Using Nexthink Assist
Last updated
Last updated
Nexthink Assist is the unified entry point to managing digital employee experience across the entire Infinity platform. Embedded directly into the search navigation, Nexthink Assist uses the latest large language models from OpenAI and Anthropic to help IT teams see, diagnose and fix DEX challenges instantly through the power of Generative AI. In particular, Nexthink Assist enables users to perform contextual searches across product documentation, extract data on device performance, user sessions, and applications, and quickly create Nexthink campaigns using natural language requests.
Nexthink Assist is currently in Beta and is continually improving. As it evolves, it may occasionally provide information that requires verification. Nexthink recommends confirming your results to ensure accuracy while using Nexthink Assist.
First, ensure that your role allows you to view Nexthink Assist. Refer to the Permissions section for more information.
To access Nexthink Assist, select Nexthink Assist from the main menu.
The Nexthink Assist window appears, allowing you to type your text into the search bar. Use the following options to get the information you need:
Search: Type text in the search bar without hitting Enter to conduct searches across various parameters. Refer to the Using Search documentation for more information.
Assist: Type text in the search bar and hit Enter to create investigations and campaigns, or to get answers related to Nexthink Infinity.
Assist is activated when you press the Enter key. To continue using Search in standard mode, type the name of a binary, device or package.
Use Nexthink Assist to simplify building investigations, streamline campaign creation and answer your questions about Nexthink Infinity.
Ask about Nexthink: Assist enables contextual search across product documentation to get you started quickly, with the information and context you need.
Query Data: Assist helps you extract data and quickly find answers about device performance, binaries, user and session data, application information, and more to resolve issues proactively.
Create: Assist helps you create Nexthink campaigns, making campaign building instantaneous. Compose a quick request in natural language, and watch Nexthink do the rest.
Once you send your question to Assist, it generates and executes an NQL query, creates a campaign or provides an answer from the documentation.
Ask follow-up questions on the same topic to keep the current conversation going. To start a conversation from scratch, click the reset button in the top-right corner of the Nexthink Assist window.
Imagine that you work for a company with a Sales department in Boston. This department has complained about problems with MS Teams call quality. You decide to investigate this issue using Nexthink Assist. The following documentation sections provide guidelines on using Nexthink Assist with examples related to this use case.
To identify the cause of the MS Teams call quality issue, ask Assist to display the average Wi-Fi signal strength per US city sorted in ascending order and hit Enter. The query that Assist creates immediately reveals that the Boston office has the worst Wi-Fi signal strength.
Continue the conversation with Assist in the same window and ask for a list of Sales department employees in Boston. Then, click on View in Investigations to access the Investigations module and get the full list. Refer to the Visual editor and NQL editor documentation for more information about Investigations.
Nexthink NQL data model provides an overview of data Nexthink collects. Assist currently supports a subset of the NQL data model presented below. Refer to the NQL data model for table and field definitions.
Topic | Supported tables |
---|---|
Device & device performance | device |
device_performance/event | |
device_performance/system_crash | |
device_performance/boot | |
Packages, binaries and execution related | package/package |
binary | |
execution/crash | |
execution/event | |
User and sessions related | user/user |
session/login | |
Applications and web applications | application/application |
application/page | |
web/page_view | |
web/transaction | |
web/error | |
Collaboration | collaboration/session |
connectivity/event | |
session/event |
The table below identifies a subset of the NQL data model outside of Assist scope. Additionally, Assist does not support custom fields.
Topic | Unsupported tables |
---|---|
Web events | web/event |
Connections | connection/event |
connection/tcp/event | |
connection/udp/event | |
Packages | packages.installed_packages |
package/uninstallation | |
Alerts | alert/alert |
| alert/monitor |
Campaigns | campaign/campaign |
campaign/response | |
Remote actions | remote_action/execution |
remote_action/remote_action | |
remote_execution/execution_summary | |
Devices | device_performance/hard_resets |
Sessions | session/logout |
session/lifecycle_event | |
session/connect | |
session/disconnect | |
session/lock | |
session/unlock | |
Software metering | software_metering/meter_configuration |
software_metering/event | |
Automation | automation/automation |
automation/execution | |
automation/execution_summary | |
DEX score | dex/score |
Workflows | workflow/workflow |
workflow/executions | |
workflow/executions_summary |
The response times of Assist may vary, and occasionally, some Assist-generated queries might not display correctly in the Visual editor. If you encounter any display issues, view the query in the NQL editor for optimal results.
Once you have identified the problem with the Wi-Fi signal strength in the Boston office, the next step is notifying all affected employees via a Nexthink campaign.
Use Assist to create a campaign to inform employees that the Boston office has Wi-Fi issues. Assist creates this campaign—questions and answers—according to your instructions.
If you would like to improve your campaign, type additional commands into the search bar to provide further guidance.
If you are satisfied with the suggested campaign, simply type Yes in the search bar to save it as a draft in the Campaigns module and define targeted users and the trigger mechanism. Refer to the Creating Campaigns documentation for more information on how to finalize a campaign draft and distribute it among selected audiences.
Assist can help you complete the content section for any type of Nexthink campaign. Examples:
Create a device usage survey
Create a campaign to inform users about ongoing Wi-Fi issues in our office
Create an IT satisfaction survey
Refer to the Conducting engaging campaigns documentation for more information about creating effective campaigns.
Wi-Fi problems are very common and can occur again. Use one of the monitors available in Nexthink Library to effectively monitor Wi-Fi issues and take action to resolve the issue. Ask Assist how you can enable the monitor in the Alerts module.
Assist uses Nexthink Infinity documentation resources to provide the best answer. For further information or instructions, refer to the relevant documentation pages and training linked by Assist at the bottom of its response.
Assist answers your questions using Nexthink Infinity documentation, which includes in-product, and online documentation sources.
Question examples:
How to configure a webhook?
What is the difference between hard and soft navigations?
What is the limit of campaigns I can create in Workplace Experience?