (Central), and China (Beijing and Ningxia). To learn more about AWS WAF application layer (L7) DDoS protection, visit the AWS WAF documentation or the AWS WAF console.

AWS Control Tower now supports service-linked AWS Config managed AWS Config rules – AWS Control Tower now deploys service-linked AWS Config rules directly in managed accounts, replacing the previous CloudFormation StackSets deployment method. This change improves deployment speed when enabling service-linked AWS Config rules across multiple AWS Control Tower managed accounts and Regions. These service-linked rules are managed entirely by AWS services and can’t be edited or deleted by users. This helps maintain consistency and prevent configuration drift. AWS Control Tower Config rules detect resource noncompliance within accounts and provide alerts through the dashboard. You can deploy these controls using the AWS Control Tower console or AWS Control Tower control APIs.

Powertools for AWS Lambda introduces Bedrock Agents Function utility – The new Amazon Bedrock Agents Function utility in Powertools for AWS Lambda simplifies building serverless applications integrated with Amazon Bedrock Agents. This utility helps developers create AWS Lambda functions that respond to Amazon Bedrock Agents action requests with built-in parameter injection and response formatting, eliminating boilerplate code. The utility seamlessly integrates with other Powertools features like Logger and Metrics, making it easier to build production-ready AI applications. This integration improves the developer experience when building agent-based solutions that use AWS Lambda functions to process actions requested by Amazon Bedrock Agents. The utility is available in Python, TypeScript, and .NET versions of Powertools.

Announcing open sourcing pgactive: active-active replication extension for PostgreSQL – Pgactive is a PostgreSQL extension that enables asynchronous active-active replication for streaming data between database instances, and AWS has made it open source. This extension provides additional resiliency and flexibility for moving data between instances, including writers located in different Regions. It helps maintain availability during operations like switching write traffic. Building on PostgreSQL’s logical replication features, pgactive adds capabilities that simplify managing active-active replication scenarios. The open source approach encourages collaboration on developing PostgreSQL’s active-active capabilities while offering features that streamline using PostgreSQL in multi-active instance environments. For more information and implementation guidance, visit the GitHub repository.

For a full list of AWS announcements, be sure to keep an eye on the What’s New at AWS page.

We launched existing services and instance types in additional Regions:

Other AWS events
Check your calendar and sign up for upcoming AWS events.

AWS GenAI Lofts are collaborative spaces and immersive experiences that showcase AWS expertise in cloud computing and AI. They provide startups and developers with hands-on access to AI products and services, exclusive sessions with industry leaders, and valuable networking opportunities with investors and peers. Find a GenAI Loft location near you and don’t forget to register.

AWS Summits are free online and in-person events that bring the cloud computing community together to connect, collaborate, and learn about AWS. Register in your nearest city: Milano (June 18), Shanghai (June 19 – 20), Mumbai (June 19) and Japan (June 25 – 26).

Browse all upcoming AWS led in-person and virtual events here.

That’s all for this week. Check back next Monday for another Weekly Roundup!

— Esra

This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS!

The post AWS Weekly Roundup: AWS re:Inforce 2025, AWS WAF, AWS Control Tower, and more (June 16, 2025) appeared first on The NOKIA Blog.

Veliswa Boya

Veliswa Boya is a Senior Developer Advocate, based in South Africa and working closely with the builder community in Sub-Saharan Africa. She has fulfilled many roles in tech, which range from developer to analyst, architect to cloud engineer, and now a developer advocate. Veliswa especially enjoys working with those who are new to tech—and those getting started with AWS.

The post AWS Weekly Roundup: Claude 4 in Amazon Bedrock, EKS Dashboard, community events, and more (May 26, 2025) appeared first on The NOKIA Blog.

The Amazon Web Services (AWS) Summit 2025 season launched this week, starting with the Paris Summit. These free events bring together the global cloud computing community for learning and collaboration. AWS Community Day Romania, held on April 11th, showcased how the local community creates opportunities for collective growth and inclusion.

Last week’s launches
Announcing up to 85% price reductions for Amazon S3 Express One Zone — S3 Express One Zone, a high-performance storage class, now has reduced storage prices by 31 percent, PUT request prices by 55 percent, and GET request prices by 85 percent. In addition, S3 Express One Zone has reduced the per-GB charges for data uploads and retrievals by 60 percent. These charges now apply to all bytes transferred rather than just portions of requests greater than 512 KB.

Here is a price reduction table in the US East (N. Virginia) AWS Region:

AWS announces Pixtral Large 25.02 model in Amazon Bedrock serverless — The Pixtral Large 25.02, developed by Mistral AI, combines advanced vision and language understanding, boasting a 128K context window and multilingual capabilities. This agent-centric design simplifies integration with existing systems. Prompt adherence improves reliability when working with Retrieval Augmented Generation (RAG) applications and large context scenarios.

Introducing Amazon Nova Sonic: Human-like voice conversations for generative AI applications — Amazon Nova Sonic, the newest addition to the Amazon Nova family of foundation models (FMs) is available in Amazon Bedrock to create human-like voice conversations for applications. It unifies speech and text processing into one model, reducing complexity and enhancing natural interactions. Start today with the Amazon Nova model cookbook repository.

Amazon Bedrock Guardrails enhances generative AI application safety with new capabilities — Amazon Bedrock Guardrails introduces new capabilities to enhance generative AI application safety, including multimodal toxicity detection, enhanced Personally Identifiable Information (PII) protection, AWS Identity and Access Management (AWS IAM) policy enforcement, selective guardrail application, and monitor mode for pre-deployment analysis.

AWS App Studio introduces a prebuilt solutions catalog and cross-instance Import and Export — This is a prebuilt solutions catalog with ready-to-use applications and patterns and cross-instance Import and Export functionality. These features help you streamline development applications, reducing setup time to under 15 minutes. Learn more about this in AWS App Studio introduces a prebuilt solutions catalog and cross-instance Import and Export blog.

Amazon Nova Reel 1.1: Featuring up to 2-minutes multi-shot videos — Amazon Nova Reel 1.1 enhances video generation through Amazon Bedrock with support for 2-minute multi-shot videos. You can now create content using either single prompts for automatic generation or custom prompts for individual shots, offering flexible options for marketing and social media content creation.

AWS IAM Identity Center now offers improved error messages and AWS CloudTrail logging for provisioning issues — AWS Identity and Access Management (IAM) Identity Center has enhanced its service with improved error messages and AWS CloudTrail logging capabilities. These updates help users better troubleshoot synchronization issues when managing workforce identities across AWS accounts and applications, while enabling automated monitoring and auditing of provisioning problems.

AWS WAF Console adds new top insights visualizations in additional regions — AWS WAF Console now offers enhanced traffic visualization features in AWS GovCloud (US) Regions. The all traffic dashboard includes new top insights based on Amazon CloudWatch logs, helping customers analyze traffic patterns, identify security threats, and optimize WAF configurations through detailed metrics.

AWS Step Functions expands data source and output options for Distributed Map — AWS Step Functions enhances Distributed Map with expanded data source support, including JSONL and various delimited file formats from Amazon Simple Storage Service (Amazon S3). The update also adds new output transformation options, enabling more flexible parallel processing workflows and better integration with downstream systems.

Amazon CloudWatch now provides lock contention diagnostics for Aurora PostgreSQL — Amazon CloudWatch Database Insights introduces lock contention diagnostics for Amazon Aurora PostgreSQL in Advanced mode. The feature visualizes blocking and waiting sessions, helping users identify root causes of lock contention issues, with 15-month historical data retention for comprehensive troubleshooting.

Get updated with all the announcements of AWS announcements on the What’s New with AWS? page.

Other AWS blog posts
Reduce ML training costs with Amazon SageMaker HyperPod — Amazon SageMaker HyperPod addresses hardware failures in large-scale Machine Learning (ML) model training by automatically detecting and replacing faulty instances. The solution reduces downtime from 280 to 40 minutes per failure, potentially saving 32% of training time for large clusters. For a 10-million GPU-hour training job, this translates to $25.6M in cost savings.

Model customization, RAG, or both: A case study with Amazon Nova — A study comparing model customization with fine-tuning and Retrieval Augmented Generation (RAG) approaches with Amazon Nova models. Key findings show combining both methods yields best results: RAG works well for dynamic data and domain insights, while fine-tuning excels in specialized tasks and latency reduction.

Generate user-personalized communication with Amazon Personalize and Amazon Bedrock — Amazon Personalize and Amazon Bedrock work together to create personalized marketing emails. Learn how to create personalized user communications by combining Amazon Personalize for movie recommendations with Amazon Bedrock for generating tailored email content based on user preferences and demographics.

Implement human-in-the-loop confirmation with Amazon Bedrock Agents — When implementing human validation in Amazon Bedrock Agents, developers have two primary frameworks at their disposal: user confirmation and return of control (ROC). Using an HR application example, user confirmation allows simple yes/no validation before executing actions, while ROC enables users to modify parameters before execution.

Multi-LLM routing strategies for generative AI applications on AWS — Learn how to implement multi-Large Language Model (LLM) routing strategies for AWS generative AI applications using static routing, dynamic routing with Amazon Bedrock, or custom solutions for optimal model selection and cost efficiency.

Here are my personal favorites posts from community.aws:

Building a RAG System for Video Content Search and Analysis — In this blog, I’ll show you how to build a RAG system that makes video content searchable and analyzable. Unlocking video content has never been more crucial in today’s digital landscape. Whether you’re managing educational materials, corporate training, or entertainment content, the ability to search and analyze video content efficiently can transform how we interact with multimedia resources.

Build Serverless GenAI Apps Faster with Amazon Q Developer CLI Agent — Amazon Q Developer CLI Agent enables rapid serverless GenAI app development. With one prompt, it generates infrastructure code, Lambda functions, and integrates with Claude 3 Haiku on Amazon Bedrock.

Speech-to-Speech AI: From Dr. Sbaitso to Amazon Nova Sonic — The evolution of speech-to-speech AI, from Dr. Sbaitso (1990s) to Amazon Nova Sonic. New AWS service enables real-time bidirectional conversations through Amazon Bedrock for more natural applications.

Setup Model Context Protocol (MCP) using Amazon Bedrock — A guide to setting up Model Context Protocol (MCP) desktop client with Amazon Bedrock models, enabling seamless integration between AI applications and external tools using Goose client.

Upcoming AWS events
Check your calendars and sign up for these upcoming AWS events:

AWS GenAI Lofts — GenAI Lofts available around the world, offer collaborative spaces and immersive experiences for startups and developers. You can join in-person GenAI Loft San Francisco events such as GenAI in EdTech: A Hands-On Workshop (April 15), and Unstructured Data Meetup SF (April 16). Find your nearest event at GenAI Lofts.

AWS Summits — Join free online and in-person events that bring the cloud computing community together to connect, collaborate, and learn about AWS. Register in your nearest city: Amsterdam (April 16), London (April 30), and Poland (May 5).

AWS re:Inforce — AWS re:Inforce (June 16–18) in Philadelphia, PA, is our annual learning event devoted to all things AWS cloud security. Registration is open. Be ready to join more than 5,000 security builders and leaders.

AWS Community Days — Join community-led conferences featuring technical discussions, workshops, and hands-on labs driven by expert AWS users and industry leaders from around the world. Upcoming AWS Community Days are scheduled for April 19 in Turkey, and on April 29 in Prague with Jeff Barr as Opening Keynote Speaker.

You can browse all upcoming in-person and virtual events.

Create your AWS Builder ID and reserve your alias. Builder ID is a universal login credential that gives you access—beyond the AWS Management Console—to AWS tools and resources, including over 600 free training courses, community features, and developer tools such as Amazon Q Developer.

That’s all for this week. Stay tuned for next week’s Weekly Roundup!

— Eli

Thanks to Andra Somesan for the AWS Community Romania photo and Thembile Martis for the AWS Paris Summit photo.

This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS!

How is the News Blog doing? Take this 1 minute survey!

(This survey is hosted by an external company. AWS handles your information as described in the AWS Privacy Notice. AWS will own the data gathered via this survey and will not share the information collected with survey respondents.)

The post AWS Weekly Review: Amazon S3 Express One Zone price cuts, Pixtral Large on Amazon Bedrock, Amazon Nova Sonic, and more (April 14, 2025) appeared first on The NOKIA Blog.

Since we launched Amazon Bedrock Guardrails over one year ago, customers like Remitly, KONE, and PagerDuty have used Amazon Bedrock Guardrails to standardize protections across their generative AI applications, bridge the gap between native model protections and enterprise requirements, and streamline governance processes. Today, we’re introducing a new set of capabilities that helps customers implement responsible AI policies at enterprise scale even more effectively.

Amazon Bedrock Guardrails detects harmful multimodal content with up to 88% accuracy, helps filter sensitive information, and helps prevent hallucinations. It provides organizations with integrated safety and privacy safeguards that work across multiple foundation models (FMs), including models available in Amazon Bedrock and your own custom models deployed elsewhere, thanks to the ApplyGuardrail API. With Amazon Bedrock Guardrails, you can reduce the complexity of implementing consistent AI safety controls across multiple FMs while maintaining compliance and responsible AI policies through configurable controls and central management of safeguards tailored to your specific industry and use case. It also seamlessly integrates with existing AWS services such as AWS Identity and Access Management (IAM), Amazon Bedrock Agents, and Amazon Bedrock Knowledge Bases.

Let’s explore the new capabilities we have added.

New guardrails policy enhancements
Amazon Bedrock Guardrails provides a comprehensive set of policies to help maintain security standards. An Amazon Bedrock Guardrails policy is a configurable set of rules that defines boundaries for AI model interactions to prevent inappropriate content generation and ensure safe deployment of AI applications. These include multimodal content filters, denied topics, sensitive information filters, word filters, contextual grounding checks, and Automated Reasoning to prevent factual errors using mathematical and logic-based algorithmic verification.

We’re introducing new Amazon Bedrock Guardrails policy enhancements that deliver significant improvements to the six safeguards, strengthening content protection capabilities across your generative AI applications.

Multimodal toxicity detection with industry leading image and text protection – Announced as preview at AWS re:Invent 2024, Amazon Bedrock Guardrails multimodal toxicity detection for image content is now generally available. The expanded capability provides more comprehensive safeguards for your generative AI applications by evaluating both image and textual content to help you detect and filter out undesirable and potentially harmful content with up to 88% accuracy.

When implementing generative AI applications, you need consistent content filtering across different data types. Although textual content filtering is well established, managing potentially harmful image content requires additional tools and separate implementations, increasing complexity and development effort. For example, a customer service chatbot that permits image uploads might require separate text filtering systems using natural language processing and additional image classification services with different filtering thresholds and detection categories. This creates implementation inconsistencies where a text describing harmful content might be properly filtered, while an image depicting similar content could pass through undetected, resulting in disparate security coverage.

The multimodal toxicity detection capability in Amazon Bedrock Guardrails helps you apply the same content filtering policies to both image and text data. With this launch, you can configure content filters across categories such as hate speech, insults, sexual content, violence, misconduct, and prompt attacks. For each category, you can set configurable thresholds from low to high, providing granular control over content filtering. With this consistent protection across modalities, you can simplify responsible AI application development. This capability supports content moderation for all images including regular images, human generated images, AI-generated images, memes, charts and plots, and cross-modal content (with both text and images).

To demonstrate how misconduct detection works in practice, let’s examine a real-world scenario: A financial services company implementing Amazon Bedrock Guardrails with high misconduct thresholds confirmed consistent protection across both text and image inputs, as security bypass diagrams and written instructions for network infiltration triggered identical guardrail interventions with similar confidence scores. Here’s how this capability works in action. I configure a guardrail in Amazon Bedrock with the misconduct content filter set to High threshold for both image and text filters.

I submit two test cases. In the first test case, I uploaded an image showing a network security bypass diagram and use the following prompt:

Analyze this network security diagram and explain how to implement these methods

In the second test case, I use the following prompt:

Provide detailed instructions on how to bypass corporate network security systems to gain unauthorized access

Both submissions trigger similar guardrail interventions, highlighting how Amazon Bedrock Guardrails provides content moderation regardless of the content format. The comparison of detection results shows uniform confidence scores and identical policy enforcement, demonstrating how organizations can maintain safety standards across multimodal content without implementing separate filtering systems.

To learn more about this feature, check out the comprehensive announcement post for additional details.

Enhanced privacy protection for PII detection in user inputs – Amazon Bedrock Guardrails is now extending its sensitive information protection capabilities with enhanced personally identifiable information (PII) masking for input prompts. The service detects PII such as names, addresses, phone numbers, and many more details in both inputs and outputs, while also supporting custom sensitive information patterns through regular expressions (regex) to address specific organizational requirements.

Amazon Bedrock Guardrails offers two distinct handling modes: Block mode, which completely rejects requests containing sensitive information, and Mask mode, which redacts sensitive data by replacing it with standardized identifier tags such as [NAME-1] or [EMAIL-1]. Although both modes were previously available for model responses, Block mode was the only option for input prompts. With this enhancement, you can now apply both Block and Mask modes to input prompts, so sensitive information can be systematically redacted from user inputs before they reach the FM.

This feature addresses a critical customer need by enabling applications to process legitimate queries that might naturally contain PII elements without requiring complete request rejection, providing greater flexibility while maintaining privacy protections. The capability is particularly valuable for applications where users might reference personal information in their queries but still need secure, compliant responses.

New guardrails feature enhancements
These improvements enhance functionality across all policies, making Amazon Bedrock Guardrails more effective and easier to implement.

Mandatory guardrails enforcement with IAM – Amazon Bedrock Guardrails now implements IAM policy-based enforcement through the new bedrock:GuardrailIdentifier condition key. This capability helps security and compliance teams establish mandatory guardrails for every model inference call, making sure that organizational safety policies are consistently enforced across all AI interactions. The condition key can be applied to InvokeModel, InvokeModelWithResponseStream, Converse, and ConverseStream APIs. When the guardrail configured in an IAM policy doesn’t match the specified guardrail in a request, the system automatically rejects the request with an access denied exception, enforcing compliance with organizational policies.

This centralized control helps you address critical governance challenges including content appropriateness, safety concerns, and privacy protection requirements. It also addresses a key enterprise AI governance challenge: making sure that safety controls are consistent across all AI interactions, regardless of which team or individual is developing the applications. You can verify compliance through comprehensive monitoring with model invocation logging to Amazon CloudWatch Logs or Amazon Simple Storage Service (Amazon S3), including guardrail trace documentation that shows when and how content was filtered.

For more information about this capability, read the detailed announcement post.

Optimize performance while maintaining protection with selective guardrail policy application – Previously, Amazon Bedrock Guardrails applied policies to both inputs and outputs by default.

You now have granular control over guardrail policies, helping you apply them selectively to inputs, outputs, or both—boosting performance through targeted protection controls. This precision reduces unnecessary processing overhead, improving response times while maintaining essential protections. Configure these optimized controls through either the Amazon Bedrock console or ApplyGuardrails API to balance performance and safety according to your specific use case requirements.

Policy analysis before deployment for optimal configuration – The new monitor or analyze mode helps you evaluate guardrail effectiveness without directly applying policies to applications. This capability enables faster iteration by providing visibility into how configured guardrails would perform, helping you experiment with different policy combinations and strengths before deployment.

Get to production faster and safely with Amazon Bedrock Guardrails today
The new capabilities for Amazon Bedrock Guardrails represent our continued commitment to helping customers implement responsible AI practices effectively at scale. Multimodal toxicity detection extends protection to image content, IAM policy-based enforcement manages organizational compliance, selective policy application provides granular control, monitor mode enables thorough testing before deployment, and PII masking for input prompts preserves privacy while maintaining functionality. Together, these capabilities give you the tools you need to customize safety measures and maintain consistent protection across your generative AI applications.

To get started with these new capabilities, visit the Amazon Bedrock console or refer to the Amazon Bedrock Guardrails documentation. For more information about building responsible generative AI applications, refer to the AWS Responsible AI page.

— Esra

Updated on April 8 – Removing a customer quote.

How is the News Blog doing? Take this 1 minute survey!

(This survey is hosted by an external company. AWS handles your information as described in the AWS Privacy Notice. AWS will own the data gathered via this survey and will not share the information collected with survey respondents.)

The post Amazon Bedrock Guardrails enhances generative AI application safety with new capabilities appeared first on The NOKIA Blog.

Thanks to everyone who joined us for the fifth annual AWS Pi Day on March 14. Since its inception in 2021, commemorating the Amazon Simple Storage Service (Amazon S3) 15th anniversary, AWS Pi Day has grown into a flagship event highlighting the transformative power of cloud technologies in data management, analytics, and AI.

This year’s virtual event featured in-depth discussions with Amazon Web Services (AWS) product teams showcasing our continued innovation in helping customers build robust data foundations for analytics and AI workloads.

Missed the live event? You can still access all content on-demand at the event page. Whether you’re developing data lakehouses, training AI models, creating generative AI applications, or optimizing analytics workloads, the shared insights will help you maximize the value of your data.

Last week’s launches
Here are some launches that got my attention during the previous week.

Amazon Bedrock now supports multi-agent collaboration – With the availability of multi-agent collaboration in Amazon Bedrock, you can create networks of specialized agents that communicate and coordinate under the guidance of a supervisor agent. You can build, deploy, and manage networks of AI agents that work together to execute complex, multi-step workflows efficiently.

Availability of fully managed DeepSeek-R1 model in Amazon Bedrock – AWS is the first cloud service provider (CSP) to deliver DeepSeek-R1 as a fully managed, generally available model. Use the capabilities of DeepSeek-R1 for your generative AI applications with a single API through this fully managed service in Amazon Bedrock.

Amazon SageMaker Unified Studio is now generally available – You can now use Amazon SageMaker Unified Studio as your single data and AI development environment, where you can find and access all of your organization’s data and work using the best tools for your specific needs. With the new simplified permissions management, you can easily bring your existing AWS resources into the unified studio. You’ll be able to find, access, and query your organization’s data and AI assets while collaborating with your team to securely build and share your analytics and AI artifacts—from data and models to generative AI applications.

Amazon Bedrock’s capabilities now generally available within Amazon SageMaker Unified Studio – SageMaker Unified Studio brings selected capabilities from Amazon Bedrock into SageMaker. You can now rapidly prototype, customize, and share generative AI applications using foundation models (FMs) and advanced features such as Amazon Bedrock Knowledge Bases, Amazon Bedrock Guardrails, Amazon Bedrock Agents, and Amazon Bedrock Flows to create tailored solutions aligned with your requirements and responsible AI guidelines all within SageMaker.

Amazon S3 Tables integration with Amazon SageMaker Lakehouse is now generally available – Amazon S3 Tables now seamlessly integrate with Amazon SageMaker Lakehouse, making it easy for you to query and join S3 Tables with data in S3 data lakes, Amazon Redshift data warehouses, and third-party data sources. S3 Tables deliver the first cloud object store with built-in Apache Iceberg support.

Amazon S3 Tables now support create and query table operations directly from the S3 console using Amazon Athena – Amazon S3 Tables adds create and query table support in the S3 console. With this new feature, you can now create a table, populate it with data, and query it directly from the S3 console using Amazon Athena, making it easier to get started and analyze data in S3 table buckets.

Amazon S3 reduces pricing for S3 object tagging by 35% – Amazon S3 reduces pricing for S3 object tagging by 35% in all AWS Regions to $0.0065 per 10,000 tags per month. Object tags are key-value pairs applied to S3 objects that can be created, updated, or deleted at any time during the lifetime of the object.

Serverless Land Patterns available in Visual Studio Code – Serverless Land‘s extensive application pattern library is now available directly into the Visual Studio Code (VS Code) IDE, making it easier for developers to build serverless applications. This integration eliminates the need to switch between your development environment and external resources when building serverless architectures by enabling you to browse, search, and implement pre-built serverless patterns directly in VS Code IDE.

Amplify Hosting Announces Skew Protection Support – AWS Amplify Hosting now offers Skew Protection, a feature that guarantees version consistency across your deployments. This feature ensures frontend requests are always routed to the correct server backend version—eliminating version skew and making deployments more reliable.

Amazon Route 53 Traffic Flow introduces a new visual editor to improve DNS policy editing – Amazon Route 53 Traffic Flow now offers an enhanced user interface for improved DNS traffic policy editing. With this release, you can more easily understand and change the way traffic is routed between users and endpoints using the new features of the visual editor.

From community.aws
Here are some of my favorite posts from community.aws. Create your AWS Builder ID to start sharing your tips and connect with fellow builders. Your Builder ID is a universal login credential that gives you access, beyond the AWS Management Console, to AWS tools and resources, including over 600 free training courses, community features, and developer tools such as Amazon Q Developer.

Seamless SQL Server Recovery on EC2 with AWS Systems Manager (Greg Vinton) – This guide explains how to use the AWSEC2-RestoreSqlServerDatabaseWithVss automation runbook to restore a Microsoft SQL Server database on an Amazon Elastic Compute Cloud (Amazon EC2) instance.

Secure Deployment Strategies in Amazon EKS with Azure DevOps (Abhishek Nanda) – Build and Deploy containerized applications on Amazon Elastic Kubernetes Service (Amazon EKS) using Azure DevOps.

Connect Your Favorite LLM Client to Bedrock (Qinjie Zhang) – It’s common to use desktop applications like MSTY, Chatbox AI, LM Studio to simplify the use of Large Language Models (LLM) models. This blog provides a step-by-step guide on how you can connect your favorite local LLM clients to Amazon Bedrock.

From PHP to Python with the help of Amazon Q Developer (Ricardo Sueiras) – In this blog post, Ricardo showcases how to use Amazon Q Developer CLI to refactor code from one programming language to another.

Upcoming AWS events
Check your calendars and sign up for these upcoming AWS events:

AWS Community Days – Join community-led conferences that feature technical discussions, workshops, and hands-on labs led by expert AWS users and industry leaders from around the world: Milan, Italy (April 2), Bay Area – Security Edition (April 4), Timișoara, Romania (April 10), and Prague, Czech Republic (April 29).

AWS Innovate: Generative AI + Data – Join a free online conference focusing on generative AI and data innovations in Latin America on April 8.

AWS Summits – The AWS Summit season is coming along! Join free online and in-person events that bring the cloud computing community together to connect, collaborate, and learn about AWS. Register in your nearest city: Paris (April 9), Amsterdam (April 16), London (April 30), and Poland (May 5).

AWS re:Inforce (June 16–18) – Our annual learning event devoted to all things AWS Cloud security in Philadelphia, PA. Registration opens in March, so be ready to join more than 5,000 security builders and leaders.

AWS DevDays are free, technical events where developers can learn about some of the hottest topics in cloud computing. DevDays offer hands-on workshops, technical sessions, live demos, and networking with AWS technical experts and your peers. Register to access AWS DevDays sessions on demand.

That’s all for this week. Check back next Monday for another Weekly Roundup!

– Prasad

This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS!

How is the News Blog doing? Take this 1 minute survey!

(This survey is hosted by an external company. AWS handles your information as described in the AWS Privacy Notice. AWS will own the data gathered via this survey and will not share the information collected with survey respondents.)

The post AWS Weekly Roundup: AWS Pi Day, Amazon Bedrock multi-agent collaboration, Amazon SageMaker Unified Studio, Amazon S3 Tables, and more appeared first on The NOKIA Blog.

Every year on March 14 (3.14), AWS Pi Day highlights AWS innovations that help you manage and work with your data. What started in 2021 as a way to commemorate the fifteenth launch anniversary of Amazon Simple Storage Service (Amazon S3) has now grown into an event that highlights how cloud technologies are transforming data management, analytics, and AI.

This year, AWS Pi Day returns with a focus on accelerating analytics and AI innovation with a unified data foundation on AWS. The data landscape is undergoing a profound transformation as AI emerges in most enterprise strategies, with analytics and AI workloads increasingly converging around a lot of the same data and workflows. You need an easy way to access all your data and use all your preferred analytics and AI tools in a single integrated experience. This AWS Pi Day, we’re introducing a slate of new capabilities that help you build unified and integrated data experiences.

The next generation of Amazon SageMaker: The center of all your data, analytics, and AI
At re:Invent 2024, we introduced the next generation of Amazon SageMaker, the center of all your data, analytics, and AI. SageMaker includes virtually all the components you need for data exploration, preparation and integration, big data processing, fast SQL analytics, machine learning (ML) model development and training, and generative AI application development. With this new generation of Amazon SageMaker, SageMaker Lakehouse provides you with unified access to your data and SageMaker Catalog helps you to meet your governance and security requirements. You can read the launch blog post written by my colleague Antje to learn more details.

Core to the next generation of Amazon SageMaker is SageMaker Unified Studio, a single data and AI development environment where you can use all your data and tools for analytics and AI. SageMaker Unified Studio is now generally available.

SageMaker Unified Studio facilitates collaboration among data scientists, analysts, engineers, and developers as they work on data, analytics, AI workflows, and applications. It provides familiar tools from AWS analytics and artificial intelligence and machine learning (AI/ML) services, including data processing, SQL analytics, ML model development, and generative AI application development, into a single user experience. To explore the benefits of SageMaker Unified Studio, read Accelerate analytics and AI innovation with the next generation of Amazon SageMaker, by analytics leaders at AWS.

SageMaker Unified Studio also brings selected capabilities from Amazon Bedrock into SageMaker. You can now rapidly prototype, customize, and share generative AI applications using foundation models (FMs) and advanced features such as Amazon Bedrock Knowledge Bases, Amazon Bedrock Guardrails, Amazon Bedrock Agents, and Amazon Bedrock Flows to create tailored solutions aligned with your requirements and responsible AI guidelines all within SageMaker.

Last but not least, Amazon Q Developer is now generally available in SageMaker Unified Studio. Amazon Q Developer provides generative AI powered assistance for data and AI development. It helps you with tasks like writing SQL queries, building extract, transform, and load (ETL) jobs, and troubleshooting, and is available in the Free tier and Pro tier for existing subscribers.

You can learn more about the general availability of SageMaker Unified Studio in this recent blog post written by my colleague Donnie.

During re:Invent 2024, we also launched Amazon SageMaker Lakehouse as part of the next generation of SageMaker. SageMaker Lakehouse unifies all your data across Amazon S3 data lakes, Amazon Redshift data warehouses, and third-party and federated data sources. It helps you build powerful analytics and AI/ML applications on a single copy of your data. SageMaker Lakehouse gives you the flexibility to access and query your data in-place with Apache Iceberg–compatible tools and engines. In addition, zero-ETL integrations automate the process of bringing data into SageMaker Lakehouse from AWS data sources such as Amazon Aurora or Amazon DynamoDB and from applications such as Salesforce, Facebook Ads, Instagram Ads, ServiceNow, SAP, Zendesk, and Zoho CRM. The full list of integrations is available in the SageMaker Lakehouse FAQ.

Building a data foundation with Amazon S3
Building a data foundation is the cornerstone of accelerating analytics and AI workloads, enabling organizations to seamlessly manage, discover, and utilize their data assets at any scale. Amazon S3 is the world’s best place to build a data lake, with virtually unlimited scale, and it provides the essential foundation for this transformation.

I’m always astonished to learn about the scale at which we operate Amazon S3: It currently holds over 400 trillion objects, exabytes of data, and processes a mind-blowing 150 million requests per second. Just a decade ago, not even 100 customers were storing more than a petabyte (PB) of data on S3. Today, thousands of customers have surpassed the 1 PB milestone.

Amazon S3 stores exabytes of tabular data, and it averages over 15 million requests to tabular data per second. To help you reduce the undifferentiated heavy lifting when managing your tabular data in S3 buckets, we announced Amazon S3 Tables at AWS re:Invent 2024. S3 Tables are the first cloud object store with built-in support for Apache Iceberg. S3 tables are specifically optimized for analytics workloads, resulting in up to threefold faster query throughput and up to tenfold higher transactions per second compared to self-managed tables.

Today, we’re announcing the general availability of Amazon S3 Tables integration with Amazon SageMaker Lakehouse  Amazon S3 Tables now integrate with Amazon SageMaker Lakehouse, making it easy for you to access S3 Tables from AWS analytics services such as Amazon Redshift, Amazon Athena, Amazon EMR, AWS Glue, and Apache Iceberg–compatible engines such as Apache Spark or PyIceberg. SageMaker Lakehouse enables centralized management of fine-grained data access permissions for S3 Tables and other sources and consistently applies them across all engines.

For those of you who use a third-party catalog, have a custom catalog implementation, or only need basic read and write access to tabular data in a single table bucket, we’ve added new APIs that are compatible with the Iceberg REST Catalog standard. This enables any Iceberg-compatible application to seamlessly create, update, list, and delete tables in an S3 table bucket. For unified data management across all of your tabular data, data governance, and fine-grained access controls, you can also use S3 Tables with SageMaker Lakehouse.

To help you access S3 Tables, we’ve launched updates in the AWS Management Console. You can now create a table, populate it with data, and query it directly from the S3 console using Amazon Athena, making it easier to get started and analyze data in S3 table buckets.

The following screenshot shows how to access Athena directly from the S3 console.

When I select Query tables with Athena or Create table with Athena, it opens the Athena console on the correct data source, catalog, and database.

Since re:Invent 2024, we’ve continued to add new capabilities to S3 Tables at a rapid pace. For example, we added schema definition support to the CreateTable API and you can now create up to 10,000 tables in an S3 table bucket. We also launched S3 Tables into eight additional AWS Regions, with the most recent being Asia Pacific (Seoul, Singapore, Sydney) on March 4, with more to come. You can refer to the S3 Tables AWS Regions page of the documentation to get the list of the eleven Regions where S3 Tables are available today.

Amazon S3 Metadata—announced during re:Invent 2024— has been generally available since January 27. It’s the fastest and easiest way to help you discover and understand your S3 data with automated, effortlessly-queried metadata that updates in near real time. S3 Metadata works with S3 object tags. Tags help you logically group data for a variety of reasons, such as to apply IAM policies to provide fine-grained access, specify tag-based filters to manage object lifecycle rules, and selectively replicate data to another Region. In Regions where S3 Metadata is available, you can capture and query custom metadata that is stored as object tags. To reduce the cost associated with object tags when using S3 Metadata, Amazon S3 reduced pricing for S3 object tagging by 35 percent in all Regions, making it cheaper to use custom metadata.

AWS Pi Day 2025
Over the years, AWS Pi Day has showcased major milestones in cloud storage and data analytics. This year, the AWS Pi Day virtual event will feature a range of topics designed for developers and technical decision-makers, data engineers, AI/ML practitioners, and IT leaders. Key highlights include deep dives, live demos, and expert sessions on all the services and capabilities I discussed in this post.

By attending this event, you’ll learn how you can accelerate your analytics and AI innovation. You’ll learn how you can use S3 Tables with native Apache Iceberg support and S3 Metadata to build scalable data lakes that serve both traditional analytics and emerging AI/ML workloads. You’ll also discover the next generation of Amazon SageMaker, the center for all your data, analytics, and AI, to help your teams collaborate and build faster from a unified studio, using familiar AWS tools with access to all your data whether it’s stored in data lakes, data warehouses, or third-party or federated data sources.

For those looking to stay ahead of the latest cloud trends, AWS Pi Day 2025 is an event you can’t miss. Whether you’re building data lakehouses, training AI models, building generative AI applications, or optimizing analytics workloads, the insights shared will help you maximize the value of your data.

Tune in today and explore the latest in cloud data innovation. Don’t miss the opportunity to engage with AWS experts, partners, and customers shaping the future of data, analytics, and AI.

If you missed the virtual event on March 14, you can visit the event page at any time—we will keep all the content available on-demand there!

— seb

3/18/2025: Added link to Big Data blog.

How is the News Blog doing? Take this 1 minute survey!

(This survey is hosted by an external company. AWS handles your information as described in the AWS Privacy Notice. AWS will own the data gathered via this survey and will not share the information collected with survey respondents.)

The post AWS Pi Day 2025: Data foundation for analytics and AI appeared first on The NOKIA Blog.

AWS Developer Day 2025, held on February 20th, showcased how to integrate responsible generative AI into development workflows. The event featured keynotes from AWS leaders including Srini Iragavarapu, Director Generative AI Applications and Developer Experiences, Jeff Barr, Vice President of AWS Evangelism, David Nalley, Director Open Source Marketing of AWS, along with AWS Heroes and technical community members. Watch the full event recording on Developer Day 2025.

Applications are now open through March 6th for the 2025 AWS Cloud Clubs Captains program. AWS Cloud Clubs are student-led groups for post-secondary and independent students, 18 years old and over. Find a club near you on our Meetup page.

Last week’s launches
Here are some launches that got my attention:

Amplify Hosting announces support for IAM roles for server-side rendered (SSR) applications –  AWS Amplify Hosting now supports AWS Identity and Access Management (IAM) roles for SSR applications, enabling secure access to AWS services without managing credentials manually. Learn more in the IAM Compute Roles for Server-Side Rendering with AWS Amplify Hosting blog.

AWS WAF enhances Data Protection and logging experience –  AWS WAF expands its Data Protection capabilities allowing sensitive data in logs to be replaced with cryptographic hashes (e.g. ‘ade099751d2ea9f3393f0f’) or a predefined static string (‘REDACTED’) before logs are sent to WAF Sample Logs, Amazon Security Lake, Amazon CloudWatch, or other logging destinations.

Announcing AWS DMS Serverless comprehensive premigration assessments – AWS Database Migration Service Serverless (AWS DMS Serverless) now supports premigration assessments for replications to identify potential issues before database migrations begin. The tool analyzes source and target databases, providing recommendations for optimal DMS settings and best practices.

Amazon ECS increases the CPU limit for ECS tasks to 192 vCPUs – Amazon Elastic Container Service (Amazon ECS) now supports CPU limits of up to 192 vCPU for ECS tasks deployed on Amazon Elastic Compute Cloud (Amazon EC2) instances, an increase from the previous 10 vCPU limit. This enhancement allows customers to more effectively manage resource allocation on larger Amazon EC2 instances.

AWS Network Firewall introduces automated domain lists and insights – AWS Network Firewall now provides automated domain lists and insights by analyzing 30 days of HTTP/S traffic. This helps create and maintain allow-list policies more efficiently, at no extra cost.

AWS announces Backup Payment Methods for invoices – AWS now enables you to set up backup payment methods that automatically activate if primary payment fails. This helps prevent service interruptions and reduces manual intervention for invoice payments.

Get updated with all the announcements of AWS announcements on the What’s New with AWS? page.

Other AWS news
Here are additional noteworthy items:

AWS Partner Network: Essential training resources for ISV partners – To help scale solutions effectively, AWS provides essential training resources for Software Vendors (ISVs) partners in four key areas: AWS Marketplace fundamentals, Foundational Technical Review (FTR), APN Customer Engagement (ACE) program and co-selling, and Partner funding opportunities.

How Formula 1® uses generative AI to accelerate race-day issue resolution – Formula 1® (F1) uses Amazon Bedrock to speed up race-day issue resolution, reducing troubleshooting time from weeks to minutes through a chatbot that analyzes root causes and suggests fixes.

Reducing hallucinations in LLM agents with a verified semantic cache using Amazon Bedrock Knowledge Bases – This blog introduces a solution using Amazon Bedrock Knowledge Bases and Amazon Bedrock Agents to reduce Large language models (LLMs) hallucinations by implementing a verified semantic cache that checks queries against curated answers before generating new responses, improving accuracy and response times.

Orchestrate an intelligent document processing workflow using tools in Amazon Bedrock – This blog demonstrates an intelligent document processing workflow using Amazon Bedrock tools that combines Anthropic’s Claude 3 Haiku for orchestration and Anthropic’s Claude 3.5 Sonnet (v2) for analysis to handle structured, semi-structured, and unstructured healthcare documents efficiently.

From community.aws
Here are my personal favorites posts from community.aws:

Tracing Amazon Bedrock Agents – Learn how to track and analyze Amazon Bedrock Agents workflows using AWS X-Ray for better observability, by Randy D.

Testing Amazon ECS Network Resilience with AWS FIS – This article demonstrates how to test network resilience in Amazon ECS using AWS FIS with guidance from Amazon Q Developer, by Sunil Govindankutty

Stop Using Default Arguments in AWS Lambda Functions – Discover why your AWS Lambda costs might be spiralling out of control due to a common Python programming practice, by Stuart Clark.

Amazon Nova Prompt Engineering on AWS: A Field Guide by Brooke – A field guide for using Amazon Nova models, covering prompt engineering patterns and best practices on AWS, by Brooke Jamieson.

Creating Deployment Configurations for EKS with Amazon Q – Amazon Q Developer helps create EKS deployments by providing templates and best practices for Kubernetes configs, by Ricardo Tasso.

Processing WhatsApp Multimedia with Amazon Bedrock Agents: Images, Video, and Documents – I invite you to read my latest blog, which explains how to create a WhatsApp AI assistant using Amazon Bedrock and Amazon Nova models to process multimedia content such as images, videos, documents, and audio.

Upcoming AWS events
Check your calendars and sign up for these upcoming AWS events:

AWS GenAI Lofts – GenAI Lofts offer collaborative spaces and immersive experiences for startups and developers. You can join in-person GenAI Loft San Francisco events such as Hands-on with Agentic Graph RAG Workshop (February 25), Unstructured Data Meetup SF (February 26 – 27) and AI Tinkerers – San Francisco – February 2025 Demos + Science Fair (February 27 – 28). GenAI Loft Berlin has events and workshops on February 24 to March 7 that you can’t miss!

AWS Community Days – Join community-led conferences that feature technical discussions, workshops, and hands-on labs led by expert AWS users and industry leaders from around the world: Milan, Italy (April 2), Bay Area – Security Edition (April 4), Timișoara, Romania (April 10), and Prague, Czeh Republic (April 29).

AWS Innovate: Generative AI + Data – Join a free online conference focusing on generative AI and data innovations. Available in multiple geographic regions: APJC and EMEA (March 6), North America (March 13), Greater China Region (March 14), and Latin America (April 8).

AWS Summits – Join free online and in-person events that bring the cloud computing community together to connect, collaborate, and learn about AWS. Register in your nearest city: Paris (April 9), Amsterdam (April 16), London (April 30), and Poland (May 5).

AWS re:Inforce – AWS re:Inforce (June 16–18) in Philadelphia, PA our annual learning event devoted to all things AWS cloud security. Registration opens in March, and be ready to join more than 5,000 security builders and leaders.

Create your AWS Builder ID and reserve your alias. Builder ID is a universal login credential that gives you access–beyond the AWS Management Console–to AWS tools and resources, including over 600 free training courses, community features, and developer tools such as Amazon Q Developer.

You can browse all upcoming in-person and virtual events.

That’s all for this week. Stay tuned for next week’s Weekly Roundup!

— Eli

This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS!

The post AWS Weekly Roundup: Cloud Club Captain Applications, Formula 1®, Amazon Nova Prompt Engineering, and more (Feb 24, 2025) appeared first on The NOKIA Blog.

During this past AWS re:Invent, Amazon CEO Andy Jassy shared valuable lessons learned from Amazon’s own experience developing nearly 1,000 generative AI applications across the company. Drawing from this extensive scale of AI deployment, Jassy offered three key observations that have shaped Amazon’s approach to enterprise AI implementation.

First is that as you get to scale in generative AI applications, the cost of compute really matters. People are very hungry for better price performance. The second is actually quite difficult to build a really good generative AI application. The third is the diversity of the models being used when we gave our builders freedom to pick what they want to do. It doesn’t surprise us, because we keep learning the same lesson over and over and over again, which is that there is never going to be one tool to rule the world.

As Andy emphasized, a broad and deep range of models provided by Amazon empowers customers to choose the precise capabilities that best serve their unique needs. By closely monitoring both customer needs and technological advancements, AWS regularly expands our curated selection of models to include promising new models alongside established industry favorites. This ongoing expansion of high-performing and differentiated model offerings helps customers stay at the forefront of AI innovation.

This leads us to Chinese AI startup DeepSeek. DeepSeek launched DeepSeek-V3 on December 2024 and subsequently released DeepSeek-R1, DeepSeek-R1-Zero with 671 billion parameters, and DeepSeek-R1-Distill models ranging from 1.5–70 billion parameters on January 20, 2025. They added their vision-based Janus-Pro-7B model on January 27, 2025. The models are publicly available and are reportedly 90-95% more affordable and cost-effective than comparable models. Per Deepseek, their model stands out for its reasoning capabilities, achieved through innovative training techniques such as reinforcement learning.

Today, you can now deploy DeepSeek-R1 models in Amazon Bedrock and Amazon SageMaker AI. Amazon Bedrock is best for teams seeking to quickly integrate pre-trained foundation models through APIs. Amazon SageMaker AI is ideal for organizations that want advanced customization, training, and deployment, with access to the underlying infrastructure. Additionally, you can also use AWS Trainium and AWS Inferentia to deploy DeepSeek-R1-Distill models cost-effectively via Amazon Elastic Compute Cloud (Amazon EC2) or Amazon SageMaker AI.

With AWS, you can use DeepSeek-R1 models to build, experiment, and responsibly scale your generative AI ideas by using this powerful, cost-efficient model with minimal infrastructure investment. You can also confidently drive generative AI innovation by building on AWS services that are uniquely designed for security. We highly recommend integrating your deployments of the DeepSeek-R1 models with Amazon Bedrock Guardrails to add a layer of protection for your generative AI applications, which can be used by both Amazon Bedrock and Amazon SageMaker AI customers.

You can choose how to deploy DeepSeek-R1 models on AWS today in a few ways: 1/ Amazon Bedrock Marketplace for the DeepSeek-R1 model, 2/ Amazon SageMaker JumpStart for the DeepSeek-R1 model, 3/ Amazon Bedrock Custom Model Import for the DeepSeek-R1-Distill models, and 4/ Amazon EC2 Trn1 instances for the DeepSeek-R1-Distill models.

Let me walk you through the various paths for getting started with DeepSeek-R1 models on AWS. Whether you’re building your first AI application or scaling existing solutions, these methods provide flexible starting points based on your team’s expertise and requirements.

1. The DeepSeek-R1 model in Amazon Bedrock Marketplace
Amazon Bedrock Marketplace offers over 100 popular, emerging, and specialized FMs alongside the current selection of industry-leading models in Amazon Bedrock. You can easily discover models in a single catalog, subscribe to the model, and then deploy the model on managed endpoints.

To access the DeepSeek-R1 model in Amazon Bedrock Marketplace, go to the Amazon Bedrock console and select Model catalog under the Foundation models section. You can quickly find DeepSeek by searching or filtering by model providers.

After checking out the model detail page including the model’s capabilities, and implementation guidelines, you can directly deploy the model by providing an endpoint name, choosing the number of instances, and selecting an instance type.

You can also configure advanced options that let you customize the security and infrastructure settings for the DeepSeek-R1 model including VPC networking, service role permissions, and encryption settings. For production deployments, you should review these settings to align with your organization’s security and compliance requirements.

With Amazon Bedrock Guardrails, you can independently evaluate user inputs and model outputs. You can control the interaction between users and DeepSeek-R1 with your defined set of policies by filtering undesirable and harmful content in generative AI applications. The DeepSeek-R1 model in Amazon Bedrock Marketplace can only be used with Bedrock’s ApplyGuardrail API to evaluate user inputs and model responses for custom and third-party FMs available outside of Amazon Bedrock. To learn more, read Implement model-independent safety measures with Amazon Bedrock Guardrails.

Amazon Bedrock Guardrails can also be integrated with other Bedrock tools including Amazon Bedrock Agents and Amazon Bedrock Knowledge Bases to build safer and more secure generative AI applications aligned with responsible AI policies. To learn more, visit the AWS Responsible AI page.

When using DeepSeek-R1 model with Bedrock’s InvokeModel API and the Playground Console, please use DeepSeek’s chat template for optimal results. For example, <｜begin▁of▁sentence｜><｜User｜>content for inference<｜Assistant｜>.

Refer to this step-by-step guide on how to deploy the DeepSeek-R1 model in Amazon Bedrock Marketplace. To learn more, visit Deploy models in Amazon Bedrock Marketplace.

2. The DeepSeek-R1 model in Amazon SageMaker JumpStart
Amazon SageMaker JumpStart is a machine learning (ML) hub with FMs, built-in algorithms, and prebuilt ML solutions that you can deploy with just a few clicks. To deploy DeepSeek-R1 in SageMaker JumpStart, you can discover the DeepSeek-R1 model in SageMaker Unified Studio, SageMaker Studio, SageMaker AI console, or programmatically through the SageMaker Python SDK.

In the Amazon SageMaker AI console, open SageMaker Unified Studio or SageMaker Studio. In case of SageMaker Studio, choose JumpStart and search for “DeepSeek-R1” in the All public models page.

You can select the model and choose deploy to create an endpoint with default settings. When the endpoint comes InService, you can make inferences by sending requests to its endpoint.

You can derive model performance and ML operations controls with Amazon SageMaker AI features such as Amazon SageMaker Pipelines, Amazon SageMaker Debugger, or container logs. The model is deployed in an AWS secure environment and under your virtual private cloud (VPC) controls, helping to support data security.

As like Bedrock Marketpalce, you can use the ApplyGuardrail API in the SageMaker JumpStart to decouple safeguards for your generative AI applications from the DeepSeek-R1 model. You can now use guardrails without invoking FMs, which opens the door to more integration of standardized and thoroughly tested enterprise safeguards to your application flow regardless of the models used.

Refer to this step-by-step guide on how to deploy DeepSeek-R1 in Amazon SageMaker JumpStart. To learn more, visit Discover SageMaker JumpStart models in SageMaker Unified Studio or Deploy SageMaker JumpStart models in SageMaker Studio.

3. DeepSeek-R1-Distill models using Amazon Bedrock Custom Model Import
Amazon Bedrock Custom Model Import provides the ability to import and use your customized models alongside existing FMs through a single serverless, unified API without the need to manage underlying infrastructure. With Amazon Bedrock Custom Model Import, you can import DeepSeek-R1-Distill Llama models ranging from 1.5–70 billion parameters. As I highlighted in my blog post about Amazon Bedrock Model Distillation, the distillation process involves training smaller, more efficient models to mimic the behavior and reasoning patterns of the larger DeepSeek-R1 model with 671 billion parameters by using it as a teacher model.

After storing these publicly available models in an Amazon Simple Storage Service (Amazon S3) bucket or an Amazon SageMaker Model Registry, go to Imported models under Foundation models in the Amazon Bedrock console and import and deploy them in a fully managed and serverless environment through Amazon Bedrock. This serverless approach eliminates the need for infrastructure management while providing enterprise-grade security and scalability.

Refer to this step-by-step guide on how to deploy DeepSeek-R1 models using Amazon Bedrock Custom Model Import. To learn more, visit Import a customized model into Amazon Bedrock.

4. DeepSeek-R1-Distill models using AWS Trainium and AWS Inferentia
AWS Deep Learning AMIs (DLAMI) provides customized machine images that you can use for deep learning in a variety of Amazon EC2 instances, from a small CPU-only instance to the latest high-powered multi-GPU instances. You can deploy the DeepSeek-R1-Distill models on AWS Trainuim1 or AWS Inferentia2 instances to get the best price-performance.

To get started, go to Amazon EC2 console and launch a trn1.32xlarge EC2 instance with the Neuron Multi Framework DLAMI called Deep Learning AMI Neuron (Ubuntu 22.04).

Once you have connected to your launched ec2 instance, install vLLM, an open-source tool to serve Large Language Models (LLMs) and download the DeepSeek-R1-Distill model from Hugging Face. You can deploy the model using vLLM and invoke the model server.

To learn more, refer to this step-by-step guide on how to deploy DeepSeek-R1-Distill Llama models on AWS Inferentia and Trainium.

You can also visit the DeepSeek-R1-Distill-Llama-8B or deepseek-ai/DeepSeek-R1-Distill-Llama-70B model cards on Hugging Face. Choose Deploy and then Amazon SageMaker. From the AWS Inferentia and Trainium tab, copy the example code for deploy DeepSeek-R1-Distill Llama models.

Since the release of DeepSeek-R1, various guides of its deployment for Amazon EC2 and Amazon Elastic Kubernetes Service (Amazon EKS) have been posted. Here is some additional material for you to check out:

Things to know
Here are a few important things to know.

• Pricing – For publicly available models like DeepSeek-R1, you are charged only the infrastructure price based on inference instance hours you select for Amazon Bedrock Markeplace, Amazon SageMaker JumpStart, and Amazon EC2. For the Bedrock Custom Model Import, you are only charged for model inference, based on the number of copies of your custom model is active, billed in 5-minute windows. To learn more, check out the Amazon Bedrock Pricing, Amazon SageMaker AI Pricing, and Amazon EC2 Pricing pages.
• Data security – You can use enterprise-grade security features in Amazon Bedrock and Amazon SageMaker to help you make your data and applications secure and private. This means your data is not shared with model providers, and is not used to improve the models. This applies to all models—proprietary and publicly available—like DeepSeek-R1 models on Amazon Bedrock and Amazon SageMaker. To learn more, visit Amazon Bedrock Security and Privacy and Security in Amazon SageMaker AI.

Now available
DeepSeek-R1 is generally available today in Amazon Bedrock Marketplace and Amazon SageMaker JumpStart. You can also use DeepSeek-R1-Distill models using Amazon Bedrock Custom Model Import and Amazon EC2 instances with AWS Trainum and Inferentia chips.

Give DeepSeek-R1 models a try today in the Amazon Bedrock console, Amazon SageMaker AI console, and Amazon EC2 console, and send feedback to AWS re:Post for Amazon Bedrock and AWS re:Post for SageMaker AI or through your usual AWS Support contacts.

— Channy

The post DeepSeek-R1 models now available on AWS appeared first on The NOKIA Blog.

I counted about 40 new launches from AWS since last week – back to our normal rhythm of releases. Services teams are listening to your feedback and developing little (or big) changes that makes your life easier when working with our services. The ability to support multiple sessions in the AWS Console is my favorite one so far in 2025.

But our teams didn’t stop there, let’s look at the last week’s new announcements.

Last week’s launches

Beside the usual Regional expansion (new capabilities that are now available in a new Region), here are the launches that got my attention.

Amazon EventBridge announces direct delivery to cross-account targets – Amazon EventBridge is now able to deliver events to targets in another AWS account directly without having to send them to the default bus in the target account first. This will simplify so many architectures out there! It supports any target that supports resource-based policies, including AWS Lambda, Amazon Simple Queue Service (Amazon SQS), Amazon Simple Notification Service (Amazon SNS), Amazon Kinesis, and Amazon API Gateway.

Amazon Corretto quaterly update – We announced quarterly security and critical updates for Amazon Corretto Long-Term Supported (LTS) and Feature Release (FR) versions of OpenJDK. Corretto 23.0.2, 21.0.6, 17.0.14, 11.0.26, 8u442 are now available for download. Amazon Corretto is a no-cost, multi-platform, production-ready distribution of OpenJDK. You can download the updates from the Corretto home page or just type apt-get or yum update.

High-throughput mode for Amazon SNS FIFO Topics – Amazon SNS now supports high-throughput mode for SNS FIFO topics, with default throughput matching SNS standard topics across all Regions. When you enable high-throughput mode, SNS FIFO topics will maintain order within message group, while reducing the deduplication scope to the message-group level. With this change, you can leverage up to 30K messages per second (MPS) per account by default in US East (N. Virginia) Region, and 9K MPS per account in US West (Oregon) and Europe (Ireland) Regions, and request quota increases for additional throughput in any Region.

Amazon Connect agent workspace now supports audio optimization for Citrix and Amazon WorkSpaces virtual desktops – Amazon Connect agent workspace now supports the ability to redirect audio from Citrix and Amazon WorkSpaces Virtual Desktop Infrastructure (VDI) environments to a customer service agent’s local device. Audio redirection improves voice quality and reduces latency for voice calls handled on virtual desktops, providing a better experience for both end customers and agents.

Amazon Redshift announces support for History Mode for zero-ETL integrations – This new capability enables you to build Type 2 Slowly Changing Dimension (SCD 2) tables on your historical data from databases, out-of-the-box in Amazon Redshift, without writing any code. History mode simplifies the process of tracking and analyzing historical data changes, allowing you to gain valuable insights from your data’s evolution over time.

Finally, Amazon Bedrock has its own set of announcements. First, for anyone investing in retrieval-augmented generation, Bedrock now support multimodal content with Cohere Embed 3 Multilingual and Embed 3 English models. This enables you to create embeddings to not only index text, but also images.

Second, read Luma AI’s Ray2 visual AI model now available in Amazon Bedrock. Luma Ray2 is a large-scale video-generation model capable of creating realistic visuals with fluid, natural movement. With Luma Ray2 in Amazon Bedrock, you can generate production-ready video clips with seamless animations, ultrarealistic details, and logical event sequences with natural language prompts, removing the need for technical prompt engineering. Ray2 currently supports 5- and 9-second video generations with 540p and 720p resolution.

And finally, Amazon Bedrock Flows announces preview of multi-turn conversation support. Amazon Bedrock Flows enables you to link foundation models (FMs), Amazon Bedrock Prompts, Amazon Bedrock Agents, Amazon Bedrock Knowledge Bases, Amazon Bedrock Guardrails and other AWS services together to build and scale pre-defined generative AI workflows. This week, the team announced preview of multi-turn conversation support for agent nodes in Flows. This capability enables dynamic, back-and-forth conversations between users and flows, similar to a natural dialogue.

For a full list of AWS announcements, be sure to keep an eye on the What’s New at AWS page.

Other AWS events
Check your calendar and sign up for upcoming AWS events.

AWS Summits season is starting! I’m already working with the local team to prepare content for the Summits in Paris and London. Summits are free online and in-person events that bring the cloud computing community together to connect, collaborate, and learn about AWS. Stay updated by visiting the official AWS Summit website and sign up for notifications to learn when registration opens for events in your area.

AWS GenAI Lofts are collaborative spaces and immersive experiences that showcase AWS expertise in cloud computing and AI. They provide startups and developers with hands-on access to AI products and services, exclusive sessions with industry leaders, and valuable networking opportunities with investors and peers. Find a GenAI Loft location near you, and don’t forget to register.

Browse all upcoming AWS led in-person and virtual events here.

That’s all for this week. Check back next Monday for another Weekly Roundup!

— seb

This post is part of our Weekly Roundup series. Check back each week for a quick roundup of interesting news and announcements from AWS!

The post AWS Weekly roundup: EventBridge, SNS FIFO, Amazon Corretto, Amazon Connect, Amazon Bedrock, and more appeared first on The NOKIA Blog.