This is the second post in our series on LLM evaluations. In the companion post, Evaluate LLM and agent quality in Dynatrace AI Observability with dt-evals, we showed you how to run online evaluations against real GenAI prompt traces and bring quality scores into Dynatrace AI Observability alongside latency, cost, and errors. This post steps back to the fundamentals: what evaluations are, how they work, and the methods teams use to measure AI quality.

Just as traditional software relies on testing frameworks to ensure reliability, AI systems require robust evaluation frameworks to measure the quality, accuracy, and safety of model outputs. Evals are the primary mechanism by which teams build trust in, iterate on, and responsibly deploy AI systems. Without them, organizations may risk deploying systems that produce unreliable answers, hallucinate facts, or quietly degrade in performance over time.

Key takeaways

• Evaluations are how teams move from “the LLM feels right” to “we can prove the LLM works.”
• There is no single best evaluation method. The right approach depends on what you’re measuring and why.
• LLM-as-a-Judge is one powerful tool within the broader evaluation ecosystem, not synonymous with evals as a whole.
• Online and offline evaluations serve complementary roles: offline for development, online for production monitoring.
• A mature evaluation strategy combines code-based, model-based, and human-based methods.
• Evals should be treated as living artifacts — maintained, versioned, and improved over time like any other engineering asset.

Why LLM evaluation is fundamentally different from traditional testing

Traditional software produces deterministic outputs — the same input consistently returns the same result, making pass/fail testing straightforward. LLMs are probabilistic systems: the same prompt can produce different responses depending on context, temperature, and model behavior. This variability makes conventional testing methods insufficient.

Instead of verifying a single correct output, teams must evaluate across multiple dimensions simultaneously:

• Correctness— does the response answer the question accurately?
• Relevance — is the output aligned with the user’s intent?
• Faithfulness — is the response grounded in source data, not invented?
• Safety and bias — does the output comply with organizational policies?

This transforms evaluation from simple pass/fail checks into continuous measurement of AI quality.

The hallucination problem

The most well-known consequence of probabilistic generation is hallucination — when a model produces plausible-sounding but factually incorrect information. This happens because LLMs predict likely word sequences rather than verify facts, which enables powerful reasoning but introduces serious risk in enterprise environments where accuracy is critical.

Addressing this requires evaluation frameworks that track signals like factual accuracy, semantic similarity, groundedness in source data, and consistency across responses. These metrics transform subjective quality judgments into measurable, improvable signals.

What is an LLM evaluation?

An LLM evaluation is a systematic process of testing a model or AI-powered system to determine whether it meets a defined standard of quality. That standard could be factual accuracy, helpfulness, safety, tone, latency, cost-efficiency, or any other measurable dimension that matters to the application.

Evaluations translate vague product goals (“the assistant should be helpful and safe”) into concrete, repeatable measurements. They allow teams to:

• Catch regressions when a model is updated, or a prompt is changed.
• Compare candidates — different models, prompt versions, or retrieval strategies — objectively.
• Build accountability by producing evidence that a system behaves as intended.
• Accelerate iteration by giving developers fast, structured feedback loops.

Evals exist on a spectrum of formality, from a small hand-curated test set run locally, to a large, automated pipeline running thousands of test cases in CI/CD on every deployment.

How do LLM evaluations operate?

At their core, evaluations follow a consistent pattern regardless of their complexity:

1. Define the task and success criteria. What should the LLM model do, and how will you know when it does it correctly? This is the hardest and most important step.
2. Assemble a dataset. A set of inputs (prompts, user messages, documents) paired with expected outputs or grading rubrics. Datasets can be human-curated, synthetically generated, or sampled from production traffic.
3. Run inference. Pass the inputs through the system under test and collect outputs.
4. Score the outputs. Apply a scoring method — a function, a model, or a human — to assess how well each output meets the success criteria.
5. Aggregate and analyze. Roll up scores into metrics (accuracy, pass rate, average score), visualize distributions, and compare against baselines or previous runs.
6. Act on results. Use the findings to accept or reject a change, file a bug, update a prompt, or trigger retraining.

This loop can run manually during development, automatically in CI/CD pipelines, or continuously against live production traffic.

What’s the difference between LLM evaluations and LLM-as-a-Judge?

This is one of the most common points of confusion in the space.

LLM evaluations are the broader discipline — the full process described above. They encompass everything from how you define success to how you collect test data to how you score outputs to how you act on results.

LLM-as-a-Judge is one specific scoring method that can be used within an evaluation pipeline. It involves using a language model (often a strong general-purpose model like GPT-5 or Claude Sonnet 4.6) to automatically assess the quality of another model’s outputs.

Think of it this way: evaluations are the framework, and LLM-as-a-Judge is one type of grader you can plug into that framework — alongside code-based graders, human graders, or embedding-based similarity checks.

• LLM-as-a-judge handles open-ended, subjective dimensions (tone, creativity, helpfulness) that are hard to capture in code.
• It scales to large datasets without human effort.
• It can be surprisingly well-calibrated when prompts and rubrics are carefully designed.

Limitations

• Inherent biases of the LLM model used to judge (verbosity bias, position bias, self-preference).
• Requires prompt engineering and validation to ensure the judge is grading what you intend.
• Adds cost and latency to the evaluation pipeline.
• Not appropriate for tasks with clear ground-truth answers where code-based checks suffice.

Code-based evaluations

Code-based evaluations use deterministic functions — written in Python or any language — to score model outputs. No secondary LLM model is involved.

How it works

You write a function that takes the model output as input and returns a score. The function might check for exact string matches, run regex patterns, execute generated code and test it, parse JSON and validate its structure, call an external API to verify a fact, or compare numerical results.

Common patterns

• Exact match — does the output equal the expected answer?
• Contains / regex match — does the output include a required phrase or follow a required format?
• Execution-based — for code generation tasks, run the output and check whether tests pass.
• Structured output validation — parse JSON/XML outputs and verify schema and values.
• Tool call verification — for agentic tasks, did the model call the right tool with the right parameters?

Strengths

• Fully deterministic and reproducible.
• Fast and cheap to run at scale.
• Easy to understand, debug, and audit.
• No dependence on a secondary model’s judgment.

Limitations

• Cannot handle open-ended or subjective quality dimensions.
• Requires knowing the exact expected output or a verifiable property of the output.
• Brittle for tasks where there are many valid correct outputs (for example, summarization, creative writing).

Code-based LLM evals are the first tool to reach for whenever a task has a clear, verifiable answer. They form the backbone of any reliable eval suite.

Online vs. offline evaluations

These two modes are not competing approaches — they’re complementary phases of a complete evaluation strategy.

Offline evaluations

Offline evals run against a static, pre-collected dataset before a system reaches production. They’re the evaluation equivalent of unit and integration tests in software development.

• When: During development, before deploying a new model, prompt, or retrieval change.
• Dataset: Curated, labeled, or synthetically generated. Often maintained in version control.
• Latency: Can run in batch; speed is less critical.
• Use cases: Regression testing, model comparison, prompt optimization, safety red-teaming, fine-tune evaluation.

Key advantage: Full control over the test distribution and ground-truth labels.

Key limitation: The dataset may not reflect real user behavior or the long tail of production inputs.

Online Evaluations

Online evals run against live production traffic in real time or near real time. They observe what is actually happening when real users interact with the system.

• When: Continuously, in production.
• Dataset: Real user inputs — unlabeled, unpredictable, and representative.
• Latency: Must be fast or asynchronous to avoid slowing down user-facing requests.
• Use cases: Production monitoring, anomaly detection, drift detection, A/B testing, continuous quality assurance.

Key advantage: Captures real-world usage patterns, prompts, and failure modes from production traffic, giving teams the most representative signal for monitoring AI quality over time.

Key limitation: No pre-defined labels; scoring must rely on heuristics, implicit signals (thumbs up/down, re-prompts), or async LLM-as-a-Judge pipelines.

Get started with LLM evaluations today

The field of LLM evals is evolving rapidly. As enterprises deploy increasingly autonomous AI systems, evaluation can play an important role in improving AI accuracy, reliability, and safety.

Here are the trends worth watching and investing in:

1. Evaluation-driven development. Treat evals as a first-class engineering artifact. Write eval cases before building features, maintain them in version control, and integrate them into CI/CD pipelines — mirroring test-driven development practices from software engineering.
2. Agentic and multi-step evaluation. As AI systems move from single-turn Q&A to multi-step agents that use tools and maintain state, evaluations must evolve to assess full trajectories rather than just individual outputs. This includes evaluating tool use, planning quality, error recovery, and task completion over long horizons.
3. Adversarial and safety evals. Red-teaming — probing a system for failures, biases, and unsafe behaviors — is becoming a standard part of the eval lifecycle, especially as regulatory requirements around AI safety mature.
4. Human-in-the-loop calibration. Even automated eval pipelines benefit from periodic human review to catch drift in what the judge model or scoring function is measuring. Building lightweight human-annotation workflows alongside automated evaluations yields a more reliable signal over time.
5. Standardization and benchmarking. The industry is moving toward shared benchmarks and eval frameworks (for example, HELM, MMLU, LMSYS Chatbot Arena, OpenAI Evals) that allow apples-to-apples comparisons across models. Building internal evals that complement these public benchmarks will be an increasingly important capability for any team deploying LLMs.
6. Cost-aware evaluation. As evals scale, cost becomes a real constraint. Emerging approaches include training lightweight specialized judge models, using embedding-based similarity as a cheap first filter, and intelligently sampling which examples need expensive LLM-as-a-Judge scoring.

Organizations that invest early in robust evaluation frameworks and combine them with AI observability will be positioned to scale AI safely across their operations.

Ready to put this into practice?

See our companion blog post, Evaluate LLM and agent quality in Dynatrace AI Observability with dt-evals, to learn how dt-evals lets you run LLM-as-a-judge evaluations on real GenAI traces and turn AI quality into a queryable, trendable, and alertable signal inside Dynatrace AI Observability.

Because in the end, AI systems are only as trustworthy as the processes used to evaluate them.

The post Beyond LLM-as-a-judge: Establishing LLM evaluations as a foundation for trustworthy agentic AI systems appeared first on Dynatrace news.

Organizations are evolving from human-driven operations to supervised autonomous operations, where AI investigates, recommends, and remediates, and humans stay in control of what matters most. A big part of delivering on that vision is working with the agents that customers already run in their cloud environments.

Harness the power of hyperscale agents

Each hyperscaler has AI agents that automatically investigate and help resolve production incidents using native cloud telemetry and tools. They act like embedded site reliability engineers, analyzing issues and recommending or executing remediation steps without waiting for a human to start the process.

AWS DevOps Agent provides investigation and remediation in AWS using native tooling. An Azure SRE Agent specializes in investigating and remediating Azure issues. And Google Gemini Cloud Assist is for incident analysis across Google Cloud Platform (GCP).

Over the past year, we’ve published how Dynatrace supercharges each of these cloud agents individually. When an issue occurs, Dynatrace Intelligence combines causal, predictive, and agentic AI using the Smartscape dependency graph to automatically link related symptoms and root causes across the environment into one unified problem card.

When Dynatrace integrates with the AWS DevOps Agent, dependency-aware root cause analysis combines with AWS frontier-agent capabilities, and joint customers report up to 70% reductions in mean time to resolution. When Azure SRE Agent connects with Dynatrace, deterministic, causation-based AI flows directly into Azure-native remediation workflows, cutting the back-and-forth between teams. And with Google Gemini Cloud Assist, Dynatrace delivers the same production context layer to GCP-hosted incidents: precise root cause, full topology, real business impact.

From integrations to intelligent orchestration

Many enterprises run workloads across AWS, Azure, and Google Cloud simultaneously, and managing three separate integrations with separate routing logic and separate cost controls is its own operational tax. Cloud SRE Agents provides a single orchestration layer that routes problems to specific hyperscaler agents based on configurable profiles to see everything happening across all three cloud agents.

The Cloud SRE Agents app writes findings back to Dynatrace, and provides your team with measurable visibility into autonomous actions.

How Cloud SRE Agents works

When Dynatrace Intelligence detects a problem and identifies the root cause, Cloud SRE Agents calls dedicated cloud-native agents from AWS, Azure, and Google Cloud to retrieve deeper insights from the sources that only they can reach: CloudTrail history, Azure subscription policy, GCP project IAM, recent deployments, and native runbooks. These agents run in parallel, gathering evidence as soon as the problem is detected. Their findings, and, where applicable, the recommended remediation path, are displayed in the same Dynatrace problem view that the on-call SRE is already using in their day-to-day workflow.

One view. No tab-switching. The work starts without you.

Three workflows do the orchestration in the background:

• Investigate evaluates your Interaction Profiles and dispatches matching problems to the right agents in parallel.
• Periodic Tasks polls each cloud provider for completion, detects stalled or timed-out investigations, and writes findings back as problem annotations.
• Event Handlers normalize the cloud-provider event stream so every action correlates back to its originating problem, end to end.

Cloud SRE Agents has the insights and intelligence to decide which agent gets which problem, tracks each run to completion, and brings the answers back together in a single view. The Overview tab provides a real-time, interactive network graph of problems, agents, and activities. The replay view allows the user to step back in time and get an overview of what has happened when, as well as the status of each investigation.

Intelligent routing with Interaction Profiles

In agentic operations, routing rules make the difference between turning autonomous systems loose on every alert and pointing them precisely where they earn their keep. Interaction Profiles are how you express routing judgment in Cloud SRE Agents. Each profile pairs a set of conditions with the agent or agents that should handle the problems flagged by the profile, and evaluates the conditions whenever Dynatrace Intelligence detects a problem.

The conditions you can write are deliberately broad. You can route by the cloud account, subscription, or project an incident touches; by problem category (availability, error, slowdown, resource contention); by affected entity type (a Kubernetes cluster, a database, a Lambda function); by tag, label, or any custom attribute carried in the problem record. Conditions combine with AND/OR logic and nest as deeply as you need, keeping real production routing policy inside the app rather than spilling into custom workflows or scripts.

Three ways teams put it to work

Route problems to the right cloud, automatically

A spike in Lambda error rates belongs to AWS DevOps Agent. An Azure App Service degradation calls for Azure SRE Agent. A Pub/Sub latency issue lands with Gemini Cloud Assist. In a multicloud estate, none of those decisions should fall to a human at 2:00 AM. A profile filtered by AWS Account ID, Azure Subscription ID, or GCP Project ID, then narrowed by resource type or tag, settles the routing question once. Every matching problem is automatically routed to the right specialist with the right cloud-native context.

Optimize spend with budget-aware routing

Cloud AI agents do work, and that work has a cost. Cloud SRE Agents lets you set a Monthly Duration Budget per agent and gate dispatch on it via a Has Available Budget filter: once the budget is exhausted, new investigations either stop (in strict enforcement mode) or proceed with a logged warning. The duration figure itself is a proxy, derived from Dynatrace event timestamps rather than the cloud provider’s clock, which makes it useful as a circuit breaker and directional signal, not a substitute for AWS, Azure, or GCP usage reports. The governance value is what matters: you decide how much autonomous investigation you’re willing to underwrite each month, and the system holds the line.

Tier autonomous investigation by problem type and entity

Not every Dynatrace problem warrants an autonomous investigation. Problem Category filters let you dispatch agents only to the problem categories that warrant it, for example, availability or error problems that require immediate action, rather than slowdowns or custom alerts where human triage might still be the right call. Layer on Entity Type filters, and you can further focus on specific infrastructure tiers (hosts, services, process groups, Kubernetes clusters). The result is a tiered model: high-severity issues receive immediate autonomous investigation, lower-severity signals queue for human review, and your team controls the threshold.

Governance that makes autonomous work measurable

Agentic operations earn trust when teams can see what the agents did, why, and whether it worked. Cloud SRE Agents treats that as a first-class concern, with two views built for the two audiences who care about it.

The Activity tab is the audit trail. Every investigation and mitigation appears as a card on a unified timeline; expand any card to see the agent’s full findings, the evidence it pulled, and the action it took or recommended. Each response can be rated Good, OK, or Bad, building a quality signal grounded in what your team actually saw rather than what the system predicted. When a single problem triggers work across multiple agents, those activities roll up to a single status (in progress, done, or stalled), so you always know where things stand without having to reconstruct the run from individual records.

The Statistics tab is where autonomous operations become a number you can show to a leadership team: problems handled, mitigations executed, average investigation time, MTTR and MTTI trends, success rates, and satisfaction scores broken down by agent. The same view doubles as a directional cost lens, since agent working time is the dominant driver on the cloud side of the bill. Treat the number as a trend signal and a circuit-breaker input, not a billing record (reconcile against AWS, Azure, and GCP usage reports for exact spend), and it makes the case for expanding agentic coverage with evidence rather than anecdote.

Why production context multiplies the value

What changes Cloud SRE Agents from a smart dispatcher into something more is what Dynatrace Intelligence contributes before an agent ever begins its analysis. Dynatrace delivers deterministic, causation-based root cause analysis grounded in Dynatrace’s Smartscape real-time dependency mapping, alongside business impact assessment and correlated telemetry. That context shapes the entire direction of the investigation. A cloud agent arriving with that foundation starts from “this specific service on this specific host is the root cause, and here’s the customer impact” rather than “something is wrong somewhere in this account.”

The numbers reflect it. According to AWS, organizations using the AWS DevOps Agent with Dynatrace see up to a 75% reduction in mean time to resolution.

Western Governors University, which runs a fully online learning environment for 200,000 students, uses AWS DevOps Agent with Dynatrace to automate cross-system correlation that previously required manual effort across multiple tools. At a larger scale, United Airlines transports more than 500,000 passengers daily across a hybrid environment that includes more than 500 AWS accounts, 20,000 Lambda functions, and 38,000 OneAgent deployments.

The team’s description of the before and after status is direct: previously, multiple tools with overlapping functions created gaps and black boxes during troubleshooting. With AWS DevOps Agent and Dynatrace, Dynatrace identifies the responsible layer, the agent investigates and provides resolution steps, and everything surfaces in a single Dynatrace view. No 3:00 AM tool-switching required.

Get started

For a closer look at the individual integrations, read the posts on AWS DevOps Agent and Dynatrace and Azure SRE Agent and Dynatrace, or see how Dynatrace Intelligence powers autonomous operations. To put your cloud agents to work today, install Cloud SRE Agents from the Dynatrace Hub. Cloud SRE Agents is currently available as a community-supported app.

The post Orchestrate multicloud AI agents for autonomous incident resolution appeared first on Dynatrace news.

What is the Kiro power for Dynatrace?

The Kiro power for Dynatrace delivers live observability data, root cause analysis, and remediation suggestions directly into the Kiro IDE, with no JSON editing or manual MCP setup.

Kiro is an AI-powered IDE that helps developers move from idea to working code through spec-driven development and an agentic assistant. To make the assistant genuinely useful in unfamiliar domains, Kiro recently introduced powers: curated, partner-validated bundles of MCP servers, steering files, and best practices that install with a single click and load on demand when a relevant task comes up. Install a power, and Kiro’s agent gains specialized expertise the moment you need it.

For Dynatrace customers already working in Kiro, it’s the shortest path yet from code to production insight. For developers new to Dynatrace, it’s a one-click way to ground Kiro’s reasoning in real facts from your environment, not guesses.

Why this matters for developers

Developers have historically been one step removed from production. When something breaks after deployment, the path to figuring out what went wrong usually runs through a Site Reliability Engineering (SRE) or operations team, and AI coding assistants can’t automatically and reliably remediate issues in software they’re unfamiliar with. Agents that can write code are guessing about how their code behaves in production unless they have access to real telemetry data.

The Dynatrace Kiro power for Dynatrace closes this gap through Dynatrace Intelligence, the agentic operations system at the core of the Dynatrace platform. Kiro’s answers are grounded in deterministic, causal AI and real-time production data, not probabilistic guesses.

With the tools provided by the Kiro power, developers can:

• Investigate live incidents and get root cause analysis directly in Kiro chat
• Query metrics, logs, and traces from production using natural language
• Surface security vulnerabilities affecting the code they’re working on
• Get remediation suggestions grounded in what’s actually happening in their environment

“Using Kiro powers for Dynatrace has been a total game-changer in the observability space. Deep-dive root cause analysis of complex system issues that once required lengthy manual intervention now happens in seconds, giving us unprecedented speed and confidence.”

Mike Kobush, Sr. Software Performance Engineer, NAIC

How to install the Kiro power for Dynatrace

Getting started takes only a few steps. Once installed, the Kiro power activates automatically when Kiro detects a relevant task. Mention an incident, a slow service, or anything that needs production context, and the Dynatrace tools and guidance will load in Kiro chat.

Prerequisites

• A Dynatrace account. If you don’t already have one, you can start a free 15-day trial.
• Kiro installed on your system.

Prepare the Dynatrace connection

First, create a Dynatrace Platform Token, which Kiro will use to authenticate. Then add the required permissions for the Dynatrace MCP server.

Install the Kiro power

The power can be installed from either the Kiro IDE or the Kiro powers website. For this walkthrough, we’ll use the IDE.

1. Launch the Kiro IDE.
2. Select the Ghosty icon with the lightning bolt to open the powers panel.
3. Select Dynatrace Observability from the Recommended
4. Select Install. The power is registered with placeholder values for the Dynatrace URL and token. Therefore, Kiro will show an error message that the MCP server can’t be reached.
5. To complete the configuration, select Open Settings and replace the placeholders with your environment details.

Configure your tenant and token

In the settings file, replace the two placeholders:

Start asking questions

Open a new chat in Kiro and start interacting with your Dynatrace environment using natural language. Query active problems or security vulnerabilities, request a root cause analysis to identify critical issues in production, or pull related logs and traces, all without leaving the IDE.

See it in action

The short demo below walks through installing the Kiro power for Dynatrace, verifying the connection, and running a first query against your environment to list the top 10 vulnerabilities detected by Dynatrace.

Get started with the Kiro power for Dynatrace

Kiro powers transform what used to be a stitching exercise (MCP servers here, steering files there, custom instructions somewhere else) into one single, ready-to-use bundle. The Kiro power for Dynatrace applies the same idea to observability: live production insight, causal root cause analysis, and remediation grounded in real telemetry, all available the moment a developer needs them.

The result is a tighter loop between writing code and understanding how it behaves in production. Less waiting for diagnostic data from someone else. Less guesswork from an AI assistant operating without context. And, more time spent on the work that actually matters.

Ready to try it? The Kiro Power for Dynatrace is publicly available: install it from kiro.dev or the Kiro IDE and start asking your environment questions.

The post Dynatrace observability is now a Kiro power appeared first on Dynatrace news.

If you’ve already wired an AI coding assistant up to Dynatrace, through the MCP server, the Dynatrace CLI (dtctl), or a custom agent you built yourself, you’ve seen your agent have difficulty interpreting data or calling for fields that don’t exist. This makes sense, your agent may be making assumptions based upon training that isn’t relevant. It lacks the skills to understand how to get the best value from Dynatrace. That is where Dynatrace for AI fills the gap.

What are agent skills?

Agent skills are an open format for packaging domain knowledge that AI agents can load on demand. A skill is a folder containing a SKILL.md file with focused instructions, examples, and optional reference material. Compatible agents, such as Claude Code, GitHub Copilot, Cursor, Cline, or others, discover installed skills and load the full content only when it’s relevant to the task at hand.

The net effect: you can install dozens of skills without bloating an agent’s context window. Agents pull in exactly what’s relevant when it’s relevant, and ignore the rest.

Built for agents working with Dynatrace

Dynatrace for AI is a curated set of skills that give an agent the three things it needs to efficiently do real work on Dynatrace:

• Access to Dynatrace data and insights: through DQL queries against Grail®, Smartscape® dependency graph, or problem records.
• Dynatrace expertise: the syntax rules, entity-model distinctions, and query patterns that separate a working query from one that looks correct but returns nothing.
• Task-level starting points: ready-made prompt templates for common engineering workflows, so teams don’t have to invent the approach from scratch.

Skills don’t connect to Dynatrace directly. You have to pair them with the MCP server or dtctl to perform live queries and initiate actions. Together, they turn an agent with generic observability intuition into one that easily extracts value from Dynatrace.

Complement your agent with domain expertise

The first release of Dynatrace for AI agent skills is focused on the workflows that engineering teams run every day:

• DQL fundamentals: covering the pipeline model, core data objects, and when to use fetch, timeseries, or smartscapeNodes to prevent failures that typically come from models trained on generic query-language data.
• Observability across the stack: services, traces, logs, frontends, and problems, each covering the entity model, key fields, and query patterns that make answers correct rather than merely plausible.
• Infrastructure and cloud: covering Kubernetes, AWS, and hosts.
• Platform tasks worth delegating: providing programmatic creation of dashboards and notebooks

Prompt templates for common workflows

Alongside the skills, the repo hosts a small set of prompt templates you can use as structured starting points to invoke the right skills for specific tasks. These save teams from having to design their approach from scratch and make outcomes more consistent across agents and users.

Current templates include:

• Performance regression: walks the agent through comparing RED metrics before and after a deployment, correlating any regression with distributed traces, and summarizing the root cause.
• Daily standup: pulls the last 24 hours of problems, deployment activity, and notable anomalies for a team’s services, so anyone can walk into a standup with the relevant production context already framed.
• Troubleshoot a problem: takes a problem ID and guides the agent through root-cause analysis, including affected entities, correlated events, relevant logs and traces, and creates a structured summary for the incident channel.

These are a starting point, not a ceiling, designed to be forked and shaped to your team’s on-call runbooks.

What Dynatrace for AI is and what it isn’t

Skills and prompts are a knowledge and workflow layer. They don’t connect to your Dynatrace environment, define what actions your agent can take, or set guardrails. That’s the job of the tool you pair them with and your Dynatrace permission model.

The quality of what your agent can produce also depends on the entities your environment is instrumented to capture. Skills help agents ask better questions of data, but they don’t control what data is collected.

Think of this skill as onboarding a smart new hire who already knows software, but needs to learn your platform. The skills are the platform user guide; your observability data is the work itself.

Get started

It’s super simple to install the skills and prompts in one go. Just run:

npx skills add dynatrace/dynatrace-for-ai

…or activate the skills as a Claude Code plugin:

claude plugin marketplace add dynatrace/dynatrace-for-ai
claude plugin install dynatrace@dynatrace-for-ai

Make sure your agent can reach Dynatrace, then try a real agent-skill task. A few good example starting prompts:

• “Compare the error rate of the checkout service over the last hour vs the same hour yesterday.”
• “Are any pods in the production namespace restarting or getting OOM-killed right now?”
• “Use the performance-regression prompt to check the deployment I just shipped.”

The difference in output quality is immediate: fewer corrections, cleaner queries, and answers that accurately reflect how Dynatrace continuously models your environment in real-time.

The Dynatrace for AI project is open source and actively developed. Issues, discussions, and pull requests are all welcome, especially from teams running agent skills against real workloads. We’d love to hear from you.

The post Dynatrace for AI: Teach your AI coding agent how to use Dynatrace appeared first on Dynatrace news.

A paradigm shift: Moving from signal monitoring to true entity health understanding

Digital systems continuously evolve and adapt. Making effective decisions requires real-time, always up-to-date insights into how everything is connected—from infrastructure to applications—and understanding the impact on users and the business when issues arise. When an anomaly occurs, you need to quickly pinpoint the root cause, understand why it happened, identify exposed components, and determine which critical services depend on them.

Autonomous AI agents raise expectations for speed, precision, and self-healing IT systems, but, like humans, AI agents rely on high-quality data and rich context to operate effectively. Basic observability signals fall short because they lack contextual information and a holistic view of IT entities and their dependencies, making it difficult to derive impact and causality. In a world of AI agents, an accurate, real-time production context becomes non-negotiable, as only then can you trust AI agents to make the right decisions.

Smartscape has been a core part of the Dynatrace platform for years, and it powers Dynatrace causal AI. Smartscape is a real-time dependency graph that visualizes how your IT components depend on each other, continuously updating as your topology changes. Smartscape maintains AI-ready context across ephemeral components in hybrid and multicloud environments. This real-time discovery and updating happens automatically across multiple sources, so the model always reflects reality and serves as your ultimate single source of truth.

^{Figure 1. Explore your IT systems and their dependencies visually with the new Smartscape app.}

The new Smartscape was developed for cloud native, large-scale environments and comes with major new capabilities:

• Powerful visual analytics in the all-new Smartscape app, including domain-specific views for cloud, Kubernetes, infrastructure, and more.
• Fully native cloud entities with complete metadata and raw cloud/Kubernetes object JSON.
• Agentless cloud data ingest that automatically adds all entity dependencies and policy context.

• Exploration at scale with Dynatrace Query Language (DQL). Run native graph queries (for example, traverse) to multi-hop across millions of relationships with full Grail® context.

These enhancements unlock many high-value use cases, transforming the way you and your teams work.

• End-to-end cloud visibility: Close cloud‑console gaps with full relationship context for faster decisions across multi‑cloud and hybrid environments.
• Understand Kubernetes dependencies immediately: Diagnose issues quicker with full‑fidelity objects, YAML context, and cross‑cluster dependency tracing.
• Stronger security posture: Visualize exposure and attack paths, prioritize by real blast radius, and enforce IAM and configuration best practices.
• Accelerate incident response and collaboration: Use the new Visual Resolution Path to see upstream and downstream dependencies and get Dynatrace Intelligence insights in context. Route alerts to the right owners, cut handoffs, and reduce escalations.
• Validate and optimize architecture and cost: Compare intended vs. runtime architecture, align ownership, and reduce costs using real dependency and utilization context.
• Reliable CMDB/ServiceNow enrichment: Export precise, auto‑discovered dependencies with external IDs for accurate ITSM automation.

Spot and understand patterns instantly with the new Smartscape app’s powerful visual analytics capabilities

The new Smartscape app delivers rich, large-scale visual analysis tailored for modern cloud and AI-native environments, with a smooth and responsive experience at scale.

• Explore thousands of entities interactively and quickly drill down into topology and entity details.
• Navigate your entire environment with all dependencies, or use domain-focused, ready-made Smartscape views for clouds, Kubernetes, classic infrastructure, or services.
• Work in context across the platform:
  • The Visual Resolution Path in the Problems app lets you jump directly into the Smartscape Problems Graph to analyze systemic patterns or blast radius.
  • View topology: an intuitive, in-context action that lets you explore vertical and horizontal topologies for any entity without leaving your app or workflow, which is perfect for understanding dependencies and drilling into details.
• Align views to your business context with segments. Focus your analysis on entities by team ownership, environment, business unit, or region to reduce noise during change windows and reviews. This allows you to understand who owns what and accelerate collaboration with a shared understanding of your IT system.
• Analyze patterns from every angle: switch topology layouts to reveal different insights. force exposes hidden clusters and dependency hubs for dynamic microservice exploration; horizontal traces workflows left to right for end-to-end transactions or CI/CD flows; and vertical highlights layered architectures top to bottom for dependency stacks or escalation paths.

Agentless topology discovery from clouds

Dynatrace can now directly discover entities and relationships from cloud environments, including security groups, VPCs, load balancers, subnets, and other network services, providing accurate connectivity, policy, and configuration context, even without deploying OneAgent. In addition to raw topology, Dynatrace automatically ingests, normalizes, and enriches cloud‑native metadata such as tags, labels, ownership properties, cost centers, compliance attributes, and compute metadata, creating a high-quality semantic layer.

All discovered entities and their metadata are unified in the new Smartscape, revealing practical and actionable insights, for example: Which instances are publicly accessible? How is traffic routed across accounts and regions? How do security groups influence exposure paths? And much more.

Experience the new Smartscape, now Generally Available, in your Dynatrace environment

Explore the new Smartscape app, which will be available in your Dynatrace SaaS environments during the first week of February 2026, and begin uncovering dependencies across clouds, Kubernetes, infrastructure, services, and problems.

For a deeper dive, check out our documentation and walk through the Playground notebook, which guides you step‑by‑step in using DQL to query Kubernetes entities.

And stay tuned: our next blog post in this series will take you even further, exploring the new domain‑specific views in Smartscape.

Ready to get started? Start exploring your digital systems now on the Dynatrace Playground.

The post The new Smartscape: Move faster and make better decisions with a real-time dependency graph of all your digital systems appeared first on Dynatrace news.

March 31, 2026 update

Today we congratulate AWS on the general availability of AWS DevOps Agent. This marks an important step forward in how teams operate and innovate in the cloud, moving closer to systems that can investigate and respond with minimal human intervention.

At Dynatrace, we are proud to have collaborated with AWS on this initiative from the beginning. Together, we have worked to bring observability, AI, and automation closer together to help customers simplify operations and resolve incidents faster.
Our joint customers are already seeing measurable value, including up to a 70 percent reduction in mean time to resolution, as teams move from reactive troubleshooting to more intelligent and automated workflows.

This work reflects a broader shift toward agentic operations. We are continuing to deepen our collaboration with AWS across DevOps Agent and other AI services as this space evolves. This foundation sets the stage for how the Dynatrace platform and AWS DevOps Agent integration works in practice.

How AWS DevOps Agent and Dynatrace complement each other to resolve incidents faster

It’s late at night, you’re on call, and an alert fires for an AWS application. You need to assess the severity, understand the impact, and quickly notify the relevant teams. Until now, that potentially meant toggling between Dynatrace and the AWS Console to piece together the full picture. With the AWS DevOps Agent and Dynatrace integration, you instantly have all the information you need at every stage of remediation.

AWS DevOps Agent represents a new class of frontier agents: AI that works autonomously for hours or days, investigating incidents without constant human intervention. Dynatrace provides causal and predictive AI that pinpoints the root cause of issues and anticipates problems before they escalate. Together, they create something neither can deliver alone: end-to-end incident resolution that spans from early warning through root cause to remediation.

When AWS announced the DevOps Agent at re:Invent last December, they showcased this integration as a key use case, demonstrating how autonomous investigation becomes dramatically more effective when powered by Dynatrace precise, topology-aware production context. The agent doesn’t just correlate signals; it understands what those signals mean for your business.

Experience topology-aware root cause analysis with guided mitigation

Consider a typical CRM stack: a React frontend on S3 and CloudFront, an ALB routing to Lambda-hosted Python services implementing the CRM business logic, backed by an RDS PostgreSQL. During normal operations, the responses take ~1 ms, but suddenly those degrade to 1 s+. Dynatrace instantly detects the problem with all relevant context, including business impact, and automatically triggers the AWS DevOps Agent to initiate further investigation.

Figure 1: Dynatrace and the AWS DevOps Agent work hand in hand to analyze and mitigate the problem.

• Root cause analysis with causal AI: Dynatrace detects response-time degradation and automatically gathers relevant context, including potentially AWS resources causing the issue, such as Lambda, RDS, and ALB.
• Seamless collaboration with AWS DevOps Agent: Dynatrace triggers the AWS DevOps Agent and passes full runtime context, allowing it to trace the execution path from symptom to failing component.
• Pinpoint the root cause: The AWS DevOps Agent analyzes underlying RDS logs, identifies DROP INDEX commands that correlate with slowdown events, and surfaces the findings directly in Dynatrace, without tool switching. The commands are traced to an input error by a database administrator.
• Recommend and stage a fix: the agent provides a clear diagnosis, recommended remediation steps, and proposed action that’s ready for human approval.
• Prevent recurrence: The agent suggests proactive monitoring of database logs for similar commands to prevent future incidents.

This always-on, on-call workflow accelerates triage, allows topology-aware root cause analysis, guides mitigation, and adds preventative recommendations. It works across a broad set of AWS services, including AWS Lambda function errors, Amazon EKS container failures, Amazon VPC connectivity issues, and more.

Ready to try it out yourself?

With the Dynatrace integration into AWS DevOps agents, you get:

• Fewer handoffs and clearer ownership with a single investigation narrative (no bouncing between teams/tools)
• Less manual correlation as Dynatrace supplies topology, dependencies, and traces as a ready-to-use production context
• Faster “why” analysis as AWS DevOps Agent correlates AWS telemetry with change/deployment history and proposes mitigations
• A more repeatable incident response, including prevention recommendations to reduce repeats

For more details on the preview and how to try it yourself, have a look at this hands-on walkthrough on the AWS Cloud Operations Blog. You can also refer to AWS documentation for instructions on connecting Dynatrace and the AWS DevOps Agent.

For more news on Dynatrace and AWS, have a look at this recent blog post.

The post Integration with AWS DevOps Agent: Autonomous investigations powered by production context appeared first on Dynatrace news.

In today’s cloud-native environments, having real-time observability data at your fingertips is crucial. By integrating Kiro powered by AWS with Dynatrace, you can leverage powerful AI-assisted monitoring and troubleshooting capabilities directly in your development workflow.

Kiro—which recently reached general availability—helps developers by bringing structure to AI coding with spec-driven development. When a developer needs to fix an issue, investigate an error, or optimize resource usage, it’s crucial they can analyze what happened just before the issue occurred and delve deeper into the infrastructure utilization of your applications in your cloud or container environment.

Unlock development productivity with live production insights

Developers typically face restricted access to production environments, being fully dependent on site reliability engineers (SREs) or operations teams to detect and report issues post-deployment, and provide them with the necessary information to fix an issue. This segmented workflow can result in delayed problem identification and resolution, an increased risk of failures in production, and reduced efficiency throughout the development lifecycle.

By connecting Dynatrace with Kiro, developers can access real-time insights from production environments, gain contextual information down to the root cause of an incident, and receive remediation proposals—all within their Kiro environment.

Kiro has a built-in Model Context Protocol (MCP) client that can be used to extend its capabilities to communicate securely and flexibly with external data sources and tools such as Dynatrace.

Let’s dig deeper into how to leverage this capability and provide Dynatrace’s unique insights to your development teams.

Step-by-step integration guide

Prerequisites

• You’ll need a Dynatrace account. If you don’t already have one, you can start a free 15-day trial.
• Kiro must be installed on your system.
• You must have basic familiarity with AWS services and the Dynatrace platform.

Prepare integration with Dynatrace

First, you need to create a Dynatrace Platform Token, which is used to define Kiro access, and then add the required permissions for the Dynatrace MCP server.

Configure Kiro MCP Settings

The Kiro MCP configuration is managed through a JSON file. The interface supports two levels of configuration:

• User-level: ~/.kiro/settings/mcp.json applies to all workspaces
• Workspace-level: .kiro/settings/mcp.json is specific to the current workspace

You can apply the configuration using two different methods:

Method 1: Open the command palette (use Cmd + Shift + P on Mac or Ctrl + Shift + P on Windows/Linux), search for MCP and select Kiro: Open workspace MCP config (JSON) or Kiro: Open user MCP config (JSON), depending on whether or not you want to configure the settings for the workspace or user level.

Method 2: Alternatively, you can use the Kiro Panel. Open Kiro and select the Kiro ghost icon to open the left-side panel. Locate the MCP SERVERS section, select  Open MCP Config, and then start configuring the connection for the Dynatrace MCP Server.

Dynatrace specific settings

Note: Only add one of the following configurations, depending on whether you want to use the remote MCP server or the local MCP server. You can’t use both at the same time.

Using the remote MCP server

Use the following configuration. Replace $TENANT_ID with your Dynatrace environment ID. (You can find your environment ID in the URL of your Dynatrace environment — for example, https://<ENVIRONMENT_id>.apps.dynatrace.com/ui.) Then, replace $DT_PLATFORM_TOKEN with the ID of the Dynatrace platform token you created previously (for example, dt0s16.XXXXX).

{ 
"mcpServers": 
  { 
    "dynatrace": {
      "type": "http",
      "url": "https://$TENANT_ID.apps.dynatrace.com/platform-reserved/mcp-gateway/v0.1/servers/dynatrace-mcp/mcp",
      "headers": {
        "Authorization": "Bearer $DT_PLATFORM_TOKEN"
      },
      "tools": ["*"]
      }
  }
}

Connect the local MCP server

The configuration for the local Dynatrace MCP server can be added to the Kiro IDE using one-click installation or by following the manual configuration as shown below. Don’t forget to replace $TENANT_ID with the ID of your tenant.

{
  "mcpServers": {
    "dynatrace-mcp-server": {
      "command": "npx",
      "args": ["-y", "@dynatrace-oss/dynatrace-mcp-server@latest"],
      "env": {
        "DT_ENVIRONMENT": "https://$TENANT_ID.apps.dynatrace.com"
      }
    }
  }
}

Verify the integration

Once configured, you can use the Kiro chat to interact with Dynatrace through natural language conversations. Simply tell Kiro what you need, whether it’s investigating a critical incident, gaining insights into metrics, logs, or traces from your application, analyzing dependencies, or setting up automated alerts.

In the screenshot below, you can see in the lower left which capabilities are provided by the Dynatrace MCP Server. Beyond the standardized actions, such as listing active vulnerabilities or problems, querying data stored in Dynatrace, or creating a workflow, you can also interact with Davis CoPilot®, the Dynatrace natural language assistant.

Conclusion

This integration isn’t just another feature; it’s a fundamental shift in how Dynatrace integrates with your development workflow. It brings together the power of Kiro’s AI capabilities with the Dynatrace unified observability platform, allowing developers to access critical monitoring data and gain a real-time understanding of their production environments via natural language interaction.

Spend less time context switching and more time creating value for your customers. Start today and benefit from real-time insights, precise root cause analysis based on causal understanding or improved troubleshooting capabilities, and enhanced development workflows.

Explore how Dynatrace can integrate seamlessly into your development landscape using our remote MCP Server. If you’re interested in learning more about Kiro, have a look at their launch blog post or visit the documentation and dig deeper into how to connect with MCP Servers.

The post Real-time insights: Leverage Dynatrace observability capabilities within Kiro powered by AWS appeared first on Dynatrace news.

The integration of Dynatrace with Microsoft Azure SRE Agent establishes a new benchmark for cloud operations by leveraging AI-based root cause analysis and real-time production insights, alongside a comprehensive understanding of complex, large-scale IT environments. You can leverage the combined strengths of Dynatrace and Microsoft, enabling teams to resolve complex problems in large-scale IT environments more quickly and efficiently, and automate incident remediation, moving one step closer to driving autonomous operations across their complex environments.

In today’s cloud-first world, reliability isn’t just a goal; it’s a competitive advantage. As more services move online and LLM-powered assistants evolve into autonomous agents, maintaining the reliability, scalability, and cost-efficiency of critical systems becomes essential.

That’s why Dynatrace and Microsoft teamed up to integrate Dynatrace® AI-powered observability with the Azure SRE Agent. This collaboration allows site reliability engineers (SREs) to ensure seamless operations while proactively planning for future scalability and reliability requirements.

Transform your incident management through the combined capabilities of Azure SRE Agent and Dynatrace AI

Azure SRE Agent, introduced earlier this year, provides SREs and developers with the tools they need to increase the speed and efficiency of incident responses, diagnostics, and collaboration, allowing them to resolve problems quickly.

Seamlessly integrated with incident management tools such as ServiceNow, as well as the developer ecosystem, represented by GitHub Copilot or Azure DevOps, the agent runs in the background 24/7, learning and monitoring the health and performance of your cloud environment.

As a reliability assistant, Azure SRE Agent supports teams by efficiently diagnosing and resolving production issues. You can ask the agent questions in natural language, easily access clear and concise problem summaries, and coordinate incident workflows with integrated human-in-the-loop approvals.

Dynatrace enhances Azure SRE Agent’s troubleshooting and automation capabilities with advanced observability insights. By mapping topology, data, and business context, Dynatrace gains a comprehensive understanding and delivers production-accurate visibility across your entire IT system. This visibility feeds Dynatrace deterministic AI, allowing precise root-cause identification and impact analysis. All these insights are now seamlessly supplied to the Azure SRE Agent, equipping it with real-time production context and reliable root cause analysis.

This allows your teams to move beyond simply receiving alerts; teams are now provided with AI that acts, guides safe mitigations, and accelerates resolution within Azure-native workflows.

Gain efficiency across every stage of the incident lifecycle

Using the Model Context Protocol (MCP), the Azure SRE Agent is securely connected with Dynatrace. Whether a team member uses the agent to ask questions in plain natural language, or the agent interacts with Dynatrace directly—sharing insights, asking for real-time observability data, or root cause analysis, together with remediation steps—the close collaboration supports use cases across every stage of incident management, allowing you to:

• Cut MTTR by automating routine runbooks and diagnostics, with safe, approved mitigation actions based on full context.
• Reduce security risk by triaging vulnerabilities faster with production evidence, triggering guided fixes, and validating outcomes.
• Accelerate delivery with contextual GitHub issues and PRs that include root cause, blast radius, and tests, minimizing issue reproduction time and rework.
• Improve fix accuracy by correlating Azure and Dynatrace telemetry for precise root-cause and impact analysis.
• Prevent incidents before they happen using real-time signals and historical trends to stop regressions and reduce toil.

Illustrating the value: Proactively detect and remediate security vulnerabilities

Let’s take a look at a concrete example, which we presented at Microsoft Ignite. Imagine you run a Java-based payroll app on Azure, and a new security warning (CVE) appears. Every second matters now, and there’s no room for error: you need the issue fixed quickly, without lots of back-and-forth between teams.

• Once the vulnerability is detected, Dynatrace automatically identifies the library that caused the vulnerability, opens a GitHub issue containing all relevant information, such as which parts of your app are affected, and informs Azure SRE Agent.
• The SRE agent reviews the GitHub issue and requests additional information from Dynatrace via the MCP server, such as the number of users affected, how often it happens, which endpoints are involved, or which customers might be affected, to assess the scope and impact of the vulnerability.

• After gathering all necessary details, the SRE Agent synthesizes the information and creates a new GitHub issue, assigning it to GitHub Copilot for remediation.
• GitHub Copilot then takes action by updating the configuration and code in the GitHub repository to resolve the vulnerability automatically.
• The pull request not only includes the necessary version changes but also includes documentation, highlighting all findings as well as how the issue was remediated, along with unit tests, to prevent the issue from recurring.

Try the power of Agentic AI for incident resolution

Dynatrace delivers deep, causation-based insights into your live systems, now seamlessly integrated with Azure SRE Agent to elevate your incident management. With this integration, you can unlock:

• Smarter detection and remediation: Deep contextual observability from Dynatrace, correlated with Azure telemetry, enhances issue identification and resolution across complex environments.
• Automated operations: Routine runbook actions and diagnostic workflows can be automated, reducing mean time to repair and freeing teams to focus on innovation.
• Proactive reliability: Continuous analysis of real-time and historical data identifies leading indicators of failure, allowing teams to prevent incidents before they impact customers.

Azure customers can now access Azure SRE Agent directly in the Azure portal. To connect Dynatrace with the agent and learn how to set up Dynatrace MCP Server, see Dynatrace Documentation.

The post Boost cloud reliability: Dynatrace and Azure SRE Agent unite for autonomous operations appeared first on Dynatrace news.

With Dynatrace, developers can rest assured that everything they need—from development to deployed infrastructure—is available with full context at every touchpoint. Traditionally, developers have had limited visibility into production systems, relying on operations teams to surface issues after deployment. This disjointed approach often leads to delays in identifying and resolving problems, increased risk of production failures, and inefficiencies in the development process

With GitHub’s recent announcement of custom agents, Dynatrace is proud to launch its first custom agent, introducing a powerful new entry point for Dynatrace insights directly within GitHub repositories, where developers can act on them immediately. This integration ensures that developers no longer need to leave their familiar GitHub environment to access critical observability and security data. Whether it’s triaging production errors, validating deployments, or responding to security vulnerabilities

This isn’t just another way to consume observability and security insights from Dynatrace—this is about achieving true end-to-end visibility, from code to production, by combining the capabilities of Dynatrace with GitHub Copilot and its custom agents.

In this blog post, we’ll explore the most prominent use cases offered by this integration and demonstrate how deploying these two tools in tandem can unlock new levels of efficiency, reliability, and security for your software development lifecycle.

How it works

Dynatrace and Git solutions support opposite ends of the Software Delivery Lifecycle: Git hosts your code repository while Dynatrace monitors your production infrastructure. Agentic AI and the MCP protocol allow bridging of this gap, essentially allowing AI assistants to verify their code in production.

Setting up the connection with Dynatrace is simple

We recommend using your local MCP server for prototyping and testing things out. First, follow these instructions to create a platform token with the necessary scopes. Once this is done, install the MCP server in your GitHub repository: you’ll find the configuration in Settings > CoPilot > Coding Agent (an example can be found in the repository linked above).

Finally, you need to set up the custom agent in your repository under .github/agents/Dynatrace.md. For your convenience, we’ve provided an example file that you can simply drag and drop. Update your MCP server’s credentials, and you’re all set.

Tip: Before promotion to production, we recommend switching from your local MCP Server to our remote MCP Server.

Use cases: Unlock the power of production insights

Dynatrace’s custom agent for GitHub Copilot unlocks the following core use cases, each designed to enhance developer productivity and ensure operational excellence:

Incident Response and Root Cause Analysis

Developers can investigate and resolve production failures directly within GitHub by leveraging Dynatrace Davis® AI for real-time problem detection, backend stack trace analysis, and business impact assessment. This provides higher precision in less time, without requiring changes to workflows at other locations.

Deployment impact analysis

The agent validates deployments by comparing pre- and post-deployment metrics, detecting anomalies, and providing data-driven health assessments to ensure smooth rollouts.

Production error triage

Dynatrace systematically monitors and categorizes production errors. Now, with a custom agent, we can prioritize remediation efforts, reduce error backlogs, and improve application reliability directly in GitHub Copilot.

Performance regression detection

Dynatrace continuously monitors application performance baselines, ensuring that any degradation in latency, throughput, or error rates is flagged before it impacts your end-users or breaches service-level objectives (SLOs).

Release validation and health checks

Acting as an automated quality gate, the agent can validate releases, monitor post-deployment stabilization, and ensure compliance with SLOs.

Security vulnerability response and compliance monitoring

Dynatrace integrates security workflows into GitHub, proactively identifying vulnerabilities, mapping them to compliance frameworks, and providing prioritized remediation recommendations

To infinity and beyond

Dynatrace’s custom agent is more than just a tool for many use cases—it’s a powerful toolkit that helps you unlock the full potential of your existing data to uncover the insights you need, precisely when you need them. The use cases we’ve highlighted here are just the beginning. The true power of this integration lies in the dynamic nature of AI, enabling you to search, query, and connect insights across a vast network of agents and platforms. While the journey may take you through uncharted territories of interconnected ecosystems, and it may sound a bit scary at first, there is huge value (and fun!) in turning complexity into clarity and productivity.

Ready to consolidate observability and get answers faster?

Have you already seen the recently launched GitHub custom agents, and are you interested in trying out Dynatrace’s custom agents? Then familiarize yourself with our remote MCP Server and learn how to integrate it into your development landscape.

The post From code to cloud: Dynatrace launches first GitHub custom agent, consolidating observability for developers appeared first on Dynatrace news.

Ninety-five percent of Generative AI projects fail to deliver measurable value, and leaders are under mounting pressure to demonstrate that their AI investments are effective. Achieving this requires clear visibility into how and where AI is used, and the outcomes it’s driving.

Dynatrace is setting a standard for observability across the AI stack, and we’re extending that same level of insight to our own AI tools. The new Davis CoPilot® Feature Adoption Dashboard utilizes the same telemetry that Dynatrace teams rely on to improve product quality. Assess effectiveness and optimize how Davis CoPilot supports productivity and decision-making, to move from experimentation to sustainable results.

Davis CoPilot, the Dynatrace platform’s LLM-powered assistant, helps teams work faster by leveraging the full context of their data on Dynatrace to deliver precise and actionable answers. The result is less time spent searching for information or onboarding users, and more time extracting the maximum value from the Dynatrace platform and achieving measurable outcomes.

IT and central team leaders typically offer Davis CoPilot to their users, with specific goals in mind that align with their organization’s broader AI strategy. Initiatives like these typically aim to achieve three key objectives:

• Adoption and engagement: Ensure AI becomes an integral part of routine workflows, so value can scale across teams.
• Productivity gains: Reduce manual effort, increase speed to insight, and improve the quality of outcomes.
• Demonstrable business value: Connect usage to measurable results, such as reduced operational costs, faster incident resolution, or improved service levels.

Understand how AI is used and how it delivers value

To make these objectives measurable, you need visibility into how AI is adopted by your users, the purposes it serves, and whether it delivers the intended value. Only then can you identify where improvements are needed. The ready-made Davis CoPilot Feature Adoption Dashboard delivers this visibility out of the box, showing how Dynatrace generative AI features are used across your organization. Based on the provided metrics and insights, administrators and central teams can make data-driven adjustments.

Know how frequently and for what purpose Davis CoPilot is used, in real time

Gain real-time visibility into when and how regularly teams are using Davis CoPilot in their workflows. The dashboard highlights active engagement, query activity, and usage trends across your organization, helping you understand where Davis CoPilot delivers the most value and where additional enablement may be needed.

By analyzing usage patterns, you can identify high-performing teams, monitor overall adoption progress, and ensure employees are using Davis CoPilot effectively to achieve meaningful outcomes.

For a deeper analysis, break Davis CoPilot usage down further by skill:

• Chat: Analyze chat interactions and workflow actions (currently in private preview), showing how users engage with Davis CoPilot to ask questions, troubleshoot issues, and automate routine tasks.
• Natural language querying: Tracks how users convert everyday language into Dynatrace Query Language (DQL) commands, supporting faster data exploration for both technical and non-technical users.
• Explain DQL queries: Shows how users rely on Davis CoPilot to interpret and summarize complex queries, making it easier to understand and build on existing work.
• Document search: Tracks how users engage with AI-driven document retrieval for accelerated troubleshooting in the Problems app.

Track user experience and satisfaction

To determine whether Davis CoPilot delivers value, it’s important to measure not only usage but also the quality of user interactions and outcomes. The dashboard tracks execution times and success rates to demonstrate how well Davis CoPilot performs in real-world scenarios. This makes it easier to identify technical issues such as invalid DQL generation or prompts blocked by guardrails and content filters.

Additional user feedback adds context to these signals. Thumbs-up and thumbs-down reactions help indicate where users achieve the desired outcome and where they run into problems. When negative feedback clusters around similar prompts or skills, administrators can examine the failed prompts, identify common failure modes, and understand the conditions that lead to them. This supports targeted follow-up actions, such as improving internal guidance for AI usage, reinforcing enablement for specific teams, and surfacing actionable improvement requests to Dynatrace.

For example, if multiple users struggle with natural language queries for Kubernetes data, admins can review the failed prompts, provide best practices, and verify that these measures lead to higher success rates over time. You can even consider enriching your data by adding common synonyms with OpenPipeline. Nequi shared their story at Perform 2025.

Together, operational metrics and contextual feedback help organizations to quickly identify friction points and take concrete steps to improve user outcomes and overall satisfaction.

Optimize performance of AI-generated insights

The dashboard also provides transparency into the queries executed through Davis CoPilot, including query counts and the volume of data scanned. This helps you better understand the resource and cost impact of AI-generated insights across your environment. This level of visibility is critical, as many AI initiatives stall because teams lack the insight to understand the operational impact of increased usage.

By identifying data-intensive queries early, you can optimize performance, control cost exposure, and avoid unexpected resource spikes that can undermine confidence in scaling AI. Capabilities such as segment filtering or organizing data into dedicated buckets allow you to fine-tune data access based on organizational needs. This gives you the ability not only to monitor AI activity but also to adjust and govern it responsibly, ensuring Davis CoPilot remains efficient, controlled, and aligned with your broader business objectives.

Make use of the full potential of Davis CoPilot

The Davis CoPilot Feature Adoption Dashboard equips you with the insights needed to scale Davis CoPilot responsibly, maximizing productivity gains while maintaining control. With clear visibility into usage, success rates, and operational impact, you can build a stronger foundation for continued AI expansion.

The dashboard is instantly available in the environments of Dynatrace customers who have enabled Davis CoPilot.

The post Enhance the impact of Dynatrace Davis CoPilot with built-in observability appeared first on Dynatrace news.

The NVIDIA Enterprise AI Factory addresses the rapidly evolving needs for AI infrastructure to support the rise of agentic AI. Since its launch, customers have leveraged this validated design to build agents by following structured methodology and recommended frameworks, which simplifies deployment and configuration while facilitating the implementation of AI factories in both on-premises and hybrid cloud environments.

Dynatrace has been an integral part of this initiative. Dynatrace full-stack AI and LLM observability helps organizations move forward with confidence in building their AI and agentic AI initiatives.

Observable AI: Turn a black box into a glass box to build confidence

With the publication of comprehensive guidelines, it’s simpler than ever for Dynatrace customers to set up and start monitoring their full-stack NVIDIA enterprise AI infrastructure, including its key tiers and components. Covering the infrastructure layer from GPUs to Kubernetes, NVIDIA NIM microservices, NVIDIA NeMo, and other technologies up to the application layer, Dynatrace observability enables customers to confidently run and operate complex AI workflows on NVIDIA infrastructure.

In parallel, Dynatrace has worked to significantly advance our AI and LLM observability offering by introducing the following:

• A dedicated app experience for AI observability with out‑of‑the‑box analytics, auto‑instrumentation, targeted metrics, a debugging flow, and ready‑made dashboards.
• Data governance and audit trails for AI services, turning governance into a competitive advantage.
• Model versioning and A/B testing to compare model performance across versions.
• Multi-modal agent explainability and tracing throughout RAG pipelines and agentic frameworks.

These improvements address challenges such as missing observability insights, scale, sovereignty, and trust. This empowers organizations to operationalize AI by building trust and monitoring guardrails; providing analytics capabilities to detect user-facing issues; helping SREs and AI-native engineers maintain performance, reliability, and security; and reducing cost across the agentic, AI, and LLM stack.

Privacy and security lead the way to scaling AI with confidence

AI is delivering significant productivity improvements, with 66% of senior executives reporting positive trends in productivity, according to PwC’s AI Agent Survey. This momentum is driving the demand to manage AI expenditures, enhance the decision-making quality of agents, and optimize development through visibility into AI components’ behavior in production environments — from pilot projects to full-scale operations.

However, sensitive data considerations and strict compliance requirements often impede progress, preventing organizations from fully realizing the benefits of AI adoption. As enterprises prioritize data privacy, regulatory compliance, and data sovereignty, there is an increasing need for high-performance NVIDIA AI infrastructure alongside frameworks designed to preserve control, trust, and autonomy in AI development.

In a recent blog on sovereign AI, NVIDIA shares strategies for nations and enterprises to develop AI factories that uphold local governance, security, and cultural values. Combining such factories with the Dynatrace advanced observability solution enables organizations to operationalize AI at scale — building secure and scalable agents, deployed on premises or in hybrid environments.

From privacy needs to public-sector requirements: NVIDIA AI Factory for Government

At NVIDIA GTC Washington, D.C. today, NVIDIA AI Factory for Government was announced, in support of the needs for regulated environments to drive AI initiatives. The U.S. Office of Management and Budget’s decision to establish scorecards for agencies’ AI maturity and management is in line with a 2024 Gartner Research forecast that more than 60% of government organizations will be prioritizing their investments in business automation by 2026 — up from 35% in 2022. The NVIDIA AI Factory for Government is a full-stack, end-to-end reference design that brings the power of reasoning AI to federal organizations. It helps organizations unlock productivity gains just like it does for enterprises, from service delivery to threat detection and day-to-day operations.

Built on the experience of deploying internal AI factories, the reference design offers guidance for deploying agentic AI, physical AI, and high-performance computing workloads on premises and in hybrid cloud environments, while meeting the compliance needs of federal and other secure organizations. The NVIDIA AI Factory for Government reference design includes NVIDIA Blackwell accelerated computing and NVIDIA networking, NVIDIA-Certified Systems, NVIDIA AI Enterprise software, NVIDIA Nemotron open models, and third-party software from AI leaders, all validated by NVIDIA.

Dynatrace delivers trusted observability and automation for regulated environments

Dynatrace has always been committed to supporting the public sector and other industries with regulatory requirements by providing customers with capabilities to control data flow through its lifecycle and manage sensitive data from ingestion to deletion, as well as global deployment options to meet data residency requirements, configurable retention times for different data types and use cases, unique encryption keys for customer’s stored data, and more.

Our dedication is reflected in customers’ success stories from regulated industries, as well as a growing list of global and local certifications, such as ISO 27001, SOC 2 Type II, CSA STAR 2, ENS, Tisax, and others. Find out more about our certifications and supported compliance frameworks in our Trust Center. For organizations also navigating evolving sovereignty requirements, our approach to digital sovereignty demonstrates how Dynatrace combines technical innovation with policy alignment to deliver trusted solutions globally.

Benefit from full-stack observability for end-to-end validated design

Dynatrace observability with the NVIDIA AI Factory for Government reference design enables organizations to accelerate the deployments of their AI agents and applications for federal and enterprise environments, and benefit from real-time, AI-powered insights.

These benefits range from improved scalability and performance to reduced complexity and total cost of ownership by simplifying processes, mitigating deployment risks to improved data security and compliance.

Visit the Dynatrace Playground to experience the possibilities of AI and LLM observability, and discover how Dynatrace is accelerating enterprise AI at scale.

Dynatrace and the Dynatrace logo are trademarks of the Dynatrace, Inc. group of companies. All other trademarks are the property of their respective owners.

The post Unlocking productivity and trust: Dynatrace observability in NVIDIA AI Factory appeared first on Dynatrace news.

The value of automation and agentic AI

The Dynatrace® AI-powered observability and security platform, with its remote Model Context Protocol (MCP) server, revolutionizes this process by integrating observability context into automation and agentic AI-driven workflows. By connecting Dynatrace with GitHub Copilot coding agent, organizations can achieve prioritized and automated vulnerability remediation that not only streamlines security but also maintains system performance and developer efficiency.

Both developers and site reliability engineers (SREs) benefit from this agentic AI collaboration, bringing actionable runtime insights from Dynatrace directly into GitHub and efficiently automating vulnerability remediation.

Automated security remediation with smart runtime verification use case

GitHub Dependabot proactively alerts developers when known vulnerabilities are detected in their projects’ dependencies, helping teams stay secure and compliant. As organizations and projects scale, prioritizing and addressing the alerts becomes a challenge: deciding which vulnerabilities matter most in a given context and streamlining the path to remediation.

Let’s dig deeper into two different scenarios, where Dynatrace can help to improve remediation by automating developer tasks and prioritizing work based on impact.

To optimize remediation efforts and minimize release delays, it’s essential to prioritize vulnerabilities based on their actual impact on production applications.

Dynatrace providing context for automating the remediation of GitHub Dependabot alerts

In a typical environment, when streamlining vulnerability remediation, you might utilize GitHub Actions workflows to regularly poll Dependabot. Once a new alert is detected, the workflow creates a new issue and assigns it to the GitHub Copilot coding agent.

To fully understand the problem and its impact, GitHub Copilot coding agent queries Dynatrace—using the remote MCP server—to get additional runtime data. Dynatrace confirms that the vulnerable library is loaded, and that its own Runtime Vulnerability Analytics (RVA) identifies the same issue and verifies the impact by highlighting if the vulnerable function is used in live environments and if it’s exploitable.

Equipped with the additional context, the coding agent generates a code-level fix. To remediate and prevent insecure code, the fix is added as a pull request to the GitHub repository, awaiting developer review to ensure human oversight.

Once the change is approved and the fix deployed, Dynatrace continuously monitors the environment, verifying the remediation and ensuring the issue is resolved without introducing new problems.

Automate and orchestrate security findings from GitHub Dependabot with Dynatrace Workflows

Unifying and contextualizing vulnerability findings across different tools helps apply prioritization and centralize automation for real-time runtime validation and fix deployment, supporting SREs to minimize potential disruptions to their services.

With the Dynatrace integration for GitHub Advanced Security, you can continuously forward GitHub Dependabot alerts to Dynatrace. Once ingested, Dynatrace uses its capabilities for further analysis, including an RVA verification that provides a contextual understanding of the potential impact on the monitored environment.

The workflow creates a new GitHub issue, including a comprehensive summary of alerts with their confirmation status.

GitHub Copilot Coding Agent automatically picks up the issue and submits the proposed fix for verified alerts as a pull request for a developer to review. This ensures the remediation process remains transparent and allows for human oversight before deployment. Once the pull request is approved and merged, the alert is remediated and the code is secured.

Automated end-to-end security remediation

These two scenarios exemplify how organizations can shift from reactive to proactive security management, automating repetitive tasks and providing actionable insights for developers.

The relationship between Dynatrace and GitHub demonstrates the power of agentic AI in modern software development, where runtime data drives decision-making and empowers coding agents to apply fixes to code environments—all in a standardized way, applying enterprise guardrails.

Reduce your mean time to resolution (MTTR), enhance developer productivity, and ensure robust system security by automating security remediation—all without sacrificing performance or uptime.

The benefits of the coding agent are further amplified with the GitHub announcement of introducing custom agents. Dynatrace has just launched its first custom agent, which seamlessly integrates Dynatrace’s observability and security capabilities into GitHub Copilot, empowering teams to maintain operational excellence, ensure application reliability, and uphold security compliance across the entire software development lifecycle (SDLC).

This allows teams to streamline incident response, perform root cause analysis, validate deployments, triage production errors, and many more use cases—all directly within their GitHub repository workflows.

By delivering real-time insights and actionable data from production environments, Dynatrace extends GitHub’s reach into production, effectively closing the SDLC. Stay tuned for our upcoming blog, where we’ll dive deeper into the powerful capabilities of Dynatrace’s custom agent for GitHub Copilot.

Ready to transform your security workflows?

Explore how Dynatrace can integrate seamlessly into your development landscape using our remote MCP Server and read through our walkthrough documentation.

Sign up for the preview and experience how real-time production context makes your organization more efficient.

The post Hands-free vulnerability remediation with Dynatrace and GitHub Copilot appeared first on Dynatrace news.

The new Dynatrace integration with Atlassian solves this by embedding real-time production insights directly into incident management processes. Teams gain instant visibility into what’s happening, who’s impacted, and the actions required to resolve issues faster — all without the need to switch tools.

Dynatrace uniquely detects problems in real time by understanding topology, data context, and dependencies across your entire digital ecosystem. Incidents are automatically tied to underlying root causes, giving teams a complete, production-accurate, “live” picture of problem details, severity, and impact.

Dynatrace insights are now accessible in Jira Service Management through human-readable summaries generated by Atlassian Rovo. By bringing production context directly into Jira, Confluence, and Jira Service Management, you’ll accelerate response times and significantly reduce mean time to resolution (MTTR).

At Dynatrace, context is our mantra, sitting at the core of everything we do. This means more than just data enrichment: Every piece of data is automatically contextualized, and dependencies are mapped to reveal the full picture. However, context also means delivering the right data exactly when and where you need it. To do just that, Dynatrace is bringing these insights directly into Atlassian. This is not just limited to IT service management (ITSM). You can get access to contextualized insights directly within an IDE as described in our latest blog post about the new Dynatrace  MCP Server.

Diagnose faster with context from production at your fingertips

Most incident tickets land on an engineer’s desk with little more than a timestamp, a vague description, or a user complaint. They rarely reveal the severity of the issue, which systems are affected, or what might be causing it. This lack of context in an ITSM workflow forces teams to spend unnecessary time digging through monitoring dashboards, chasing logs, or switching between tools just to piece together the basics of the problem.

Instead of getting frustrated, you can now instantly ask the Rovo Ops agent to identify anomalies that occurred around the incident timeframe. The agent queries Dynatrace via our MCP Server and returns the findings directly in the same browser window.

Having contextual details and alerts available directly in the ticket context means you gain immediate clarity into health, what’s wrong, the impact, and the evidence. This leads to faster diagnosis and quicker recovery, while also reducing unnecessary escalations of already-known or related issues, ensuring internal resources aren’t tied up with redundant work.

Remediate smarter with AI-driven root-cause analysis and automation

Once an incident is identified, the Rovo Ops agent utilizes Dynatrace production insights, which accelerate triage and root-cause analysis for incident managers, pinpointing the actual root cause in real time and delivering a higher level of insight and accuracy.

Rovo can now pull in Dynatrace Causal AI insights, including the precise root cause and blast radius of the issue, and combines these with Jira Service Management incident and change history. With Dynatrace contextual intelligence, Rovo delivers fact-based, AI-generated problem summaries and clear remediation recommendations, outperforming the guesswork of pure GenAI approaches.

From this point, just follow the remediation recommendation and trigger a suggested automation action in Jira Service Management, or ask follow-up questions for clarification.

Learn for the future with automated post-incident reviews

The job isn’t finished after an incident is mitigated and marked resolved in Jira Service Management, as you still need to capture what happened and determine how to prevent its recurrence. Instead of spending hours on manual write-ups, Rovo automatically triggers the post-incident review (PIR) process.

In the auto-generated PIR, Rovo surfaces all of the relevant details and history, from the root cause to detected anomalies, all of which are enriched by Dynatrace AI-driven insights. This provides a complete, time-ordered view of the incident, which is combined with Jira Service Management context attributes like assignees, tags, outage duration, and related change logs. With this context, the agent generates a draft PIR. Inside the PIR, you’ll find monitoring charts showing the status before, during, and after the incident, a clear summary of the cause, and a pre-filled prevention plan. All that’s left for you to do is review, refine, and finalize the PIR.

The automatically documented PIRs act as built-in retrospectives, helping teams continuously mature their operations. They also feed insights back into Rovo to sharpen its future recommendations.

Transform how you work, beyond incident management

These are just a few examples of what’s now possible through the extended Dynatrace + Atlassian integration. We’ll continue to explore deeper integrations to make your troubleshooting journey even more efficient in the future.

Imagine directly following up on investigations from within Rovo, with seamless drill-downs into Dynatrace® Apps, or surfacing related post-mortem information and runbooks stored in Jira or Confluence to SREs when investigating an issue in Dynatrace.

And the potential impact goes well beyond incident management. By bringing reliable, real-time production truth into daily workflow and connecting that truth directly to business outcomes, more teams and roles can fundamentally transform the way they work, harnessing the full power of agentic AI.

• Get instant release validation: Developers can query Rovo for pre- and post-deployment failure rates, SLOs, and outcome metrics, allowing them to release with confidence, roll back faster when needed, and validate hypotheses with real data.
• Make decisions based on outcomes: Product managers can ask Rovo or Davis CoPilot® to analyze the impact of a new feature or release by investigating KPI shifts such as user engagement or a drop in check-outs.
• Speed up triage based on business impact: Support engineers working on Jira tickets see Dynatrace insights related to the root cause, blast radius, affected applications, and services. These insights are enriched with further details on user and business impact, allowing engineers to perform instant impact analysis before assigning tickets.
• Run smarter daily stand-ups: Development teams receive ready-made summaries, including exceptions, user analysis, and deployment reports from the last 24 hours, providing relevant insights into what’s actually happening in production.

Start benefiting from deeper integrations with Dynatrace as your trusted foundation for agentic AI

Dynatrace delivers a deep, causation-based understanding of your live digital systems, providing the precise, reliable insights that enterprises can trust as a foundation for agentic AI.

Ready to see how Dynatrace and Atlassian work together and benefit from adopting agentic AI concepts? Then dig deeper into the new possibilities using our remote MCP Server and experience how real-time production context makes your operations more efficient.

See our documentation to learn more about how to connect the Dynatrace MCP Server.

The post Dynatrace and Atlassian deliver agentic AI that transforms end-to-end incident management appeared first on Dynatrace news.

Unless you’ve been living under a rock this past year, you’ve heard the buzz about how AI is changing the day-to-day lives of developers, whether it’s using LLMs for vibe coding or adopting agentic AI concepts to improve productivity. In particular, the introduction of Model Context Protocol (MCP) as a standard for connecting AI agents with other agents or tools has led to exponential growth in the number of solutions connecting AI coding assistants with APIs, databases, and more. Last month, GitHub, publisher of the prominent AI coding assistant GitHub Copilot, announced its new MCP registry as a place where developers can find links to MCP servers. This registry solves the challenge of numerous registries, repos, or community threads listing the same MCP servers.

We’re excited to share that the GitHub MCP registry now includes Dynatrace MCP, so developers can integrate Dynatrace observability and security analysis directly into their workflows.

In this blog post, we’ll explore how developers can use Dynatrace MCP together with GitHub Copilot to streamline troubleshooting, enhance security, and boost productivity—without ever leaving their IDEs.

Need to troubleshoot an issue? Dynatrace MCP has the answers

One of the biggest challenges in troubleshooting and observability is knowing where to look for missing data when issues arise in production. It might sound odd, but when you consider the sheer number of tools, applications, environments, and layers of source code developers need to navigate, it’s not at all clear where they should look for quick answers. No wonder onboarding time is such a major factor in engineering productivity.

Your day as a developer might start with a complaint about something not working correctly. You receive a Jira ticket with a cryptic error message that includes a link to a service health dashboard or a notification in the problem list. You start rummaging through the logs and dashboards to find answers outside your IDE, with little context. This greatly increases your cognitive load and delays the problem’s resolution.

Developers who use Dynatrace, though, don’t have to manually dig through logs and dashboards. They get clear summaries, root cause information, and all relevant data in the context of the affected service. Thanks to the updated problem flow, it’s easy for them to identify the root cause and remediate it.

Context is key

Now imagine a scenario in which your DevOps team uses MCP as their standard for integrating external tools and insights. As a developer, your instinct is to jump straight into the source code, so why not share as much context as possible right there? Utilizing GitHub Copilot with the Dynatrace MCP integration in place, you get all relevant data from your production environment and quickly isolate the problem, giving you the ability to:

• Get information on the root cause
• Query related logs, metrics, and traces
• Get real-time data from all environments, including production
• Leverage additional gathered insights, such as CPU and memory profiling, from the affected service
• Get further context using query patterns, such as “group logs by customer impact”

And the best is, you don’t need to know how or where to look—Dynatrace handles all this for you automatically. And there’s more: you can even ask Dynatrace for remediation suggestions.

_{Figure 2. Dynatrace identifies the problem root cause as an arithmetic exception, all via LLM and the MCP protocol in the developer VS Code IDE. (video)}

What’s happening behind the scenes

When you type a natural language prompt into the GitHub Copilot chat, GitHub’s MCP client establishes a connection with the Dynatrace MCP server, which then connects to Dynatrace. The LLM converts the prompt into a context-aware call and ultimately transforms it into a DQL query that it executes on Dynatrace Grail® data lakehouse, which retrieves the necessary data.

Need to fix a security issue? Dynatrace MCP has the answers

By integrating security testing practices earlier in the Software Development Lifecycle, the Shift-left principle has brought security responsibilities into the developer’s world, and they’re here to stay. Developers often find themselves reacting to alerts from SREs, manually auditing code, or relying on static analysis tools that frequently miss context-specific vulnerabilities.

You can instantly access insights like:

• Vulnerabilities in your code, including open source and third party vulnerabilities
• Recommendations for fixing an issue
• Proactive checks tailored to your current coding context

All of this happens without pulling developers away from their flow. MCP allows for a smarter, more proactive approach to security—one that’s embedded in their development process.

Need to create new code? Dynatrace is here to help

Writing new code with Dynatrace allows developers to look ahead proactively. By typing natural-language, conversational questions like “Have I bumped into CPU limits?” or “What is my CPU usage? Is it too high?” developers can identify potential bottlenecks and performance issues before they become real problems, ultimately delivering higher quality code.

Developing new code or optimizing a service in an existing app brings even more complexity. Such work involves identifying inefficient API usage, reducing unnecessary load, improving performance, and assessing the potential impact of the new code so as to minimize deployment issues.

Need to verify recent CICD builds? Dynatrace helps you shift left

As a developer, you want to catch build issues early—before they snowball into deployment delays or production incidents. With Dynatrace MCP, you can type questions like:

• “What failed in the last build?”
• “Are there any performance regressions tied to this commit?”
• “Did this deployment introduce any anomalies?”

By integrating Dynatrace into your CI/CD pipeline, you gain real-time visibility into build health, test coverage, and deployment impact. This means faster feedback loops, fewer surprises, and higher delivery quality. Dynatrace helps you to shift from reactive debugging to proactive delivery assurance—all through natural language interactions.

Get started with Dynatrace MCP

The Dynatrace MCP server is available as a community-supported open source project. To familiarize yourself with all it can do, visit the Dynatrace MCP project. in our GitHub repository. There you’ll find all the necessary documentation to guide you through the setup process and explain all the available capabilities.

The post Sky-high developer productivity with Dynatrace MCP and GitHub Copilot appeared first on Dynatrace news.