--- title: Dynatrace Release Radar 05.26 | daily.dev description: Dynatrace's May SaaS releases (1.338 and 1.339) introduce several notable updates. Dynatrace Assist gains a side-by-side chat mode, reference files using... canonical: https://daily.dev/posts/dynatrace-release-radar-05-26-qrzwn5bln twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Dynatrace Release Radar 05.26 | daily.dev og:description: Dynatrace's May SaaS releases (1.338 and 1.339) introduce several notable updates. Dynatrace Assist gains a side-by-side chat mode, reference files using... og:url: https://daily.dev/posts/dynatrace-release-radar-05-26-qrzwn5bln og:image: https://api.daily.dev/og/posts/QrzWN5blN.png og:image:alt: Dynatrace Release Radar 05.26 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. # Dynatrace Release Radar 05.26 **[Dynatrace](https://daily.dev/sources/dynatrace)** · 7 min read · 1 upvotes · 0 comments ## Summary Dynatrace's May SaaS releases (1.338 and 1.339) introduce several notable updates. Dynatrace Assist gains a side-by-side chat mode, reference files using Anthropic Claude Agent Skills format, Claude Sonnet 4.6 as its foundation model, and a fine-tuned Llama 3.1 8B model for natural-language-to-DQL query generation. A new unified observability layer covers five AI coding agents — Claude Code, Google Gemini CLI, OpenAI Codex CLI, OpenCode, and GitHub Copilot SDK — tracking token usage, tool behavior, and engineering outcomes via OpenTelemetry. The Dynatrace MCP Server now integrates with Atlassian Rovo, enabling observability queries directly inside Jira and JSM tickets with per-user OAuth 2.1 and admin-controlled tool exposure. Dashboard improvements include ready-made tiles, direct JSON editing, URL-driven variables, and tab state persistence. Pipeline groups now have a dedicated configuration UI in Early Access for central governance without restricting team-level flexibility. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Which AI coding agents does Dynatrace support monitoring for? Dynatrace provides unified observability for five AI coding agents: Claude Code, Google Gemini CLI, OpenAI Codex CLI, OpenCode, and GitHub Copilot SDK. The monitoring is built on OpenTelemetry and covers token/cost tracking, tool behavior visibility, in-IDE production context via the Dynatrace MCP Server, and (for Claude Code) correlation with commits and pull requests. _Teams evaluating observability across multiple coding agents can track platform coverage details on daily.dev._ ### What foundation model powers Dynatrace Assist now? Dynatrace Assist uses Anthropic Claude Sonnet 4.6 as its foundation model, the same model used in the latest Anthropic API and Claude Code, chosen for stronger multi-step reasoning on complex, multi-tool investigations. A separate fine-tuned Llama 3.1 8B model, trained specifically on Dynatrace query patterns, handles natural-language-to-DQL generation. _Practitioners weighing which foundation models power their observability assistants can follow updates like this on daily.dev._ ### How does the Dynatrace MCP Server integration with Atlassian Rovo work in Jira? The Dynatrace MCP Server integrates with Atlassian Rovo so Rovo can call Dynatrace tools in natural language directly from Jira or JSM tickets, querying metrics, traces, logs, and topology and posting results as ticket comments. Access uses per-user OAuth 2.1 with a full audit trail, administrators control which tools are exposed, and it's included with Dynatrace SaaS at no extra cost. _Engineers who want to investigate incidents without leaving Jira can follow integrations like this via daily.dev._ ## Similar posts on daily.dev - [Dynatrace Release Radar 06.26](https://daily.dev/posts/dynatrace-release-radar-06-26-k6c1cpgfx) · Dynatrace · 0 upvotes · 0 comments - [Dynatrace release radar: 2026](https://daily.dev/posts/dynatrace-release-radar-2026-uxp2arl30) · Dynatrace · 0 upvotes · 0 comments - [Dynatrace Release Radar 02.26](https://daily.dev/posts/dynatrace-release-radar-02-26-uekqit2l6) · Dynatrace · 0 upvotes · 0 comments - [Dynatrace Release Radar 03.26](https://daily.dev/posts/dynatrace-release-radar-03-26-pppvslorm) · Dynatrace · 2 upvotes · 0 comments - [Dynatrace Release Radar 04.26: What’s new and why it matters](https://daily.dev/posts/dynatrace-release-radar-04-26-what-s-new-and-why-it-matters-5j33leupc) · Dynatrace · 0 upvotes · 0 comments --- Tags: [#devops](https://daily.dev/tags/devops), [#ai-agents](https://daily.dev/tags/ai-agents), [#observability](https://daily.dev/tags/observability), [#opentelemetry](https://daily.dev/tags/opentelemetry) [View this post on daily.dev](https://daily.dev/posts/dynatrace-release-radar-05-26-qrzwn5bln) ```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":"Dynatrace Release Radar 05.26","url":"https://daily.dev/posts/dynatrace-release-radar-05-26-qrzwn5bln","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/dynatrace-release-radar-05-26-qrzwn5bln"},"datePublished":"2026-06-16T18:53:44.106Z","dateModified":"2026-09-14T06:34:43.357Z","description":"Dynatrace's May SaaS releases (1.338 and 1.339) introduce several notable updates. Dynatrace Assist gains a side-by-side chat mode, reference files using...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/41003fb922d3558b42acb56ae3cd1e1c?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/41003fb922d3558b42acb56ae3cd1e1c?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Dynatrace","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":"Dynatrace","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/3ca5a9897e9748f4a39fa9736389609e","url":"https://daily.dev/sources/dynatrace"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/dynatrace-release-radar-05-26-qrzwn5bln","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"devops,ai-agents,observability,opentelemetry","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Dynatrace","item":"https://daily.dev/sources/dynatrace"},{"@type":"ListItem","position":3,"name":"Dynatrace Release Radar 05.26"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/dynatrace-release-radar-05-26-qrzwn5bln#faq","mainEntity":[{"@type":"Question","name":"Which AI coding agents does Dynatrace support monitoring for?","acceptedAnswer":{"@type":"Answer","text":"Dynatrace provides unified observability for five AI coding agents: Claude Code, Google Gemini CLI, OpenAI Codex CLI, OpenCode, and GitHub Copilot SDK. The monitoring is built on OpenTelemetry and covers token/cost tracking, tool behavior visibility, in-IDE production context via the Dynatrace MCP Server, and (for Claude Code) correlation with commits and pull requests. Teams evaluating observability across multiple coding agents can track platform coverage details on daily.dev."}},{"@type":"Question","name":"What foundation model powers Dynatrace Assist now?","acceptedAnswer":{"@type":"Answer","text":"Dynatrace Assist uses Anthropic Claude Sonnet 4.6 as its foundation model, the same model used in the latest Anthropic API and Claude Code, chosen for stronger multi-step reasoning on complex, multi-tool investigations. A separate fine-tuned Llama 3.1 8B model, trained specifically on Dynatrace query patterns, handles natural-language-to-DQL generation. Practitioners weighing which foundation models power their observability assistants can follow updates like this on daily.dev."}},{"@type":"Question","name":"How does the Dynatrace MCP Server integration with Atlassian Rovo work in Jira?","acceptedAnswer":{"@type":"Answer","text":"The Dynatrace MCP Server integrates with Atlassian Rovo so Rovo can call Dynatrace tools in natural language directly from Jira or JSM tickets, querying metrics, traces, logs, and topology and posting results as ticket comments. Access uses per-user OAuth 2.1 with a full audit trail, administrators control which tools are exposed, and it's included with Dynatrace SaaS at no extra cost. Engineers who want to investigate incidents without leaving Jira can follow integrations like this via daily.dev."}}]} ```