<\/span><\/h3>\nDatadog LLM Observability addresses these pains by automatically instrumenting and tracing your ADK agents, so you can start evaluating your agents offline and monitoring them in production in minutes \u2014 without code changes. This allows you to visualize every step and planner choice \u2014 from agent orchestration to tool calls \u2014 on a single trace timeline.<\/span><\/p>\nFor example, if an agent selects an incorrect tool to respond to a user query, it can yield unexpected errors or inaccurate responses. You can use Datadog\u2019s visualizations to pinpoint the exact step where the incorrect tool was selected, making troubleshooting easier and helping you reproduce the issue.<\/span><\/p>\n<\/span>Monitor token usage and latency<\/b><\/span><\/h3>\nSudden increases in latency or cost are often a sign of trouble in agentic applications. Datadog lets you view token usage and latency per tool, branch, and workflow to identify where errors happened and how they affected downstream steps.<\/span><\/p>\nFor example, if a planner agent retries a summarization tool five times, it can significantly increase latency. Datadog highlights these loops, showing you exactly how long they took and the associated cost impact.<\/span><\/p>\n<\/span>Evaluate agent response quality and security<\/b><\/span><\/h3>\nOperational performance metrics like latency are critical monitoring signals, but for a holistic view of how agentic applications are performing, teams also need to evaluate the semantic quality of the LLM and agentic responses. Datadog provides built-in evaluations to detect hallucinations, PII leaks, prompt injections, and unsafe responses.<\/span><\/p>\nYou can also add custom evaluators, including LLM-as-a-judge evaluators, for domain-specific checks. For instance, if a retrieval agent fetches irrelevant documents that lead to off-topic answers, a custom evaluator can flag that trace as having low retrieval relevance.<\/p>\n
<\/span>Iterate quickly and confidently with experiments<\/b><\/span><\/h3>\nWhen you roll out a new system prompt, you might notice spikes in latency or drifts in output consistency. Datadog allows you to replay production LLM calls in its Playground to test different models, prompts, or parameters to find the configurations that move you closer to your ideal behavior.<\/span>From there, you can run structured experiments to compare versions side-by-side using datasets built from real traffic to optimize operational and functional performance. Because every agent step is logged through ADK instrumentation, you have the full context you need to reproduce regressions and validate fixes before you deploy.<\/p>\n<\/span>Get started with Datadog LLM Observability<\/b><\/span><\/h3>\nDatadog LLM Observability simplifies monitoring and debugging for Google ADK systems, helping users debug agent operations, evaluate responses, iterate quickly, and validate changes before deploying them to production.<\/span><\/p>\nYou can get started today with the latest version of the LLM Observability SDK, or start a free trial if you are new to Datadog.<\/span><\/p>\nFor more information on how to debug agent operations and evaluate responses, view Datadog\u2019s LLM Observability documentation.<\/span><\/p>","protected":false},"excerpt":{"rendered":"Google\u2019s Agent Development Kit (ADK) cung c\u1ea5p cho b\u1ea1n c\u00e1c kh\u1ed1i x\u00e2y d\u1ef1ng \u0111\u1ec3 t\u1ea1o ra c\u00e1c h\u1ec7 th\u1ed1ng t\u00e1c nh\u00e2n m\u1ea1nh m\u1ebd. C\u00e1c t\u00e1c nh\u00e2n \u0111a b\u01b0\u1edbc n\u00e0y c\u00f3 th\u1ec3 l\u1eadp k\u1ebf ho\u1ea1ch, l\u1eb7p l\u1ea1i, c\u1ed9ng t\u00e1c v\u00e0 g\u1ecdi…<\/p>","protected":false},"author":2,"featured_media":24816,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"inline_featured_image":false,"footnotes":""},"categories":[1,135],"tags":[],"class_list":["post-24815","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-kienthuc","category-google-cloud-platform","entry","has-media"],"_links":{"self":[{"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/posts\/24815","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/comments?post=24815"}],"version-history":[{"count":2,"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/posts\/24815\/revisions"}],"predecessor-version":[{"id":24821,"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/posts\/24815\/revisions\/24821"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/media\/24816"}],"wp:attachment":[{"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/media?parent=24815"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/categories?post=24815"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/gcloudvn.com\/en\/wp-json\/wp\/v2\/tags?post=24815"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
![\"\"](\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/02\/1762240252529.jpg\")
<\/a><\/p>\n![\"\"](\"https:\/\/gcloudvn.com\/wp-content\/uploads\/2026\/02\/adk-social-card.png\")
<\/a><\/p>\n