--- title: Agent Observability FAQ: Understand the value of... description: Grafana Cloud's Agent Observability feature is now generally available for monitoring, evaluating, and improving AI agents. It tracks latency, errors, token... canonical: https://daily.dev/posts/agent-observability-faq-understand-the-value-of-monitoring-evaluating-and-improving-your-ai-agent-w98akjbnj twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Agent Observability FAQ: Understand the value of monitoring, evaluating, and improving your AI agents | daily.dev og:description: Grafana Cloud's Agent Observability feature is now generally available for monitoring, evaluating, and improving AI agents. It tracks latency, errors, token... og:url: https://daily.dev/posts/agent-observability-faq-understand-the-value-of-monitoring-evaluating-and-improving-your-ai-agent-w98akjbnj og:image: https://api.daily.dev/og/posts/w98akJbNj.png og:image:alt: Agent Observability FAQ: Understand the value of monitoring, evaluating, and improving your AI agents 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. # Agent Observability FAQ: Understand the value of monitoring, evaluating, and improving your AI agents **[Grafana Labs](https://daily.dev/sources/grafana)** · 6 min read · 1 upvotes · 0 comments ## Summary Grafana Cloud's Agent Observability feature is now generally available for monitoring, evaluating, and improving AI agents. It tracks latency, errors, token usage, and cost, and lets teams drill into individual conversations when something breaks. Built-in or custom evaluators can detect quality issues like PII leaks or prompt injection, and offline experiments catch regressions before shipping. Coding agent integrations cover Claude Code, Codex, Cursor, GitHub Copilot, OpenCode, and Pi. It accepts OpenTelemetry generative AI spans directly. Pricing includes 30,000 generations and 25 million evaluation and guard tokens per month on free and Pro plans. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How is Grafana Agent Observability priced? It bills on three separate meters: generations (each model call the agent makes), tokens consumed by LLM-based evaluations and guards, and the standard metrics and traces sent by SDKs. Free and Pro plans include 30,000 generations and 25 million evaluation and guard tokens each month, with that token allowance shared across other Grafana Cloud AI features. _Teams budgeting for agent monitoring costs can track pricing details like these on daily.dev._ ### Can I monitor coding agents like Claude Code or Cursor with Grafana? Yes, Grafana Agent Observability includes integrations for Claude Code, Codex, Cursor, GitHub Copilot, OpenCode, and Pi, sending sessions to a dedicated Coding agents view that tracks cost, tokens, and tool usage by user, repository, or branch. An open source local app also keeps sessions on your machine without needing a Grafana account. _Developers choosing how to monitor coding agent usage can follow setups like this on daily.dev._ ### Do AI agent evaluations always require an LLM judge? No, deterministic checks like regex or JSON schema validation can be used alongside LLM judges, and both approaches can be mixed within the same evaluation. This lets teams validate structured outputs precisely while still using LLM-based judgment for more subjective quality checks. _Anyone designing agent evaluation pipelines can compare approaches like these on daily.dev._ ## Similar posts on daily.dev - [Code Agents Need Observability](https://daily.dev/posts/code-agents-need-observability-44tdmilto) · Coralogix · 0 upvotes · 0 comments - [Optimize AI costs with Agent Observability](https://daily.dev/posts/optimize-ai-costs-with-agent-observability-lnsouoalu) · Datadog · 0 upvotes · 0 comments - [Agent Observability Gap: Why AI Agents Need More Monitoring](https://daily.dev/posts/agent-observability-gap-why-ai-agents-need-more-monitoring-5q6q7hm0v) · Telerik · 0 upvotes · 0 comments - [AI Agent Observability: Logging, Tracing, and Debugging Explained](https://daily.dev/posts/ai-agent-observability-logging-tracing-and-debugging-explained-95izimukh) · Machine Learning Mastery · 1 upvotes · 0 comments - [Observe your AI agents: End‑to‑end tracing with OpenLIT and Grafana Cloud](https://daily.dev/posts/observe-your-ai-agents-end-to-end-tracing-with-openlit-and-grafana-cloud-a7fg5d3yz) · Grafana Labs · 1 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#llm](https://daily.dev/tags/llm), [#observability](https://daily.dev/tags/observability), [#opentelemetry](https://daily.dev/tags/opentelemetry), [#grafana](https://daily.dev/tags/grafana) [View this post on daily.dev](https://daily.dev/posts/agent-observability-faq-understand-the-value-of-monitoring-evaluating-and-improving-your-ai-agent-w98akjbnj) ```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":"Agent Observability FAQ: Understand the value of monitoring, evaluating, and improving your AI agents","url":"https://daily.dev/posts/agent-observability-faq-understand-the-value-of-monitoring-evaluating-and-improving-your-ai-agent-w98akjbnj","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/agent-observability-faq-understand-the-value-of-monitoring-evaluating-and-improving-your-ai-agent-w98akjbnj"},"datePublished":"2026-10-27T14:42:36.798Z","dateModified":"2026-10-27T14:50:38.517Z","description":"Grafana Cloud's Agent Observability feature is now generally available for monitoring, evaluating, and improving AI agents. It tracks latency, errors, token...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/464436e6451758a43c819171a8135907?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/464436e6451758a43c819171a8135907?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Grafana Labs","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":"Grafana Labs","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/769cb8df467e4c428abd75e0c2491d1d","url":"https://daily.dev/sources/grafana"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/agent-observability-faq-understand-the-value-of-monitoring-evaluating-and-improving-your-ai-agent-w98akjbnj","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,llm,observability,opentelemetry,grafana","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Grafana Labs","item":"https://daily.dev/sources/grafana"},{"@type":"ListItem","position":3,"name":"Agent Observability FAQ: Understand the value of monitoring, evaluating, and improving your AI agents"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/agent-observability-faq-understand-the-value-of-monitoring-evaluating-and-improving-your-ai-agent-w98akjbnj#faq","mainEntity":[{"@type":"Question","name":"How is Grafana Agent Observability priced?","acceptedAnswer":{"@type":"Answer","text":"It bills on three separate meters: generations (each model call the agent makes), tokens consumed by LLM-based evaluations and guards, and the standard metrics and traces sent by SDKs. Free and Pro plans include 30,000 generations and 25 million evaluation and guard tokens each month, with that token allowance shared across other Grafana Cloud AI features. Teams budgeting for agent monitoring costs can track pricing details like these on daily.dev."}},{"@type":"Question","name":"Can I monitor coding agents like Claude Code or Cursor with Grafana?","acceptedAnswer":{"@type":"Answer","text":"Yes, Grafana Agent Observability includes integrations for Claude Code, Codex, Cursor, GitHub Copilot, OpenCode, and Pi, sending sessions to a dedicated Coding agents view that tracks cost, tokens, and tool usage by user, repository, or branch. An open source local app also keeps sessions on your machine without needing a Grafana account. Developers choosing how to monitor coding agent usage can follow setups like this on daily.dev."}},{"@type":"Question","name":"Do AI agent evaluations always require an LLM judge?","acceptedAnswer":{"@type":"Answer","text":"No, deterministic checks like regex or JSON schema validation can be used alongside LLM judges, and both approaches can be mixed within the same evaluation. This lets teams validate structured outputs precisely while still using LLM-based judgment for more subjective quality checks. Anyone designing agent evaluation pipelines can compare approaches like these on daily.dev."}}]} ```