Prompt agentic AI in Workflows

Latest Dynatrace
How-to guide
3-min read

Agentic AI integration for Workflows is able to actively react to changes and analyze real-time data in your environment by using Dynatrace agentic tools.

By using agentic AI workflow integration, you can:

Analyze real-time data in your environment.
Get insights into the status and changes within your environment by utilizing agentic tools. To learn more about available tools, see Server and server tools.
Make forecasts, analyze open problems and suggest remediation steps.
Generate and execute DQL queries.
Analyze logs, read documents and retrieve security vulnerabilities.
Automate repeated tasks by configuring agentic AI integration to react and adapt to the changes in your environment.

Prerequisites

To use Dynatrace Intelligence, you need to ensure that your DPS license includes AI Units capabilities.

To use the Dynatrace Intelligence agentic AI workflow action, ensure that you have the following permissions:

ai:operator:execute
mcp-gateway:servers:invoke
mcp-gateway:servers:read
document:documents:read

Depending on the tools you use, you might need additional permissions. For more information about tool-specific permissions, see Server and server tools.

Licensing

Starting with Dynatrace version 1.347+, using Dynatrace Intelligence AI outside the Assist UI, Dashboards, and Notebooks is subject to license consumption according to your existing licensing agreement and requires a DPS license that includes AI Units capabilities.

If you are subscribed to any non-DPS licensing model or missing the required capability, you are no longer able to use agentic AI workflow actions.

Limits

Standard usage limits for Agentic and generative AI are also applied to Dynatrace Intelligence:

Item	Maximum limit
Individual user requests	25 requests per 15 minutes
All user requests across the environment	60 requests per 15 minutes
Tools per request	20
Duration of request to operator processing	120 seconds

If you schedule the automatic workflow execution to run frequently, all other Dynatrace Intelligence agentic and generative AI functionality might get throttled due to reaching the request limit. If you do run into the usage limit, please reach out to your CSM.

Set up a "Prompt agentic AI" action

To create a workflow with Dynatrace Intelligence action

In Dynatrace, go to Workflows.
Select Workflow to create a new workflow.
Choose a workflow trigger that will prompt the execution of the workflow.
Select Add task.
Type Dynatrace Intelligence into the search field or select Dynatrace Intelligence > Prompt agentic AI.
Configure the action:
- In the Prompt field, enter your question or request. You can also add specific formatting instructions to better suit your use case.
  You can enter a maximum of 10,000 characters in this field.
- Optional In the Additional context field, provide any additional context (for example, a code snippet or a supplementary information about a problem or event) you want Dynatrace Intelligence agentic AI to reference when executing your prompt. You can reference an output from a previous workflow action in this field.
  You can enter a maximum of 200,000 characters in this field.
- Optional In the Instructions field, provide any additional output formatting instructions you want Dynatrace Intelligence agentic AI to reference when executing your prompt.
  You can enter a maximum of 5,000 characters in this field.
- In Tool selection, select up to 20 tools you want Dynatrace Intelligence agentic AI to use when executing your prompt. Use the Filter tools field to search for specific tools.
  We highly recommend that you select only the tools relevant to your task or question. Choosing all of the tools might significantly increase the time agentic AI needs for executing your prompt.
Optional Expand the Advanced tab and provide additional details for the workflow action:
- In the Output format (JSON schema) field, provide a JSON schema describing fields be included in the output. The example below shows a schema describing serviceID field:
  {
  "$schema": "http://json-schema.org/draft-07/schema#",
  "type": "object",
  "properties": {
  "serviceId": {
  "type": "string"
  }
  },
  "required": ["serviceId"]
  }
  While the Output format (JSON schema) field is optional, it will be included in the workflow output regardless of whether it was filled or not.
  If you left Output format (JSON schema) field empty, the output will look like this: jsonOutput: null.
- In the Conversation ID field, provide the ID of another workflow action that called an agent before to continue a previous conversation with an agent. You can get the previous conversation ID by referencing the output of a previous workflow action that used an agentic tool. The example below uses a result of a workflow action invoke-agent-1 as an input for a conversationId:
  {{ result("invoke-agent-1")["conversationId"] }}
Optional Add any additional workflow action before or after the Dynatrace Intelligence agentic AI action to support your use case.
Select Save.
Select Run to execute the workflow.

Prompt agentic AI in Workflows

Latest Dynatrace
How-to guide
3-min read

Agentic AI integration for Workflows is able to actively react to changes and analyze real-time data in your environment by using Dynatrace agentic tools.

By using agentic AI workflow integration, you can:

Analyze real-time data in your environment.
Get insights into the status and changes within your environment by utilizing agentic tools. To learn more about available tools, see Server and server tools.
Make forecasts, analyze open problems and suggest remediation steps.
Generate and execute DQL queries.
Analyze logs, read documents and retrieve security vulnerabilities.
Automate repeated tasks by configuring agentic AI integration to react and adapt to the changes in your environment.

Prerequisites

To use Dynatrace Intelligence, you need to ensure that your DPS license includes AI Units capabilities.

To use the Dynatrace Intelligence agentic AI workflow action, ensure that you have the following permissions:

ai:operator:execute
mcp-gateway:servers:invoke
mcp-gateway:servers:read
document:documents:read

Depending on the tools you use, you might need additional permissions. For more information about tool-specific permissions, see Server and server tools.

Licensing

If you are subscribed to any non-DPS licensing model or missing the required capability, you are no longer able to use agentic AI workflow actions.

Limits

Standard usage limits for Agentic and generative AI are also applied to Dynatrace Intelligence:

Item	Maximum limit
Individual user requests	25 requests per 15 minutes
All user requests across the environment	60 requests per 15 minutes
Tools per request	20
Duration of request to operator processing	120 seconds

Set up a "Prompt agentic AI" action

To create a workflow with Dynatrace Intelligence action

In Dynatrace, go to Workflows.
Select Workflow to create a new workflow.
Choose a workflow trigger that will prompt the execution of the workflow.
Select Add task.
Type Dynatrace Intelligence into the search field or select Dynatrace Intelligence > Prompt agentic AI.
Configure the action:
- In the Prompt field, enter your question or request. You can also add specific formatting instructions to better suit your use case.
  You can enter a maximum of 10,000 characters in this field.
- Optional In the Additional context field, provide any additional context (for example, a code snippet or a supplementary information about a problem or event) you want Dynatrace Intelligence agentic AI to reference when executing your prompt. You can reference an output from a previous workflow action in this field.
  You can enter a maximum of 200,000 characters in this field.
- Optional In the Instructions field, provide any additional output formatting instructions you want Dynatrace Intelligence agentic AI to reference when executing your prompt.
  You can enter a maximum of 5,000 characters in this field.
- In Tool selection, select up to 20 tools you want Dynatrace Intelligence agentic AI to use when executing your prompt. Use the Filter tools field to search for specific tools.
  We highly recommend that you select only the tools relevant to your task or question. Choosing all of the tools might significantly increase the time agentic AI needs for executing your prompt.
Optional Expand the Advanced tab and provide additional details for the workflow action:
- In the Output format (JSON schema) field, provide a JSON schema describing fields be included in the output. The example below shows a schema describing serviceID field:
  {
  "$schema": "http://json-schema.org/draft-07/schema#",
  "type": "object",
  "properties": {
  "serviceId": {
  "type": "string"
  }
  },
  "required": ["serviceId"]
  }
  While the Output format (JSON schema) field is optional, it will be included in the workflow output regardless of whether it was filled or not.
  If you left Output format (JSON schema) field empty, the output will look like this: jsonOutput: null.
- In the Conversation ID field, provide the ID of another workflow action that called an agent before to continue a previous conversation with an agent. You can get the previous conversation ID by referencing the output of a previous workflow action that used an agentic tool. The example below uses a result of a workflow action invoke-agent-1 as an input for a conversationId:
  {{ result("invoke-agent-1")["conversationId"] }}
Optional Add any additional workflow action before or after the Dynatrace Intelligence agentic AI action to support your use case.
Select Save.
Select Run to execute the workflow.

Prompt agentic AI in Workflows

Prerequisites

Licensing

Limits

Set up a "Prompt agentic AI" action

Related topics

Prompt agentic AI in Workflows

Prerequisites

Licensing

Limits

Set up a "Prompt agentic AI" action

Related topics