--- title: Introducing Amazon CloudWatch Omni: AI-powered... description: Amazon CloudWatch Omni is a new unified observability, evaluation, and experimentation solution for AI agents, now generally available. It offers a VS Code and... canonical: https://daily.dev/posts/introducing-amazon-cloudwatch-omni-ai-powered-observability-for-generative-ai-and-agentic-workloads-9f5hlnycw twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Introducing Amazon CloudWatch Omni: AI-powered observability for generative AI and agentic workloads | daily.dev og:description: Amazon CloudWatch Omni is a new unified observability, evaluation, and experimentation solution for AI agents, now generally available. It offers a VS Code and... og:url: https://daily.dev/posts/introducing-amazon-cloudwatch-omni-ai-powered-observability-for-generative-ai-and-agentic-workloads-9f5hlnycw og:image: https://api.daily.dev/og/posts/9f5hLnyCW.png og:image:alt: Introducing Amazon CloudWatch Omni: AI-powered observability for generative AI and agentic workloads og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Introducing Amazon CloudWatch Omni: AI-powered observability for generative AI and agentic workloads **[AWS](https://daily.dev/sources/aws)** · 8 min read · 1 upvotes · 0 comments ## Summary Amazon CloudWatch Omni is a new unified observability, evaluation, and experimentation solution for AI agents, now generally available. It offers a VS Code and Kiro IDE extension plus a standalone web experience separate from the AWS Management Console, letting developers trace agent execution, run built-in evaluators (17 metrics like coherence, helpfulness, faithfulness), compare prompt versions in a playground, build experiments from golden datasets, and detect regressions. It works with frameworks like LangChain, LangGraph, CrewAI, OpenAI SDK, Strands, and Vercel AI SDK, uses open standards (OpenInference, ADOT), integrates with Amazon Bedrock AgentCore, and supports third-party evaluators such as Braintrust, DeepEval, and Ragas. The IDE extension is free and doesn't require an AWS account to start. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is Amazon CloudWatch Omni and what does it do for AI agent monitoring? Amazon CloudWatch Omni is a unified observability, evaluation, and experimentation solution purpose-built for AI agents, generally available now. It captures full traces of agent execution (tool calls, LLM calls, reasoning steps), includes 17 built-in evaluators for metrics like coherence, helpfulness, and faithfulness, and offers a playground for comparing prompts plus an experiments view for testing agent variants against datasets. _Teams evaluating agent observability tools can track releases like CloudWatch Omni on daily.dev._ ### Which AI agent frameworks does Amazon CloudWatch Omni support? CloudWatch Omni supports LangChain, LangGraph, CrewAI, OpenAI SDK, Strands, and Vercel AI SDK in both Python and TypeScript, plus native observability for agents built with Amazon Bedrock AgentCore. Instrumentation relies on open standards OpenInference and ADOT, so agents can run on Lambda, ECS, EKS, or other clouds without re-platforming. _Developers comparing agent frameworks and tracing standards can follow updates like this on daily.dev._ ### Do I need an AWS account to use the CloudWatch Omni IDE extension? No, an AWS account is not required to get started with the CloudWatch Omni IDE extension for VS Code or Kiro, and the extension itself is free. Data is stored locally by default; you only need AWS credentials for Amazon Bedrock models or API keys for providers like OpenAI or Anthropic, and can optionally connect to AWS via Cloud Login to send telemetry to CloudWatch for production monitoring. _Anyone setting up local-first AI agent tooling can keep tabs on options like this via daily.dev._ ## Similar posts on daily.dev - [Amazon CloudWatch announces coding agent insights](https://daily.dev/posts/amazon-cloudwatch-announces-coding-agent-insights-ji7rsir7n) · AWS · 1 upvotes · 0 comments - [Amazon SageMaker AI Announces New observability capability For Inference Endpoints](https://daily.dev/posts/amazon-sagemaker-ai-announces-new-observability-capability-for-inference-endpoints-vnlhclrpa) · AWS · 0 upvotes · 0 comments --- Tags: [#aws](https://daily.dev/tags/aws), [#ai-agents](https://daily.dev/tags/ai-agents), [#observability](https://daily.dev/tags/observability), [#opentelemetry](https://daily.dev/tags/opentelemetry) [View this post on daily.dev](https://daily.dev/posts/introducing-amazon-cloudwatch-omni-ai-powered-observability-for-generative-ai-and-agentic-workloads-9f5hlnycw) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Introducing Amazon CloudWatch Omni: AI-powered observability for generative AI and agentic workloads","url":"https://daily.dev/posts/introducing-amazon-cloudwatch-omni-ai-powered-observability-for-generative-ai-and-agentic-workloads-9f5hlnycw","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/introducing-amazon-cloudwatch-omni-ai-powered-observability-for-generative-ai-and-agentic-workloads-9f5hlnycw"},"datePublished":"2026-09-22T22:52:14.892Z","dateModified":"2026-09-23T01:00:00.209Z","description":"Amazon CloudWatch Omni is a new unified observability, evaluation, and experimentation solution for AI agents, now generally available. It offers a VS Code and...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/de700678893816728b6b7f4aa46f5182?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/de700678893816728b6b7f4aa46f5182?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"AWS","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"AWS","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/aws","url":"https://daily.dev/sources/aws"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/introducing-amazon-cloudwatch-omni-ai-powered-observability-for-generative-ai-and-agentic-workloads-9f5hlnycw","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"aws,ai-agents,observability,opentelemetry","timeRequired":"PT8M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"AWS","item":"https://daily.dev/sources/aws"},{"@type":"ListItem","position":3,"name":"Introducing Amazon CloudWatch Omni: AI-powered observability for generative AI and agentic workloads"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/introducing-amazon-cloudwatch-omni-ai-powered-observability-for-generative-ai-and-agentic-workloads-9f5hlnycw#faq","mainEntity":[{"@type":"Question","name":"What is Amazon CloudWatch Omni and what does it do for AI agent monitoring?","acceptedAnswer":{"@type":"Answer","text":"Amazon CloudWatch Omni is a unified observability, evaluation, and experimentation solution purpose-built for AI agents, generally available now. It captures full traces of agent execution (tool calls, LLM calls, reasoning steps), includes 17 built-in evaluators for metrics like coherence, helpfulness, and faithfulness, and offers a playground for comparing prompts plus an experiments view for testing agent variants against datasets. Teams evaluating agent observability tools can track releases like CloudWatch Omni on daily.dev."}},{"@type":"Question","name":"Which AI agent frameworks does Amazon CloudWatch Omni support?","acceptedAnswer":{"@type":"Answer","text":"CloudWatch Omni supports LangChain, LangGraph, CrewAI, OpenAI SDK, Strands, and Vercel AI SDK in both Python and TypeScript, plus native observability for agents built with Amazon Bedrock AgentCore. Instrumentation relies on open standards OpenInference and ADOT, so agents can run on Lambda, ECS, EKS, or other clouds without re-platforming. Developers comparing agent frameworks and tracing standards can follow updates like this on daily.dev."}},{"@type":"Question","name":"Do I need an AWS account to use the CloudWatch Omni IDE extension?","acceptedAnswer":{"@type":"Answer","text":"No, an AWS account is not required to get started with the CloudWatch Omni IDE extension for VS Code or Kiro, and the extension itself is free. Data is stored locally by default; you only need AWS credentials for Amazon Bedrock models or API keys for providers like OpenAI or Anthropic, and can optionally connect to AWS via Cloud Login to send telemetry to CloudWatch for production monitoring. Anyone setting up local-first AI agent tooling can keep tabs on options like this via daily.dev."}}]} ```