--- title: Expedia Uses AI Driven Service Telemetry Analyzer to... description: Expedia Group built STAR (Service Telemetry Analyzer), an internal AI-assisted observability platform that accelerates production incident investigation.... canonical: https://daily.dev/posts/expedia-uses-ai-driven-service-telemetry-analyzer-to-accelerate-incident-investigation-0uoc0v5nr twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Expedia Uses AI Driven Service Telemetry Analyzer to Accelerate Incident Investigation | daily.dev og:description: Expedia Group built STAR (Service Telemetry Analyzer), an internal AI-assisted observability platform that accelerates production incident investigation.... og:url: https://daily.dev/posts/expedia-uses-ai-driven-service-telemetry-analyzer-to-accelerate-incident-investigation-0uoc0v5nr og:image: https://api.daily.dev/og/posts/0UoC0V5NR.png og:image:alt: Expedia Uses AI Driven Service Telemetry Analyzer to Accelerate Incident Investigation 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. # Expedia Uses AI Driven Service Telemetry Analyzer to Accelerate Incident Investigation **[InfoQ](https://daily.dev/sources/infoq)** · 3 min read · 1 upvotes · 0 comments ## Summary Expedia Group built STAR (Service Telemetry Analyzer), an internal AI-assisted observability platform that accelerates production incident investigation. Rather than using autonomous AI agents, STAR follows deterministic prompt-chaining workflows to collect Kubernetes and JVM telemetry from Datadog, run specialized LLM analyses, and produce structured root cause assessments with recommended next steps. The stack includes FastAPI, Celery with Redis for async task processing, and Langfuse for prompt management and tracing. Engineers remain in the loop to validate findings before acting. Planned expansions include service dependency graphs, MCP-based tool integrations, conversational interfaces, and integration with chaos engineering practices. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Why did Expedia replace FastAPI background tasks with Celery and Redis in their STAR observability platform? Expedia moved from FastAPI background tasks to a Celery-based asynchronous architecture using Redis as both the message broker and result backend because most of STAR's processing is I/O-bound, involving telemetry retrieval and LLM requests. This asynchronous model lets STAR process multiple analysis tasks concurrently while respecting rate limits imposed by Datadog and Expedia's internal AI gateway. _Track how teams evolve AI-assisted backend architectures like this one on daily.dev._ ### What telemetry metrics does Expedia's STAR platform analyze to diagnose production incidents? STAR analyzes standardized infrastructure telemetry from Kubernetes-based services and JVM applications, including request throughput, latency, HTTP, gRPC, and GraphQL error rates, CPU and memory utilization, container restart events, Kubernetes readiness and liveness probe failures, Java heap utilization, and garbage collection activity. Infrastructure metrics give a consistent view across services built with different languages and frameworks. _Engineers designing observability pipelines can follow incident-response tooling trends on daily.dev._ ### Does Expedia's STAR observability tool use autonomous AI agents to investigate incidents? No, STAR deliberately avoids autonomous AI agents, function calling, retrieval-augmented generation, memory, or autonomous tool use. It instead follows a deterministic workflow with predefined prompts that collect telemetry, run domain-specific analyses, consolidate intermediate findings, and produce a final report, with engineers reviewing and validating results before acting. _Teams weighing deterministic workflows versus autonomous agents can follow this design debate on daily.dev._ ## Similar posts on daily.dev - [How Databricks Uses AI to Accelerate Incident Investigation](https://daily.dev/posts/how-databricks-uses-ai-to-accelerate-incident-investigation-tyehhd3qg) · databricks · 5 upvotes · 2 comments - [Accelerate investigations with AI in Datadog Incident Response](https://daily.dev/posts/accelerate-investigations-with-ai-in-datadog-incident-response-ir84e5dlb) · Datadog · 0 upvotes · 0 comments - [How Grab is Using AI Agents to Boost Team Productivity](https://daily.dev/posts/how-grab-is-using-ai-agents-to-boost-team-productivity-fkppsh0tc) · ByteByteGo · 2 upvotes · 0 comments - [AI is coming to solve your system outages](https://daily.dev/posts/ai-is-coming-to-solve-your-system-outages-ciiwyuvu9) · The Register · 0 upvotes · 0 comments --- Tags: [#devops](https://daily.dev/tags/devops), [#llm](https://daily.dev/tags/llm), [#observability](https://daily.dev/tags/observability), [#celery](https://daily.dev/tags/celery) [View this post on daily.dev](https://daily.dev/posts/expedia-uses-ai-driven-service-telemetry-analyzer-to-accelerate-incident-investigation-0uoc0v5nr) ```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":"Expedia Uses AI Driven Service Telemetry Analyzer to Accelerate Incident Investigation","url":"https://daily.dev/posts/expedia-uses-ai-driven-service-telemetry-analyzer-to-accelerate-incident-investigation-0uoc0v5nr","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/expedia-uses-ai-driven-service-telemetry-analyzer-to-accelerate-incident-investigation-0uoc0v5nr"},"datePublished":"2026-07-23T14:24:38.769Z","dateModified":"2026-09-14T08:46:31.051Z","description":"Expedia Group built STAR (Service Telemetry Analyzer), an internal AI-assisted observability platform that accelerates production incident investigation....","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/bcac7363b06f4d510001cd59ba1dc40b?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/bcac7363b06f4d510001cd59ba1dc40b?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"InfoQ","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":"InfoQ","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/afc3bced3e1e4b188dd9127017a60e0c","url":"https://daily.dev/sources/infoq"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/expedia-uses-ai-driven-service-telemetry-analyzer-to-accelerate-incident-investigation-0uoc0v5nr","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"devops,llm,observability,celery","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"InfoQ","item":"https://daily.dev/sources/infoq"},{"@type":"ListItem","position":3,"name":"Expedia Uses AI Driven Service Telemetry Analyzer to Accelerate Incident Investigation"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/expedia-uses-ai-driven-service-telemetry-analyzer-to-accelerate-incident-investigation-0uoc0v5nr#faq","mainEntity":[{"@type":"Question","name":"Why did Expedia replace FastAPI background tasks with Celery and Redis in their STAR observability platform?","acceptedAnswer":{"@type":"Answer","text":"Expedia moved from FastAPI background tasks to a Celery-based asynchronous architecture using Redis as both the message broker and result backend because most of STAR's processing is I/O-bound, involving telemetry retrieval and LLM requests. This asynchronous model lets STAR process multiple analysis tasks concurrently while respecting rate limits imposed by Datadog and Expedia's internal AI gateway. Track how teams evolve AI-assisted backend architectures like this one on daily.dev."}},{"@type":"Question","name":"What telemetry metrics does Expedia's STAR platform analyze to diagnose production incidents?","acceptedAnswer":{"@type":"Answer","text":"STAR analyzes standardized infrastructure telemetry from Kubernetes-based services and JVM applications, including request throughput, latency, HTTP, gRPC, and GraphQL error rates, CPU and memory utilization, container restart events, Kubernetes readiness and liveness probe failures, Java heap utilization, and garbage collection activity. Infrastructure metrics give a consistent view across services built with different languages and frameworks. Engineers designing observability pipelines can follow incident-response tooling trends on daily.dev."}},{"@type":"Question","name":"Does Expedia's STAR observability tool use autonomous AI agents to investigate incidents?","acceptedAnswer":{"@type":"Answer","text":"No, STAR deliberately avoids autonomous AI agents, function calling, retrieval-augmented generation, memory, or autonomous tool use. It instead follows a deterministic workflow with predefined prompts that collect telemetry, run domain-specific analyses, consolidate intermediate findings, and produce a final report, with engineers reviewing and validating results before acting. Teams weighing deterministic workflows versus autonomous agents can follow this design debate on daily.dev."}}]} ```