# Understanding employee experience with Spark Spark is a conversational IT agent that serves as the first point of contact for employees when they need IT assistance. Unlike traditional chatbots that rely primarily on predefined scripts or static knowledge bases, Spark follows an agentic approach. It can reason over employee context and execute IT-approved actions to diagnose and remediate issues. Spark leverages extensive device context and Digital Employee Experience (DEX) data, enabling more accurate analysis and targeted resolution. By combining contextual awareness, action capabilities, and learning from resolved incidents, Spark accelerates issue resolution and reduces the need for manual IT intervention. Spark is accessible through a supported workplace communication interface, providing support within a familiar environment. ## How Spark works **Spark** connects with employee requests through the communication channel, runs a diagnosis, and attempts issue resolution.
The **Spark** workflow consists of the following steps: 1. The employee submits a request through a configured communication channel. 2. Spark interprets the employee request in natural language. Depending on the employee request, Spark gathers and evaluates: * Nexthink datasets for the specific user or device diagnosis, limited to the user's own data. * If an employee uses multiple devices (desktop, laptop, or virtual desktop), Spark identifies the relevant device based on context and asks for confirmation. It can list up to 3 most recently used devices. * [Imported knowledge base articles](#import-knowledge-based-article-from-servicenow). * Past ticket resolution data from ITSM, if the relevant connector is configured. * [Available actions](#enable-spark-remediation-actions), including built-in agent actions and custom remote actions for diagnostics or remediation. 3. Spark responds to the employee by sharing answers to employee questions or potential solutions to resolve their issues. Spark can either: * Provide self-help guidance or detailed information, including links to related knowledge base articles. * Request employee authorization for automated resolutions of device issues. 4. If unresolved, Spark escalates the support request to the service desk with full context.\ Spark only escalates requests in the following cases: * After exhausting relevant automatic actions and user troubleshooting * Receiving an explicit escalation request from the employee * Running into issues that require administrative access that the employee does not have * Encountering technical limitations that prevent Spark from providing an effective solution {% hint style="info" %} Spark may suggest and initiate resolution measures, but all device remediation actions require user approval. {% endhint %} ## Context and data inputs To provide relevant responses, Spark uses a combination of static and dynamic data sources: * **Knowledge base articles**: [Manually imported](https://docs.nexthink.com/platform/user-guide/spark/setting-up-and-managing-spark/managing-knowledge-sources) knowledge base articles. * **Contextual Nexthink data**: Device health, diagnostics, remediations and user metadata from Nexthink Infinity. * **Past ticket resolution data:** Resolution notes for incidents resolved by support agents. Spark can use them to suggest remediations and continuously reduce manual interventions and escalations. Refer to [connector-for-servicenow-incidents](https://docs.nexthink.com/platform/configuring_nexthink/bringing-data-into-your-nexthink-instance/integrating-nexthink-with-third-party-tools/inbound-connectors/connector-for-servicenow-incidents "mention") for more information. Consequently, Spark relies on [specific NQL data model tables](https://docs.nexthink.com/platform/user-guide/spark/spark-nql-capabilities) to query Spark-user interaction data. {% hint style="info" %} Personal data handling is covered under the Nexthink Data Processing Agreement (DPA). Spark processing is user-specific and restricted to the customer region. Spark never provides data from other organizations. {% endhint %} ## Spark communication channels Employees use Microsoft Teams as the primary channel to access Nexthink Spark for IT support and troubleshooting. Within Teams, employees can open Spark from the Applications panel and start a conversation to receive secure, AI-powered assistance. Log in to Nexthink Community and read more about [Spark Microsoft Teams app architecture](https://docs.nexthink.com/security/product-security/spark-teams-app-security). Employees can also initiate their IT requests through a supported enterprise chatbot. If the issue requires advanced support, the chatbot transfers the conversation to Spark using the configured Handoff API. The full context of the interaction is preserved, allowing employees to continue the resolution seamlessly in Microsoft Teams with Spark. Log in to Nexthink Community and read more about [Spark Handoff API](https://docs.nexthink.com/api/spark). ## Spark Actions Spark can perform actions to diagnose and remediate employee issues. These actions are enabled by Nexthink administrators after IT approval. Before executing a remediation action, Spark requests confirmation from the employee. Built-in diagnostic actions are excluded from this requirement and may run in the background without interrupting employee work. Refer to [managing-agent-actions](https://docs.nexthink.com/platform/user-guide/spark/setting-up-and-managing-spark/managing-agent-actions "mention") for more information. ## Supported languages Spark detects the employee’s language from message content and delivers responses in that language, enabling employees to interact in their preferred language across most LLM-supported languages. * If the language cannot be detected or is not supported, Spark falls back to the tenant language, currently English or Japanese, and informs the employee accordingly. * Escalated tickets are generated in the tenant language, English or Japanese. They include a short description, actions taken, and the conversation transcript. Additional fields may contain the same content in the original employee language.