---
sourceDocument: Zurich Enable AI
sourceDocumentLink: https://www.servicenow.com/docs/r/zurich/intelligent-experiences
Release :
- zurich
ft:locale :
- en-US
ft:publication_title :
- Zurich Enable AI
ft:clusterId :
- platai
bundleId :
- platai
workflow :
- Platform
---
# Analyze task trends
# Platform Analyze task trends agentic workflow {#ariaid-title1}
Release version: Zurich
Updated July 21, 2026
 8 minutes to read
Use the Platform Analyze task trends agentic workflow to detect recurring task patterns of closed tickets so that you can understand the root cause and get recommendations to prevent them from happening in future.
## Analyze task trends overview
The Analyze task trends agentic workflow enhances task management by detecting recurring patterns, predicting disruptions, and suggesting proactive resolution to reduce downtime and improve reliability. Tasks are grouped and analyzed
by AI to analyze common recurring issues and root causes. The LLM then generates resolution recommendations based on the analysis and displays it to you. After the analysis is generated, you can continue the conversation to do the
following:
* Get a summary of each group analysis. You have to specify which group you would like to get a summary of.
* Download the analysis as a PDF or Word document.
* Get more information by asking follow-up questions. For example, you can ask why certain suggestions were generated.
* Analyze the next ten groups. Each analysis is done for ten groups at a time. You can continue analyzing more groups with the same filters within the same conversation, but the other actions for the previous group are no longer available.
The exact options for follow-up actions available can be configured.
The default input fields considered for analysis are the following:
* Short Description
* Description
* Resolution Notes
* Resolution Code
* Subcategory
* Category
You can con figure additional input fields using a Now Assist Skill Config Var Set \[sn_nowassist_skill_config_var_set\]. See the Additional configuration section for more information.
The agents, tools, and triggers associated with the Analyze task trends agentic workflow are provided by AI applications. You can [activate the agentic workflow template](https://www.servicenow.com/docs/0CgczLXzyfpCWJu2gJStQw "Activate an agentic workflow that come installed with AI applications in AI Agent Studio.") by making triggers active and setting the display settings to include the ServiceNow Otto panel. If you want to change this agentic workflow's instructions, you must [duplicate it](https://www.servicenow.com/docs/BCOn_oVwhnRsx8HbgrxCCA "Duplicate an existing agentic workflow in AI Agent Studio to save time by not having to manually configure or create agentic workflows."), adjust the settings to suit your specific needs, and activate the duplicated version instead.
Note:
Depending on your license, you will have access to certain application features, generative AI skills, agentic workflows, and AI agents. For more information, see .
## Prerequisites and setup
To access this workflow, you must have ServiceNow Otto for Platform installed on your instance. You can get this by installing any other AI application.
For this agentic workflow to behave as expected, you should have at least 500 records on your task table.
You must also configure Group Action Framework (GAF). See [Group Action Framework](https://www.servicenow.com/docs/WxsAbLOMORV5HwphirGgew "Group Action Framework (GAF) is an intelligence feature on the ServiceNow AI Platform that groups related records and applies actions to them using LLMs.") for more information on what GAF is and how to set it up. The Incident, Case and HR Case tables use the default GAF records, but you can configure GAF for other task tables.
GAF is set up for certain AI applications for you. If you want the agentic workflow to have its own system of categorization different from the main application, you can clone an existing action strategy skill and use the clone in the var set described below. This enables you to train the groupings differently for different agentic resources.
Note:
If you create a clone of an action strategy skill, ensure that Optimized prediction is enabled to use AI Search as your fallback. You can leave it unchecked if you do not use AI Search on your instance.
## Role masking
Required role: sn_uxc_gen_ai.platform_ai_analyze_trnds.
Agentic workflows and their AI agents use [role masking](https://www.servicenow.com/docs/Y5Ut9VQBSiXhQFMyYJC_fw "Role masking for AI agents and agentic workflows helps users enhance security by enabling them to limit their roles during tool execution and verify that AI agents run with least-access privileges.") to determine which users can access them. Ones installed with your applications have specific roles that come included with the application. If you select Users with specific roles for user access, you must configure the security controls to include these roles. For the instructions to change the security controls, see [Define security controls for an agentic workflow](https://www.servicenow.com/docs/J8tIMMU4bpuaMo8GLEwcFQ "In the guided setup for an agentic workflow, define security controls for who can access the agentic workflow and what data the agentic workflow has access to.").
In the data access settings, you must also add the necessary roles to enable reading of the tables for the records you want to access for trend analysis. For example, you can add the itil role to the agentic workflow's list of
approved roles so that it can access Incident records.
## Additional configuration
You can change different settings related to the agentic workflow by changing values for the Now Assist Skill Config Var Set. To access the variable set and make changes, do the following while in the Platform AI Agents and Skills
scope:
* Go to the Now Assist Skill Config \[sn_nowassist_skill_config\] table.
* Open the record named Analyze Task Trends.
* In the Now Assist Skill Config Var Set related list, select Task Trends Input Config.
* Edit the variable values.
* Save or update the record.
Time is a required filter specification in the user utterance. If you want users to be able to filter tasks by fields other than time, you can configure a Task Table Config var set. One for the Task table is provided as part of the application. If you want to create one for a specific table, you can create a Now Assist Skill Config Var Set \[sn_nowassist_skill_config_var_set\]. The Skill Config is Analyze Task Trends, and the Config Type is Prompt Parameter Configuration.
{#incident-trends__entry__3}
| Config field | Description | Default value |
|-|-|-|
| Post Analysis Actions | List of possible follow-up actions a user can take before the agentic workflow completes. | * Get a summary * Get more info * Analyze next 10 groups * Download analysis |
| Analysis Time Frame | Range of time, in months, for the trends analyzer to look at records to identify trends. You can specify smaller ranges when running the agentic workflow, but this value defines the maximum limit. | 3 |
| GAF Record Limit | Number of records analyzed per GAF record grouping. See the previous Prerequisites and setup section. | 8 |
[Table 1. Task Trends Input Config configuration]
{#incident-trends__entry__15}
| Config field | Description | Default value |
|-|-|-|
| Input Table | Table that these potential filter conditions belong to | Task |
| Input Fields | Additional fields that the agentic workflow can consider as context for its analysis | None |
| Filter Fields | Fields that users can include when invoking the agentic workflow If you want to add new fields, use the dot-walked display-label format like the default values. | * Assignment group.Name * Service.Name * Configuration item.Name |
| Group Skill ID | The Group Action Framework grouping skill dedicated to arranging records into categories | No default |
| Action Skill ID | The Group Action Framework action skill dedicated to selecting and mapping representative records for each group and summarizing them See [Group Action Framework](https://www.servicenow.com/docs/WxsAbLOMORV5HwphirGgew "Group Action Framework (GAF) is an intelligence feature on the ServiceNow AI Platform that groups related records and applies actions to them using LLMs.") for information about setting up GAF. | No default |
| Auto Classify Frequency | When the grouping and action skills run again to incorporate new records for analysis | No default Note: If you provide a Group Skill ID and an Action Skill ID but leave the Auto Classify Frequency empty, it will default to 24 hours. |
[Table 2. Prompt parameter configuration]
## Accessing the Analyze task trends agentic workflow
To access the agentic workflow:
1. Navigate to AllAI Agent StudioCreate and manage.
2. Select Analyze task trends.
{#incident-trends__ol_fkq_csr_y2c}
The first step of the guided setup includes a complete list of included AI agents. Selecting the name of an AI agent opens it in a new browser tab, where you can see the full description, role, list of steps, and tools. Tools are
displayed in the second step of the AI agent guided setup, Add tools and information.
## In-product agentic AI and UI actions
Agentic workflows can be accessed in the Core UI and in workspaces in the AI Activity panel. From there, you can track their progress, provide or review input, and see the results of the work performed. For more information, see [In-product agentic AI](https://www.servicenow.com/docs/i9EOdvHBo4_P0I608lkBpA "Dedicated spaces in workspaces and in the Core UI enable you to use agentic workflows directly in record forms. You can view agentic workflow progress and previous executions, and you can answer follow-up questions for ones that require human supervision.") for more details about the AI Activity panel.
To enable users to access agentic workflows with UI actions, you can open the agentic workflow in AI Agent Studio and navigate to the Select channels and access step. You can select a UI action as a possible way to access the workflow
If you don't see your UI actions after configuring it in AI Agent Studio, ensure that the property com.glide.agentic_processes_view.enabled is set to true. See [Enable the in-product experience for agentic workflows](https://www.servicenow.com/docs/IqnpgJwAaYR7V7wuAQTT6w "Enable the AI Workflows panel and UI actions for agentic workflows on forms in the Core UI and workspaces to track agentic AI executions.").
## Testing the Analyze task trends agentic workflow
You can manually test an agentic workflow execution or access on the Testing page of AI Agent Studio if you have the sn.aia_admin role and all other roles configured [in the security controls](https://www.servicenow.com/docs/J8tIMMU4bpuaMo8GLEwcFQ "In the guided setup for an agentic workflow, define security controls for who can access the agentic workflow and what data the agentic workflow has access to."). Start a manual test, select a test type and the name of the workflow, and use utterances in the Task field like the following samples. See [Test an agentic workflow execution](https://www.servicenow.com/docs/zZoaTsjcZclHTVbXUpyTEw "Test your agentic workflow in AI Agent Studio to analyze how it functions while it executes the instructions that you defined.").
If you want to evaluate the agentic workflow over many different execution logs, run an [automated evaluation](https://www.servicenow.com/docs/3HpdefgYzICpE1J1NMccsw "Evaluate agentic AI assets against datasets to monitor performance and compare benchmarks.").
## Sample utterance
After the workflow has been activated in AI Agent Studio, use similar queries to the following to run the agentic workflow in the ServiceNow Otto panel. You can also run this workflow on the Testing page of AI Agent Studio with the same utterance in the Task field if you have the sn.aia_admin role.
Each utterance must include the name of the table and the time frame to analyze. If the utterance doesn't include these things, the agentic workflow prompts you for more information.
The time frame specified by the user can't exceed the maximum value set by the Analysis time frame configuration.
When invoking the agentic workflow, if you want to use additional filters, such as assignment group, use the name of the field in the utterance. For example, "Analyze incident trends assigned to the Hardware group" is more likely to analyze the correct records than "Analyze Hardware incident trends."
* Analyze incident trends related to payment issues within the last two months
* Analyze case trends within the last month
* Analyze HR case trends with High Priority within the last two years
* Analyze incident and problem trends within the last two weeks
## Troubleshooting
When running this agentic workflow, it's possible to see an error that states "I couldn't analyze as I didn't have the required resources." This error occurs when GAF isn't configured for the table you want to analyze. See [Configure Group Action Framework](https://www.servicenow.com/docs/dNhIqffKEr2PxfGANcbgHg "Set up Group Action Framework (GAF) to improve the response quality, recall speed, and consistency of AI agents.") for steps to configure GAF for the table. If you're still having issues after GAF is configured, reach out to Now Support.
## AI agents used in the Analyze task trends agentic workflow
The following table lists the agents that are used in the Analyze task trends agentic workflow.
Important:
In the Select channels and status step of each AI agent's guided setup, make sure that the Status toggle is enabled to activate the AI agent.
{#incident-trends__entry__36}
| AI agent name | AI agent description | Role required |
|-|-|-|
| Issue trend analysis AI agent | Analyzes grouped task data to identify recurring issues and root causes. Provides detailed, actionable recommendations using structured analysis. | sn_uxc_gen_ai.platform_ai_analyze_trnds |
[Table 3. AI agents names and descriptions in the Analyze task trends agentic workflow]
## Other Platform agentic workflows
For more information on other agentic workflows that are associated with the Platform workflow, see [Platform agentic workflows](https://www.servicenow.com/docs/_aFc28uIOhmw3GesJ6USew "You can use the available AI agents Platform agentic workflows to achieve business outcomes with self-executing autonomous AI agents.").
*[\>]: and then