Try it free

Personalize Assist responses

  • Latest Dynatrace
  • How-to guide
  • 2-min read
  • Published Aug 10, 2026

With agentic mode enabled, Dynatrace Assist personalization allows you to tailor how Dynatrace Assist responds to your prompts by providing additional context that's applied to every conversation. The additional context includes:

  • Your Profile: a freeform text field where you can describe who you are and how you work.
  • Custom Instructions: a freeform text field where you define how Dynatrace Assist should respond to your questions.

Your Profile and Custom Instructions fields are user-scoped, which means that each user can configure their personalization settings independently from their organization.

You can access the personalization feature only if you have agentic AI enabled in your environment and have sufficient permissions to use it.

To access the personalization feature

  1. Open Dynatrace Assist.
  2. From the chat interface, go to .
  3. In the Preferences tab, select Enable Personalization.
  4. In the Your Profile field, enter a short description of who you are and your working style or responsibilities. For example, I'm a senior developer working with Infrastructure observability.
  5. In the Custom instructions field, enter instructions to configure AI responses further. For example, Reply in German. Don't use emojis.
  6. Select Save to save your configuration.

Limits

The following limits apply to the Dynatrace Assist personalization feature:

  • You can enter a maximum of 500 characters in Your Profile field and 500 characters in Custom instructions field.
  • Personalization preferences don't apply to the intermediate replies, such as the analyzing steps, query generation and its execution, and explanation of the steps Dynatrace Assist takes before providing the final answer. This means that intermediate replies will use default preferences and provide responses in English. Only the final result reflects your configured preferences.

Content filters and guardrails

Dynatrace Assist applies content filters and guardrails to all chat interactions. Since your profile information and your custom instructions are applied to every conversation, they might trigger our content filters or guardrails. This includes, but is not limited to attempts to:

  • Override system behavior
  • Inject adversarial prompts
  • Include content unrelated to legitimate platform usage

If your personalized response is getting blocked, you can temporarily disable the personalization feature to test if your profile information or your custom instructions are causing this. If that's the case, we recommend that you rephrase the input for both fields and focus on your role, technical context, and response preferences.

What to include in Your Profile

The following types of information can increase Dynatrace Assist response quality and relevance:

  • Role or job title: provide your job title or a field to help Dynatrace Assist adjust its vocabulary, framing, and the type of guidance it provides. A Senior SRE and a Junior Developer receive different responses to the same question due to the difference in experience and practical skill levels.
  • Expertise with Dynatrace: provide information about your experience with Dynatrace. For example, I have no experience with Dynatrace or I have been using Dynatrace for 2 years and have a grasp on basic concepts. This information allows you to control whether Dynatrace Assist explains foundational concepts or opts to only explain advanced techniques and terminology.
  • Tech stack and tools: provide information about the tools and stacks you use in your job to prevent generic answers. When Dynatrace Assist knows that you work with Kubernetes on AWS using OpenTelemetry, it can reference specific configurations and commands rather than offer abstract guidance.
  • Domain or industry: provide the domain or department you work in. This helps to ensure that Dynatrace Assist uses the correct terminology, conventions, and compliance context. The term "deployment" has different definitions depending on whether you work in financial services or in retail.
  • Teams you support: explain which teams you support or interact with. Knowing your audience helps Assist to adjust its responses accordingly. For example, if you're an SRE writing for developers, Dynatrace Assist would tailor its responses differently than for an ops lead reporting to management.

If you don't know what information you should provide when describing your profile to tailor your experience, you can use this list as a reference.

What to include in Custom Instructions

The following types of instructions allow Dynatrace Assist to adjust its response and style, and have measurable effects on response usefulness:

  • Preferred language: instruct Dynatrace Assist to respond in a particular language. Configuring a preferred language increases the clarity and precision of responses.
  • Tone and formality: select the preferred tone and adjust Dynatrace Assist response style and tailor it to your preferred way of communication to increase readability.
  • Detail level: instruct whether Assist should be concise and terse or thorough and explanatory in its responses. Configuring the detail level allows you to save time if you're an experienced user who doesn't require additional explanation and helps you to decrease the number of follow-up questions if you're a beginner.
  • Response format: provide preferences for the response format, such as bullet points, step-by-step instructions, code examples, DQL queries, or UI navigation paths.
  • What to avoid: provide negative constraints to avoid unnecessary information. For example, you can instruct Dynatrace Assist to skip basic explanations, avoid repeating your question, or avoid technical jargon.

If you don't know what kind of instructions can help to tailor your experience, you can use this list as a reference.

Personalization feature doesn't support PII masking

Your Profile and Custom Instructions fields are stored as plain text and aren't subject to PII masking. Don't include any confidential credentials or sensitive personal data, such as:

  • Passwords
  • API tokens
  • Access keys
  • Social Security numbers
  • Financial information

You are responsible for ensuring that the content you enter in these fields is appropriate and doesn't contain information that should remain private. We strongly recommend limiting your profile to professional role, technical context, and response preferences only.

Use case examples

The following examples illustrate how different personas might configure their personalization settings.

Example 1: Advanced SRE

Your Profile

I'm a Senior SRE at a financial services company. I manage Kubernetes clusters on AWS and use Dynatrace for full-stack observability. I'm experienced with DQL, Davis AI, and OpenTelemetry. My team is responsible for maintaining SLOs across 40+ microservices.

Custom Instructions

Be concise and technical – skip basic explanations. Always include DQL examples when relevant. Use metric keys and entity selectors in your answers rather than describing UI navigation. Respond in English.
Example 2: Platform Engineer

Your Profile

I'm a Platform Engineer building an internal developer platform. I work primarily with Dynatrace workflows, Site Reliability Guardian, and OpenPipeline. My audience is development teams who are not Dynatrace experts. I have intermediate DQL skills and deep Kubernetes knowledge.

Custom Instructions

Explain concepts in a way I can relay to developers unfamiliar with Dynatrace. Prefer step-by-step instructions with code snippets. Include code or query examples when helpful. When suggesting solutions, prioritize Dynatrace-native approaches over third-party tools. Keep responses short unless I ask for detail. Avoid marketing language.
Example 3: New Dynatrace User (DevOps Engineer)

Your Profile

I'm a DevOps Engineer at a mid-size e-commerce company. I'm new to Dynatrace – we just started our rollout and I'm learning the platform. I have experience with Grafana, Prometheus, and AWS CloudWatch but I've never used DQL or Davis AI. I manage a mix of EC2 instances and EKS clusters running about 15 Java and Node.js services.

Custom Instructions

I'm still learning Dynatrace, so please explain platform-specific concepts and terminology when you use them. Link to relevant Dynatrace documentation when possible. When I ask about something I used to do in Grafana or Prometheus, show me the Dynatrace equivalent. Use step-by-step instructions with UI navigation paths rather than just DQL queries.

Related topics

  • Dynatrace Assist
  • Get started with Dynatrace Intelligence agentic and generative AI
  • Embedded conversation starters
  • Dynatrace Intelligence agentic and generative AI FAQ
  • Dynatrace MCP server
Related tags
Dynatrace PlatformDynatrace Assist