Dynatrace Intelligence generative AI overview
- Latest Dynatrace
- Explanation
- 5-min read
Dynatrace Intelligence generative AI is designed to boost productivity, help with onboarding, and enable you to explore data through natural language.
Dynatrace Intelligence generative AI
Dynatrace Intelligence generative AI is based on a large language model (LLM). The model used by Dynatrace AI generates responses based on your inputs and is probabilistic. This means that the responses are generated by predicting the most probable next word or text, based on the data that they have been created with, and on the provided context. Dynatrace Intelligence generative AI uses the Retrieval Augmented Generation (RAG) approach to provide a foundational LLM with the proper context to transform natural language into a DQL query (in-context learning).
Because of this approach, these models can sometimes behave inaccurately, incompletely, or unreliably. This means there is a risk that the response you receive does not accurately reflect the prompt you provided or that the generated content sounds reasonable but is incomplete or inaccurate.
We recommend that you carefully evaluate the responses you get back from Dynatrace Intelligence generative AI. If the generative AI responds inaccurately, please provide feedback directly from 
Notebooks, 
Dashboards, or 
Dynatrace Assist.
Generative AI skills overview
Dynatrace Intelligence generative AI service offers distinct and specialized skills. Currently, generative AI offers four skills:
-
NL2DQL: this skill powers the Prompt quick analysis functionality available in
Notebooks and Dashboards. NL2DQL translates your natural language prompts into DQL queries. For details, see Query with natural language. -
DQL2NL: this skill powers the Explain query functionality in
Notebooks and Dashboards. DQL2NL provides a summary and an explanation of existing DQL queries to help you better understand DQL. For details, see Summarize and explain queries. -
Conversational recommender: this skill powers
Dynatrace Assist, our global conversational interface. The conversational recommender is capable of answering your Dynatrace help, onboarding, and usage questions. For details, see Dynatrace Assist.- Dynatrace Assist also offers context-aware conversations in the apps such as
Problems, 
Kubernetes, or Dashboards. Context-aware conversations trigger predefined, contextual prompts and provide you with contextual explanation, remediation steps, and summaries. For details, see Dynatrace Assist context-aware conversations.
-
Document suggestions: this skill powers the relevant Troubleshooting Guide suggestion functionality in
Problems. Troubleshooting guide recommendation improves problem resolution by automatically surfacing relevant troubleshooting guides, such as notebooks or dashboards created by your team. For details, see Discover relevant troubleshooting guides with Dynatrace Intelligence generative AI.
Since the skills offered by Dynatrace Intelligence generative AI are highly specialized, Quick Analysis in Notebooks and Dashboards cannot answer general questions, and Dynatrace Assist might produce inaccurate DQL queries.
Dynatrace Intelligence generative AI architecture and data flow
Dynatrace Intelligence generative AI uses the Retrieval Augmented Generation (RAG) approach to provide a foundational LLM with the proper context to transform natural language into a DQL query (in-context learning). This means that Dynatrace Intelligence generative AI will enrich your prompt with relevant additional content or context that is sent to the foundational LLM in order to generate an appropriate response. The content or context that is used to enrich your prompt depends on which underlying skill is queried.
The data and additional context is used only to enrich prompts; the model does not learn from this. Customer data isn't used to automatically fine-tune, train, or improve any models or services. For more information, see How are NL2DQL responses generated?
Dynatrace Intelligence generative AI usage limits
There is no limit to the number of interactions you can have with generative AI. However, there is a throughput limit. This means that each user can ask 10 questions in a rolling 15-minute timeframe.
There is a similar limit to how many questions can be asked by all users in your environment simultaneously. Your environment can handle up to 40 questions in a rolling 15-minute timeframe.
If you have exceeded any of the limits, you'll see an error message: "I'm sorry, but I couldn't generate an answer for you because of unusually high demand. Please try again in a minute."
Frequently Asked Questions
If you would like to learn more about Dynatrace Intelligence generative AI, visit our FAQ page.
Related topics
Dynatrace Assist