Davis CoPilot overview

  • Latest Dynatrace
  • Explanation
  • 5-min read

Davis CoPilot™, the Dynatrace generative AI, is designed to boost productivity, help with onboarding, and enable you to explore data through natural language.

Davis CoPilot generative AI

Davis CoPilot is based on a large language model (LLM). The model used by Davis CoPilot 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. Davis CoPilot 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 Davis CoPilot. If Davis CoPilot responds inaccurately, please provide feedback directly from Notebooks Notebooks, Dashboards Dashboards, or Davis CoPilot Chat.

Davis CoPilot skills overview

The Davis CoPilot service offers distinct and specialized skills. Currently, Davis CoPilot offers four skills:

  • NL2DQL: this skill powers the Query with AI quick analysis functionality available in Notebooks Notebooks and Dashboards Dashboards. NL2DQL translates your natural language prompts into DQL queries. For details, see Quick analysis with Davis CoPilot.

  • DQL2NL: this skill powers the Explain query with AI functionality in Notebooks Notebooks and Dashboards 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 with Davis CoPilot.

  • Conversational recommender: this skill powers Davis CoPilot Chat, our global conversational interface. The conversational recommender is capable of answering your Dynatrace help, onboarding, and usage questions. For details, see Davis CoPilot Chat.

    • Davis CoPilot Chat also offers context-aware conversations in the apps such as Problems app - new Problems, Kubernetes (new) Kubernetes, or Dashboards Dashboards. Context-aware conversations trigger predefined, contextual prompts and provide you with contextual explanation, remediation steps, and summaries. For details, see Davis CoPilot Chat context-aware conversations.

  • Document suggestions: this skill powers the relevant Troubleshooting Guide suggestion functionality in Problems app - new 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 Davis CoPilot.

Since the skills offered by Davis CoPilot are highly specialized, Quick Analysis in Notebooks Notebooks and Dashboards Dashboards Dashboards cannot answer general questions, and Davis CoPilot Chat might produce inaccurate DQL queries.

Davis CoPilot architecture and data flow

Davis CoPilot 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 Davis CoPilot 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?

Davis CoPilot usage limits

There is no limit to the number of interactions you can have with Davis CoPilot. 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 Davis CoPilot, visit our FAQ page.

Related tags
Dynatrace PlatformCoPilotAsk Davis CoPilot