--- title: Monitor your Genkit features in production | daily.dev description: Firebase Genkit Monitoring provides production-grade observability for Genkit-powered AI features, surfacing metrics like usage, success rates, p95 latency,... canonical: https://daily.dev/posts/monitor-your-genkit-features-in-production-4atsdkidu twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Monitor your Genkit features in production | daily.dev og:description: Firebase Genkit Monitoring provides production-grade observability for Genkit-powered AI features, surfacing metrics like usage, success rates, p95 latency,... og:url: https://daily.dev/posts/monitor-your-genkit-features-in-production-4atsdkidu og:image: https://api.daily.dev/og/posts/4ATsDKiDU.png og:image:alt: Monitor your Genkit features in production 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. # Monitor your Genkit features in production **[Firebase](https://daily.dev/sources/firebase-blog)** · 5 min read · 0 upvotes · 0 comments ## Summary Firebase Genkit Monitoring provides production-grade observability for Genkit-powered AI features, surfacing metrics like usage, success rates, p95 latency, and token counts in the Firebase console. Enabling it requires installing the @genkit-ai/firebase plugin and calling enableFirebaseTelemetry() in the Genkit config. Feature-specific dashboards, failed-path tables, and trace viewers help pinpoint where and why complex multi-step AI flows fail, with all trace, log, and metrics data also stored in GCP for deeper analysis. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I enable telemetry monitoring for a Genkit AI feature in production? Install the @genkit-ai/firebase plugin with npm install @genkit-ai/firebase, then import enableFirebaseTelemetry from that package into the Genkit configuration file where genkit(...) is initialized and call it. After redeploying, telemetry data is automatically written to GCP Logging, Trace, and Monitoring, and becomes viewable in the Genkit Monitoring dashboard in the Firebase console. _daily.dev surfaces practical setup guides like this for teams instrumenting AI features for production observability._ ### What does token count tell you about the health of an LLM feature in Genkit Monitoring? Token count acts as a proxy for both cost and correctness of a Genkit feature. A lower than expected token count often signals the model is returning a generic fallback like 'I don't know how to answer this,' while a higher than expected count suggests the LLM inference needs a better stop sequence. The dashboard also supports models that count images as tokens versus as a discrete image metric. _Debugging LLM cost and quality issues gets easier when developers share findings like this via daily.dev._ ## Similar posts on daily.dev - [Firebase \+ Genkit: How I Actually Brought AI Into My Mobile App \(Without Losing My Mind\)](https://daily.dev/posts/firebase-genkit-how-i-actually-brought-ai-into-my-mobile-app-without-losing-my-mind--ta6av8kvz) · Medium · 0 upvotes · 0 comments - [Building multi-turn AI agents with Genkit’s Agents API](https://daily.dev/posts/building-multi-turn-ai-agents-with-genkit-s-agents-api-dfgv5puxw) · LogRocket · 0 upvotes · 0 comments - [Beyond the Spinner: Building Responsive AI Apps with Genkit Streaming](https://daily.dev/posts/beyond-the-spinner-building-responsive-ai-apps-with-genkit-streaming-cg1ie9ot0) · Firebase Developers · 1 upvotes · 0 comments - [Announcing the Genkit Extension for Gemini CLI](https://daily.dev/posts/announcing-the-genkit-extension-for-gemini-cli-k5d1aqwpu) · Google Developers · 83 upvotes · 1 comments - [Practical tools to simplify GenAI observability and monitoring](https://daily.dev/posts/practical-tools-to-simplify-genai-observability-and-monitoring-zj0kv053c) · All Things Open · 0 upvotes · 0 comments --- Tags: [#llm](https://daily.dev/tags/llm), [#gcp](https://daily.dev/tags/gcp), [#observability](https://daily.dev/tags/observability), [#firebase](https://daily.dev/tags/firebase) [View this post on daily.dev](https://daily.dev/posts/monitor-your-genkit-features-in-production-4atsdkidu) ```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":"Monitor your Genkit features in production","url":"https://daily.dev/posts/monitor-your-genkit-features-in-production-4atsdkidu","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/monitor-your-genkit-features-in-production-4atsdkidu"},"datePublished":"2026-08-23T12:20:13.813Z","dateModified":"2026-08-23T12:41:04.336Z","description":"Firebase Genkit Monitoring provides production-grade observability for Genkit-powered AI features, surfacing metrics like usage, success rates, p95 latency,...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/5371d05a0789a23a97389f0476ad306f?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/5371d05a0789a23a97389f0476ad306f?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Firebase","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":"Firebase","logo":"https://media.daily.dev/image/upload/s--i395oqZH--/f_auto,q_auto/v1787487448/logos/firebase-blog?_a=BAMAMicg0","url":"https://daily.dev/sources/firebase-blog"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/monitor-your-genkit-features-in-production-4atsdkidu","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"llm,gcp,observability,firebase","timeRequired":"PT5M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Firebase","item":"https://daily.dev/sources/firebase-blog"},{"@type":"ListItem","position":3,"name":"Monitor your Genkit features in production"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/monitor-your-genkit-features-in-production-4atsdkidu#faq","mainEntity":[{"@type":"Question","name":"How do I enable telemetry monitoring for a Genkit AI feature in production?","acceptedAnswer":{"@type":"Answer","text":"Install the @genkit-ai/firebase plugin with npm install @genkit-ai/firebase, then import enableFirebaseTelemetry from that package into the Genkit configuration file where genkit(...) is initialized and call it. After redeploying, telemetry data is automatically written to GCP Logging, Trace, and Monitoring, and becomes viewable in the Genkit Monitoring dashboard in the Firebase console. daily.dev surfaces practical setup guides like this for teams instrumenting AI features for production observability."}},{"@type":"Question","name":"What does token count tell you about the health of an LLM feature in Genkit Monitoring?","acceptedAnswer":{"@type":"Answer","text":"Token count acts as a proxy for both cost and correctness of a Genkit feature. A lower than expected token count often signals the model is returning a generic fallback like 'I don't know how to answer this,' while a higher than expected count suggests the LLM inference needs a better stop sequence. The dashboard also supports models that count images as tokens versus as a discrete image metric. Debugging LLM cost and quality issues gets easier when developers share findings like this via daily.dev."}}]} ```