Skip to main content

Datadog Introduces LLM Observability and Other New Capabilities

Datadog announced a new strategic collaboration agreement (SCA) with Amazon Web Services (AWS) and showcased multiple product launches across AI, observability and security to help organizations running on AWS monitor, optimize and secure their cloud environments.

“These launches further extend Datadog’s ability to deliver AI-powered observability and security at scale. They cover all aspects of a customer’s tech stack, including LLM and agentic applications, cloud object storage, and containerized and serverless infrastructure, so that joint customers can migrate to and manage their AWS, hybrid and multi-cloud environments with confidence,” said Yanbing Li, Chief Product Officer at Datadog.

The new Datadog product capabilities for joint AWS customers showcased at re:Invent include:

  • LLM Observability: Monitor, operate and debug agent workflows for both Amazon Bedrock Agents and Strands Agents Framework.
  • Storage Management: Get granular visibility into Amazon S3 buckets and prefixes, enabling teams to eliminate waste and prevent unexpected cloud object storage spend.
  • Datadog MCP Server Integration with AWS DevOps Agent (in Preview): Automate incident resolution by enabling AWS DevOps Agent to query Datadog logs, metrics, and traces during investigations.
  • Support for Datadog MCP Server in Kiro (in Preview): Fix bugs more effectively within your IDE by giving Kiro full Datadog context including errors, recent deployments, linked tickets, and more.
  • New Kiro power from Datadog (in Preview): Specialize your Kiro agents for observability use cases by one-click download of MCP server and steering files for use in Kiro to enable debugging of production issues and develop better code.
  • Support for AWS Lambda Managed Instances (in Preview): Gain full visibility into AWS Lambda functions running on EC2.
  • Support for Amazon Elastic Container Service (ECS) Managed Instances (in Preview): Monitor and troubleshoot workloads running on Amazon ECS Managed Instances.
  • Support for Amazon ECS Express Mode: Gain visibility into containers running on ECS Express Mode.
  • Bits AI Serverless Remediation (in Preview): Troubleshoot issues running serverless applications on AWS with AI-augmented remediation.
  • Bits AI Kubernetes Active Remediation: Accelerate issue resolution for Amazon EKS workloads with AI-guided, evidence-based recommendations.
  • AWS Lambda Cost Recommendations: Automatically identify savings opportunities for AWS Lambda, such as optimizing provisioned concurrency or deleting redundant Amazon CloudWatch logs in AWS Lambda.
  • Amazon Relational Database Service (Amazon RDS) Instance Recommendations: Automatically source optimizations for Amazon RDS instances, such as when an instance has low disk space, high disk queue depth, or read-only traffic.
  • Observability Pipelines Packs for AWS (in Preview): Speed up data processing with predefined, ready-to-use Packs for Amazon Virtual Private Cloud (Amazon VPC), AWS CloudTrail and Amazon CloudFront.
  • Observability Pipelines S3 Log Rehydration (in Preview): Quickly access and reprocess historical logs from Amazon S3 to any destination.

As part of an ongoing commitment to deliver value to joint customers, Datadog has also signed a new Strategic Collaboration Agreement (SCA) with AWS. Through deeper collaboration with AWS on solution development, AWS Marketplace availability and go-to-market programs, Datadog will help customers de-risk cloud migrations, accelerate modernization, secure AWS and multi-cloud environments, and confidently deploy GenAI capabilities on AWS. Datadog’s collaboration spans all regions and industries, including public sector, enterprise and ISVs, and strengthens Datadog’s position as a strategic partner of AWS.

“As cloud-native applications and AI workloads accelerate, observability and security across AWS environments are top of mind for enterprise customers,” said Jarrod Buckley, Vice President of Channels and Alliances at Datadog. “Expanding our global collaboration with AWS enables continued innovation to help customers become more resilient, reduce risk, and achieve time-to-value faster.”

“AWS is committed to working with partners like Datadog to help customers innovate and succeed in the AI era,” said Chris Grusz, Managing Director, Technology Partnerships at AWS. “As organizations increasingly rely on AI-powered applications, observability has become essential for ensuring performance, reliability and cost optimization at scale. Through this strategic collaboration and new integrations with AWS services, we’re making it easier for customers to gain deep insights into their AWS infrastructure and applications, enabling them to build with confidence and accelerate their AI initiatives."

The Latest

The final two installments of the series, Exploring AI Observability, cover predictions from the experts about where AI observability is heading ... In the next few years, tracking your AI won't just be a nice-to-have tool, it will be a survival requirement for businesses ...

Cloud absolutely changed IT for the better. But after more than a decade of using it, companies have also learned something else. Where an application runs matters, and there isn't one environment that makes sense for everything ...

Automation often starts with the people closest to an immediate need. A developer may schedule a script with cron or Amazon EventBridge Scheduler; a business team may adopt an RPA bot, low-code platform, or agent. Many tools stay useful within one domain. Some become consequential across organizational boundaries because other systems and teams depend on them or business outcomes rely on their timing and recovery. Those cases may call for broader coordination ...

The conventional wisdom in our industry says that AI demands a new operating model and specific data tailored for it. I disagree. AI is changing the rules, but not in the way people think ...

Most organizations invest heavily in security tools, policies, and controls. Yet despite these efforts, one reality persists: employees often find ways around them. This isn't always malicious. In many cases, it’s a response to friction, urgency, or misalignment between how work actually happens and how systems are designed to protect it. When employees bypass security, it creates blind spots. Sensitive data may move through unmonitored channels, access controls may be weakened, and risks that security teams intended to mitigate reappear in new forms ...

Enterprise AI projects are often justified with a familiar metric: hours saved. A team automates a manual process, employees spend fewer hours reviewing documents or entering data, and the productivity gain becomes the headline. Time savings matter, but they capture only part of the financial impact AI can have inside an organization ... A more useful way to evaluate enterprise AI is to examine the financial decisions and risks surrounding the workflows it supports ...

We run an internal AI assistant that answers engineering questions in Slack ... Each question kicks off what we call a turn ... We could already audit a single turn after the fact. Every reply carries a short lookup token in its footer, and a slash command pulls up the full receipt for that turn. What we could not do was answer questions about the whole fleet. How long do turns take? What do they cost? Which tools does the agent reach for? Where does the time go inside a single answer? Those are APM questions. So we treated the agent like any other service and instrumented it with OpenTelemetry, end to end. This post covers what we built, the design choices that turned out to matter, and the things that surprised us ...

Applications have long used bounded, deterministic logic to control what happens within their own functions. Process orchestration coordinates activity across people, applications, decisions, and automation tools. Workload orchestration coordinates executable work and dependencies across applications, platforms, and infrastructure. As agentic capabilities enter applications and domain systems, more planning and decision-making will also occur inside those environments. These forms of automation will coexist. Sometimes they will overlap, and they will increasingly need to exchange triggers, state, and results. But they are not becoming interchangeable ...

For many organizations, the AI agenda has landed squarely on the CIO's desk. At first glance, that makes perfect sense. AI depends on data, infrastructure, security, integration, governance and scalable technology platforms — all areas where the CIO plays a central role. But there is a problem with treating AI primarily as an IT initiative: AI is not simply a technology deployment. It’s also a business transformation ...

In MEAN TIME TO INSIGHT Episode 28, Shamus McGillicuddy, EMA VP of Research, Network Infrastructure and Operations, and special guest Sanjay Gidwani, Founder & CEO of Kosmos AI Labs, discuss root cause analysis ... 

Datadog Introduces LLM Observability and Other New Capabilities

Datadog announced a new strategic collaboration agreement (SCA) with Amazon Web Services (AWS) and showcased multiple product launches across AI, observability and security to help organizations running on AWS monitor, optimize and secure their cloud environments.

“These launches further extend Datadog’s ability to deliver AI-powered observability and security at scale. They cover all aspects of a customer’s tech stack, including LLM and agentic applications, cloud object storage, and containerized and serverless infrastructure, so that joint customers can migrate to and manage their AWS, hybrid and multi-cloud environments with confidence,” said Yanbing Li, Chief Product Officer at Datadog.

The new Datadog product capabilities for joint AWS customers showcased at re:Invent include:

  • LLM Observability: Monitor, operate and debug agent workflows for both Amazon Bedrock Agents and Strands Agents Framework.
  • Storage Management: Get granular visibility into Amazon S3 buckets and prefixes, enabling teams to eliminate waste and prevent unexpected cloud object storage spend.
  • Datadog MCP Server Integration with AWS DevOps Agent (in Preview): Automate incident resolution by enabling AWS DevOps Agent to query Datadog logs, metrics, and traces during investigations.
  • Support for Datadog MCP Server in Kiro (in Preview): Fix bugs more effectively within your IDE by giving Kiro full Datadog context including errors, recent deployments, linked tickets, and more.
  • New Kiro power from Datadog (in Preview): Specialize your Kiro agents for observability use cases by one-click download of MCP server and steering files for use in Kiro to enable debugging of production issues and develop better code.
  • Support for AWS Lambda Managed Instances (in Preview): Gain full visibility into AWS Lambda functions running on EC2.
  • Support for Amazon Elastic Container Service (ECS) Managed Instances (in Preview): Monitor and troubleshoot workloads running on Amazon ECS Managed Instances.
  • Support for Amazon ECS Express Mode: Gain visibility into containers running on ECS Express Mode.
  • Bits AI Serverless Remediation (in Preview): Troubleshoot issues running serverless applications on AWS with AI-augmented remediation.
  • Bits AI Kubernetes Active Remediation: Accelerate issue resolution for Amazon EKS workloads with AI-guided, evidence-based recommendations.
  • AWS Lambda Cost Recommendations: Automatically identify savings opportunities for AWS Lambda, such as optimizing provisioned concurrency or deleting redundant Amazon CloudWatch logs in AWS Lambda.
  • Amazon Relational Database Service (Amazon RDS) Instance Recommendations: Automatically source optimizations for Amazon RDS instances, such as when an instance has low disk space, high disk queue depth, or read-only traffic.
  • Observability Pipelines Packs for AWS (in Preview): Speed up data processing with predefined, ready-to-use Packs for Amazon Virtual Private Cloud (Amazon VPC), AWS CloudTrail and Amazon CloudFront.
  • Observability Pipelines S3 Log Rehydration (in Preview): Quickly access and reprocess historical logs from Amazon S3 to any destination.

As part of an ongoing commitment to deliver value to joint customers, Datadog has also signed a new Strategic Collaboration Agreement (SCA) with AWS. Through deeper collaboration with AWS on solution development, AWS Marketplace availability and go-to-market programs, Datadog will help customers de-risk cloud migrations, accelerate modernization, secure AWS and multi-cloud environments, and confidently deploy GenAI capabilities on AWS. Datadog’s collaboration spans all regions and industries, including public sector, enterprise and ISVs, and strengthens Datadog’s position as a strategic partner of AWS.

“As cloud-native applications and AI workloads accelerate, observability and security across AWS environments are top of mind for enterprise customers,” said Jarrod Buckley, Vice President of Channels and Alliances at Datadog. “Expanding our global collaboration with AWS enables continued innovation to help customers become more resilient, reduce risk, and achieve time-to-value faster.”

“AWS is committed to working with partners like Datadog to help customers innovate and succeed in the AI era,” said Chris Grusz, Managing Director, Technology Partnerships at AWS. “As organizations increasingly rely on AI-powered applications, observability has become essential for ensuring performance, reliability and cost optimization at scale. Through this strategic collaboration and new integrations with AWS services, we’re making it easier for customers to gain deep insights into their AWS infrastructure and applications, enabling them to build with confidence and accelerate their AI initiatives."

The Latest

The final two installments of the series, Exploring AI Observability, cover predictions from the experts about where AI observability is heading ... In the next few years, tracking your AI won't just be a nice-to-have tool, it will be a survival requirement for businesses ...

Cloud absolutely changed IT for the better. But after more than a decade of using it, companies have also learned something else. Where an application runs matters, and there isn't one environment that makes sense for everything ...

Automation often starts with the people closest to an immediate need. A developer may schedule a script with cron or Amazon EventBridge Scheduler; a business team may adopt an RPA bot, low-code platform, or agent. Many tools stay useful within one domain. Some become consequential across organizational boundaries because other systems and teams depend on them or business outcomes rely on their timing and recovery. Those cases may call for broader coordination ...

The conventional wisdom in our industry says that AI demands a new operating model and specific data tailored for it. I disagree. AI is changing the rules, but not in the way people think ...

Most organizations invest heavily in security tools, policies, and controls. Yet despite these efforts, one reality persists: employees often find ways around them. This isn't always malicious. In many cases, it’s a response to friction, urgency, or misalignment between how work actually happens and how systems are designed to protect it. When employees bypass security, it creates blind spots. Sensitive data may move through unmonitored channels, access controls may be weakened, and risks that security teams intended to mitigate reappear in new forms ...

Enterprise AI projects are often justified with a familiar metric: hours saved. A team automates a manual process, employees spend fewer hours reviewing documents or entering data, and the productivity gain becomes the headline. Time savings matter, but they capture only part of the financial impact AI can have inside an organization ... A more useful way to evaluate enterprise AI is to examine the financial decisions and risks surrounding the workflows it supports ...

We run an internal AI assistant that answers engineering questions in Slack ... Each question kicks off what we call a turn ... We could already audit a single turn after the fact. Every reply carries a short lookup token in its footer, and a slash command pulls up the full receipt for that turn. What we could not do was answer questions about the whole fleet. How long do turns take? What do they cost? Which tools does the agent reach for? Where does the time go inside a single answer? Those are APM questions. So we treated the agent like any other service and instrumented it with OpenTelemetry, end to end. This post covers what we built, the design choices that turned out to matter, and the things that surprised us ...

Applications have long used bounded, deterministic logic to control what happens within their own functions. Process orchestration coordinates activity across people, applications, decisions, and automation tools. Workload orchestration coordinates executable work and dependencies across applications, platforms, and infrastructure. As agentic capabilities enter applications and domain systems, more planning and decision-making will also occur inside those environments. These forms of automation will coexist. Sometimes they will overlap, and they will increasingly need to exchange triggers, state, and results. But they are not becoming interchangeable ...

For many organizations, the AI agenda has landed squarely on the CIO's desk. At first glance, that makes perfect sense. AI depends on data, infrastructure, security, integration, governance and scalable technology platforms — all areas where the CIO plays a central role. But there is a problem with treating AI primarily as an IT initiative: AI is not simply a technology deployment. It’s also a business transformation ...

In MEAN TIME TO INSIGHT Episode 28, Shamus McGillicuddy, EMA VP of Research, Network Infrastructure and Operations, and special guest Sanjay Gidwani, Founder & CEO of Kosmos AI Labs, discuss root cause analysis ...