Dynatrace Assist allows you to chat with Dynatrace Intelligence and ask questions about the data in your environment, as well as general questions to help you with onboarding to Dynatrace and understanding our core concepts.
The following table describes the required permissions.
To use Dynatrace Assist with generative AI features, you only need the following permissions:
document:documents:writedocument:documents:readdocument:documents:deletedavis-copilot:conversations:executehub:catalog:readYou require the remaining permissions in the table only if you want to use the full extent of agentic Dynatrace Assist capabilities. For more information, see Dynatrace Assist agentic permissions.
For more information, see Getting started with Dynatrace Intelligence generative AI.




After enabling Dynatrace Intelligence generative AI on your environment and setting the user permissions, you should see a new icon below the Search in the dock.
Answers are generated based on Dynatrace-related resources. If the model is unable to respond to your question, you'll see an error message:
Dynatrace Assist allows you to use Dynatrace agentic AI and MCP tools and capabilities to access and analyze your environment data and use it to perform tasks (such as listing problems or generating and executing DQL queries) in addition to answering general questions about Dynatrace.
Agentic Dynatrace Assist shares some additional information, such as tool call results, with enterprise vendors hosting the LLMs that Dynatrace agentic and generative AI are based on. For more information about third parties, see Is my data used to train Dynatrace Intelligence generative AI?.
With agentic AI enabled, you can ask Dynatrace Assist to analyze and provide insights on the data and security of your environment. For examples, see Ask about the data in your environment.
Dynatrace Assist respects your user permissions. This means that all agentic Dynatrace Assist calls are done within the scope of your user permissions and the results won't include anything outside of it.
To use the agentic Dynatrace Assist, you need to
Agentic Dynatrace Assist might not be available for you if you don't meet the prerequisites mentioned above or if you access Dynatrace Assist from the Embedded conversation starters.
You will also need additional permissions for calling the agentic AI tools. For the list of tools and permissions they require, see MCP tools.
Agentic Dynatrace Assist doesn't provide any PII masking. In order to protect your data, when Dynatrace Assist detects PII in the user prompt, the request is automatically blocked and the prompt isn't sent to the LLM for processing.
While interacting with Dynatrace Assist in agentic mode, Assist can call up to 10 internal MCP tools per response. If your request requires Dynatrace Assist to call more than 10 tools simultaneously, it'll be unable to complete the interaction.
You can provide feedback using the built-in feedback mechanism.
Select if Dynatrace Assist has generated a response that has met your expectations and interpreted your prompt correctly.
Select if Dynatrace Assist has generated a response that has failed to meet your expectations or has incorrectly interpreted your prompt. Please provide additional context for us to understand how we can improve this functionality to meet your needs and expectations.
Your feedback isn't used to automatically train any models. It's reviewed only by the product team to monitor the response quality and improve the core product offering.
Dynatrace Assist enriches its answers based on the official Dynatrace sources, such as:
Go through the following process to learn using Dynatrace Assist
You can use agentic Dynatrace Assist to: