--- title: Jaeger Previews AI-Assisted Troubleshooting and GenAI... description: Jaeger is previewing AI-assisted troubleshooting and GenAI trace visualization features at KubeCon + CloudNativeCon North America 2026. The experimental... canonical: https://daily.dev/posts/jaeger-previews-ai-assisted-troubleshooting-and-genai-trace-visualization-8kkgkqw38 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Jaeger Previews AI-Assisted Troubleshooting and GenAI Trace Visualization | daily.dev og:description: Jaeger is previewing AI-assisted troubleshooting and GenAI trace visualization features at KubeCon + CloudNativeCon North America 2026. The experimental... og:url: https://daily.dev/posts/jaeger-previews-ai-assisted-troubleshooting-and-genai-trace-visualization-8kkgkqw38 og:image: https://api.daily.dev/og/posts/8kKgkqw38.png og:image:alt: Jaeger Previews AI-Assisted Troubleshooting and GenAI Trace Visualization 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. # Jaeger Previews AI-Assisted Troubleshooting and GenAI Trace Visualization **[Cloud Native Now](https://daily.dev/sources/cloudnativenow)** · 2 min read · 0 upvotes · 0 comments ## Summary Jaeger is previewing AI-assisted troubleshooting and GenAI trace visualization features at KubeCon + CloudNativeCon North America 2026. The experimental capabilities ship in Jaeger v2.22. Ask Jaeger lets engineers investigate traces conversationally, with visible tool calls showing how it reaches conclusions. An opt-in MCP endpoint exposes nine tools for discovering services and traces, mapping topology and inspecting spans, plus built-in skills for root-cause analysis and N+1 query detection. The design uses progressive disclosure so agents pull only the trace evidence they need. New views based on OpenTelemetry GenAI semantic conventions show model interactions, token usage and tool execution inside traces. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What is Ask Jaeger and how does it work with MCP? Ask Jaeger is an in-product natural-language assistant, previewed in Jaeger v2.22, that lets engineers investigate distributed traces conversationally while showing the tool calls behind its conclusions. It uses an opt-in Model Context Protocol endpoint exposing nine tools for discovering services and traces, mapping topology, and inspecting spans, plus built-in skills for root-cause analysis and N+1 query detection. _Teams adopting MCP-based tracing assistants can follow Jaeger's rollout and other agent-tooling releases on daily.dev._ ### How does Jaeger avoid sending entire traces to a language model? Jaeger's AI features use a design principle called progressive disclosure, where AI agents retrieve only the trace evidence needed for each investigative step rather than the full trace. The architecture combines MCP, Agent Client Protocol, AG-UI, and OpenTelemetry, and it works with any ACP-compatible agent instead of being tied to one model or proprietary framework. _Anyone weighing how AI agents should access observability data can track architecture patterns like this on daily.dev._ ### What are OpenTelemetry GenAI semantic conventions used for in trace visualization? They back new specialized trace views in Jaeger that let teams examine model interactions, agent activity, retrieval operations, token usage, system instructions, and tool execution within distributed traces. These views were introduced as part of Jaeger's experimental GenAI-aware trace visualization, enabled after downloading Jaeger and following its AI sidecar integration guide. _Developers instrumenting AI agents with OpenTelemetry can follow conventions like these as they evolve on daily.dev._ ## Similar posts on daily.dev - [How Jaeger is evolving to trace AI agents with OpenTelemetry](https://daily.dev/posts/how-jaeger-is-evolving-to-trace-ai-agents-with-opentelemetry-wbwtfypo7) · CNCF · 4 upvotes · 0 comments - [Jaeger adopts OpenTelemetry at its core to solve the AI agent observability gap](https://daily.dev/posts/jaeger-adopts-opentelemetry-at-its-core-to-solve-the-ai-agent-observability-gap-7ufkqbnb5) · The New Stack · 1 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 - [Dynatrace AI agents begin working for you on day one, and are built to grow with you](https://daily.dev/posts/dynatrace-ai-agents-begin-working-for-you-on-day-one-and-are-built-to-grow-with-you-bwyoowzjv) · Dynatrace · 0 upvotes · 0 comments --- Tags: [#devops](https://daily.dev/tags/devops), [#observability](https://daily.dev/tags/observability), [#mcp](https://daily.dev/tags/mcp), [#opentelemetry](https://daily.dev/tags/opentelemetry) [View this post on daily.dev](https://daily.dev/posts/jaeger-previews-ai-assisted-troubleshooting-and-genai-trace-visualization-8kkgkqw38) ```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":"Jaeger Previews AI-Assisted Troubleshooting and GenAI Trace Visualization","url":"https://daily.dev/posts/jaeger-previews-ai-assisted-troubleshooting-and-genai-trace-visualization-8kkgkqw38","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/jaeger-previews-ai-assisted-troubleshooting-and-genai-trace-visualization-8kkgkqw38"},"datePublished":"2026-11-10T18:32:42.833Z","dateModified":"2026-11-10T18:37:47.345Z","description":"Jaeger is previewing AI-assisted troubleshooting and GenAI trace visualization features at KubeCon + CloudNativeCon North America 2026. The experimental...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1000660928053eb9de0dd0335ee10211?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/1000660928053eb9de0dd0335ee10211?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Cloud Native Now","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":"Cloud Native Now","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/8acc1ecd93ce4299b615252f32d78de5","url":"https://daily.dev/sources/cloudnativenow"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/jaeger-previews-ai-assisted-troubleshooting-and-genai-trace-visualization-8kkgkqw38","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"devops,observability,mcp,opentelemetry","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Cloud Native Now","item":"https://daily.dev/sources/cloudnativenow"},{"@type":"ListItem","position":3,"name":"Jaeger Previews AI-Assisted Troubleshooting and GenAI Trace Visualization"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/jaeger-previews-ai-assisted-troubleshooting-and-genai-trace-visualization-8kkgkqw38#faq","mainEntity":[{"@type":"Question","name":"What is Ask Jaeger and how does it work with MCP?","acceptedAnswer":{"@type":"Answer","text":"Ask Jaeger is an in-product natural-language assistant, previewed in Jaeger v2.22, that lets engineers investigate distributed traces conversationally while showing the tool calls behind its conclusions. It uses an opt-in Model Context Protocol endpoint exposing nine tools for discovering services and traces, mapping topology, and inspecting spans, plus built-in skills for root-cause analysis and N+1 query detection. Teams adopting MCP-based tracing assistants can follow Jaeger's rollout and other agent-tooling releases on daily.dev."}},{"@type":"Question","name":"How does Jaeger avoid sending entire traces to a language model?","acceptedAnswer":{"@type":"Answer","text":"Jaeger's AI features use a design principle called progressive disclosure, where AI agents retrieve only the trace evidence needed for each investigative step rather than the full trace. The architecture combines MCP, Agent Client Protocol, AG-UI, and OpenTelemetry, and it works with any ACP-compatible agent instead of being tied to one model or proprietary framework. Anyone weighing how AI agents should access observability data can track architecture patterns like this on daily.dev."}},{"@type":"Question","name":"What are OpenTelemetry GenAI semantic conventions used for in trace visualization?","acceptedAnswer":{"@type":"Answer","text":"They back new specialized trace views in Jaeger that let teams examine model interactions, agent activity, retrieval operations, token usage, system instructions, and tool execution within distributed traces. These views were introduced as part of Jaeger's experimental GenAI-aware trace visualization, enabled after downloading Jaeger and following its AI sidecar integration guide. Developers instrumenting AI agents with OpenTelemetry can follow conventions like these as they evolve on daily.dev."}}]} ```