|
By Datadog
Teams that build agents on open models hosted on Fireworks AI, such as GPT-OSS, Kimi, GLM, Qwen, and MiniMax, need a reliable way to measure whether their LLM applications and agents are giving accurate, safe, and helpful answers efficiently. Datadog Agent Observability now supports Fireworks AI as a model provider, so you can get end-to-end visibility into your agents built on Fireworks AI, from traces and token usage to quality evaluations.
|
By Datadog
Prompts are an important part of LLM application behavior, but teams often manage them alongside application code or across separate notebooks and configuration files. This can make prompt changes dependent on application releases and make it difficult to understand which version is running in each environment. When a change affects application quality, latency, or cost, teams also need a way to connect that behavior back to the prompt version that produced it.
|
By Datadog
When a mobile application takes too long to launch or becomes unresponsive, it can be difficult to find the cause. Datadog Real User Monitoring (RUM) helps developers detect these issues and understand which users are affected. But knowing that an application is slow doesn’t tell you which part of its code is responsible. Engineers often need to reproduce the problem locally, piecing together performance metrics and code execution information from separate tools.
|
By Datadog
Improving an AI agent means knowing which behaviors to change and where those changes will have the greatest impact. Insights in Datadog Agent Observability improves AI agents by analyzing agent traces to identify recurring cost and reliability problems. It then explains the causes of those problems, assesses their impact, and recommends fixes backed by evidence. At Datadog, we use Insights to improve the agent behind Insights.
|
By Datadog
In September 2026, OpenAI reported finding self-replicating prompt injections. These attacks hide instructions in content an AI agent retrieves, directing it to take unauthorized actions and copy those instructions into emails, files, or messages. Copied instructions can then expose other agents or later sessions to the same attack, giving it the potential to spread like a computer worm.
|
By Datadog
Datadog has been named a Leader in The Forrester Wave: AIOps Platforms, Q4 2026. We believe this placement reflects Datadog’s commitment to transforming observability into autonomous operations with a single integrated platform where AI agents detect, investigate, and remediate production issues, while engineers stay in control. Close dialog.
|
By Datadog
A voice agent can return the right words and still deliver a poor experience. It might leave a caller in silence, speak over them, or stop midway through a response. A transcript may look correct even when the audio the user heard was delayed, incomplete, or different from the text on screen. These problems are difficult to diagnose from text traces alone. Voice conversations also involve more than a single request and response.
|
By Datadog
Serverless should be the first execution model teams evaluate for AI agent workloads. Many agents spend much of their lifetime waiting, and always-on compute forces teams to pay for every idle minute. In a study of more than 35,000 production coding-agent sessions, the median session ran LLM or tool calls for only 20% of its lifetime. The rest of the time, it sat idle between steps, with its sandbox still allocated.
|
By Datadog
A back-office server that runs out of disk space can interrupt an important internal workflow. A process that stops on a staging host can delay development. Although workloads like these might not require application-level instrumentation, teams still need to know when the hosts that support them require attention. Without a monitoring solution tailored to these requirements, teams have to apply more monitoring than the workload needs, maintain a separate tool, or accept a gap in visibility.
|
By Datadog
Running one A/B test well is manageable. Scaling A/B testing to hundreds of experiments across dozens of teams is harder, because teams may make different decisions about metrics, randomization, rollout, and analysis. Experiment protocols in Datadog Experiments turn an approved methodology into a reusable configuration, giving experiments of the same type a consistent starting point. In this post, you’ll learn how to.
|
By Datadog
October’s This Month in Datadog comes to you from the Datadog Summit in San Francisco, where Jeremy shares a look inside the event, with our latest product updates. Plus, we cover how to: Build and manage Datadog Workflows using natural language, turning descriptions of automation tasks into workflows that teams can review before publishing Detect and investigate Kafka issues with Kafka Console, bringing health and performance data into one place Turn raw logs into structured fields with Datadog Tap, making logs easier to search and analyze.
|
By Datadog
AI has become incredibly sophisticated and changed the way we build and power applications. But it has also introduced volatile complexity that challenges how we ensure reliability and protect user experiences. Join our panel of experts as they discuss the realities of building AI-powered applications. They’ll talk about how testing has evolved, share insights into how they do evals and experiments, and offer advice on how to get better visibility into how your AI is performing.
|
By Datadog
As Datadog scaled to handle over a hundred trillion daily events, our engineering teams built their own custom query engines to keep things fast. While this helped teams move quickly, it also created silos that made it tough to analyze data across different products. To keep growing and support AI, we had to find a way to bring these engines together using open standards without slowing anyone down or risking reliability.
|
By Datadog
Join Datadog's Chief Product Officer Yanbing Li and OpenAI's Member of Product Staff Alexander Embiricos as they discuss emerging technologies and innovation, how they impact businesses today, and the new opportunities they create for you.
|
By Datadog
Automate Slack support questions with Datadog Workflow Automation and Bits AI Agent Builder. Datadog Workflow Automation can now trigger directly from messages posted in Slack. In this quick demo, Yuta Yoshida, Product Manager at Datadog, shows how to build an automated support workflow that: → Detects new support questions in a Slack channel→ Sends questions to a custom agent built with Bits AI Agent Builder→ Replies directly in the Slack thread with an answer and relevant documentation.
|
By Datadog
See how Datadog Journey Monitoring brings together user behavior, real-user insights, and proactive testing to track the health of critical user journeys, understand business impact, and quickly troubleshoot issues.
|
By Datadog
Modal is an AI infrastructure company rebuilding the cloud for AI, giving developers easy access to the compute needed to build and scale AI applications without managing the underlying complexity. Operating across more than 20 cloud providers and launching approximately 26 million containers daily, Modal relies on Datadog to unify observability across its infrastructure, applications, networking, and CI—helping its engineers detect 99% of incidents within five minutes, resolve 96% of issues before customer impact, and confidently scale one of the world’s most complex AI platforms.
|
By Datadog
Engineering ships faster than ever with AI writing more of the code, but test coverage has to keep pace, or users find the broken flows first.
|
By Datadog
Incident response often spans a patchwork of tools, handoffs, and manual steps. An engineer gets paged, a team investigates the issue, the incident commander coordinates the response, SREs document decisions, and somebody (anybody!) writes the postmortem. Every handoff introduces more context switching, increasing the risk of critical information loss, and ultimately slowing resolution.
|
By Datadog
When production breaks, the clues are everywhere but the story is scattered. RUM sessions, APM traces, metrics, and logs allow Datadog to tell you part of the story. What’s missing is your service ownership quirks, your team's conventions, or the three-year-old workaround buried in a comment that explains why a certain endpoint behaves the way it does.
|
By Datadog
The elasticity and nearly infinite scalability of the cloud have transformed IT infrastructure. Modern infrastructure is now made up of constantly changing, often short-lived VMs or containers. This has elevated the need for new methods and new tools for monitoring. In this eBook, we outline an effective framework for monitoring modern infrastructure and applications, however large or dynamic they may be.
|
By Datadog
As Docker adoption continues to rise, many organizations have turned to orchestration platforms like ECS and Kubernetes to manage large numbers of ephemeral containers. Thousands of companies use Datadog to monitor millions of containers, which enables us to identify trends in real-world orchestration usage. We're excited to share 8 key findings of our research.
|
By Datadog
Where does Docker adoption currently stand and how has it changed? With thousands of companies using Datadog to track their infrastructure, we can see software trends emerging in real time. We're excited to share what we can see about true Docker adoption.
|
By Datadog
Build an effective framework for monitoring AWS infrastructure and applications, however large or dynamic they may be. The elasticity and nearly infinite scalability of the AWS cloud have transformed IT infrastructure. Modern infrastructure is now made up of constantly changing, often short-lived components. This has elevated the need for new methods and new tools for monitoring.
|
By Datadog
Like a car, Elasticsearch was designed to allow you to get up and running quickly, without having to understand all of its inner workings. However, it's only a matter of time before you run into engine trouble here or there. This guide explains how to address five common Elasticsearch challenges.
|
By Datadog
Monitoring Kubernetes requires you to rethink your monitoring strategies, especially if you are used to monitoring traditional hosts such as VMs or physical machines. This guide prepares you to effectively approach Kubernetes monitoring in light of its significant operational differences.
- November 2026 (3)
- October 2026 (36)
- September 2026 (24)
- August 2026 (19)
- July 2026 (16)
- June 2026 (30)
- May 2026 (27)
- April 2026 (26)
- March 2026 (36)
- February 2026 (20)
- January 2026 (17)
- December 2025 (36)
- November 2025 (33)
- October 2025 (27)
- September 2025 (19)
- August 2025 (24)
- July 2025 (30)
- June 2025 (25)
- May 2025 (20)
- April 2025 (15)
- March 2025 (16)
- February 2025 (16)
- January 2025 (29)
- December 2024 (23)
- November 2024 (28)
- October 2024 (15)
- September 2024 (15)
- August 2024 (10)
- July 2024 (15)
- June 2024 (26)
- May 2024 (12)
- April 2024 (19)
- March 2024 (11)
- February 2024 (21)
- January 2024 (19)
- December 2023 (18)
- November 2023 (22)
- October 2023 (15)
- September 2023 (14)
- August 2023 (28)
- July 2023 (15)
- June 2023 (17)
- May 2023 (22)
- April 2023 (13)
- March 2023 (22)
- February 2023 (12)
- January 2023 (8)
- December 2022 (9)
- November 2022 (27)
- October 2022 (22)
- September 2022 (14)
- August 2022 (22)
- July 2022 (13)
- June 2022 (13)
- May 2022 (18)
- April 2022 (14)
- March 2022 (6)
- February 2022 (14)
- January 2022 (17)
- December 2021 (9)
- November 2021 (16)
- October 2021 (26)
- September 2021 (8)
- August 2021 (18)
- July 2021 (15)
- June 2021 (16)
- May 2021 (23)
- April 2021 (20)
- March 2021 (16)
- February 2021 (9)
- January 2021 (10)
- December 2020 (22)
- November 2020 (17)
- October 2020 (12)
- September 2020 (15)
- August 2020 (22)
- July 2020 (20)
- June 2020 (14)
- May 2020 (18)
- April 2020 (24)
- March 2020 (13)
- February 2020 (13)
- January 2020 (11)
- December 2019 (16)
- November 2019 (11)
- October 2019 (11)
- September 2019 (11)
- August 2019 (16)
- July 2019 (18)
- June 2019 (11)
- May 2019 (12)
- April 2019 (20)
- March 2019 (10)
- February 2019 (9)
- January 2019 (6)
- December 2018 (7)
- November 2018 (7)
- October 2018 (13)
- September 2018 (5)
- August 2018 (12)
- July 2018 (12)
- June 2018 (6)
- March 2018 (1)
- December 2017 (1)
- November 2017 (1)
- March 2015 (1)
Datadog is the essential monitoring platform for cloud applications. We bring together data from servers, containers, databases, and third-party services to make your stack entirely observable. These capabilities help DevOps teams avoid downtime, resolve performance issues, and ensure customers are getting the best user experience.
See it all in one place:
- See across systems, apps, and services: With turn-key integrations, Datadog seamlessly aggregates metrics and events across the full devops stack.
- Get full visibility into modern applications: Monitor, troubleshoot, and optimize application performance.
- Analyze and explore log data in context: Quickly search, filter, and analyze your logs for troubleshooting and open-ended exploration of your data.
- Build real-time interactive dashboards: More than summary dashboards, Datadog offers all high-resolution metrics and events for manipulation and graphing.
- Get alerted on critical issues: Datadog notifies you of performance problems, whether they affect a single host or a massive cluster.
Modern monitoring & analytics. See inside any stack, any app, at any scale, anywhere.