> For the complete documentation index, see [llms.txt](https://docs.nexthink.com/platform/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.nexthink.com/platform/user-guide/spark/working-with-spark/understanding-employee-experience-with-spark.md). # Understanding employee experience with Spark Spark is accessible through a supported workplace communication interface, providing support within a familiar environment. ## Spark workflow **Spark** connects with employee requests through the communication channel, runs a diagnosis, and attempts issue resolution. The **Spark** workflow consists of the following steps: ### Step 1: Employee initiates conversation The employee submits a request through a configured communication channel. ### Step 2: Spark interprets the employee inquiry Spark interprets the employee message using natural language processing. If the inquiry is ambiguous, Spark initiates a conversation planning phase consisting of the following steps: 1. **Acknowledge**: Spark acknowledges the request and shows empathy. 2. **Clarify**: If the request is vague or ambiguous, Spark enters plan mode and asks concise questions. 3. **Hypothesis**: Spark shares a hypothesis and next steps based on the information provided.
### Step 3: Spark evaluates data Based on the employee message, Spark gathers and evaluates multiple data sources. #### Spark data sources The following list summarizes the available data sources. For more information, refer to [Working with Spark](/platform/user-guide/spark/working-with-spark.md#context-and-data-inputs) documentation. * Nexthink datasets for user or device diagnostics, limited to the employee's own data. * Imported knowledge base articles * Service catalog ingested from ServiceNow * Past ticket resolution data from ITSM. * Available actions * Nexthink Adopt application guides * Curated list of trusted websites #### Device identification If needed, Spark identifies the employee's device for diagnosis and remediation. * 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. * When Spark cannot find or validate an employee's device, it notifies the employee and continues to provide general troubleshooting and knowledge base content. ### Step 4: Spark provides a response Spark responds to the employee by providing answers or potential solutions, depending on the situation. {% hint style="info" %} Spark only shares resources that meet visibility conditions applicable to the employee. {% endhint %} #### Spark provides self-help guidance or detailed information If no automatic remediation or service request is required or no relevant remediation actions have been made available through configuration, Spark provides guidelines to help the employee address the need. This guidance may include the following resources, relevant to the employee’s request: * Links to related knowledge base articles * Links to Adopt guides, displayed directly in the target application as step-by-step overlays. Shared links redirect the employee to the relevant web application page. The guide launches automatically. Refer to [Creating guides](/platform/user-guide/adopt/guide-creation-and-management-from-nexthink-applications/creating-guides.md) to make guides available for Spark.
#### Spark handles the service request When an employee’s question indicates a need to submit a service request, Spark searches the service request catalog to identify the most relevant option. Spark recommends the appropriate request, providing a direct link along with clear submission guidelines to help the employee complete the process quickly and accurately. #### Spark requests employee authorization for automated remediation If relevant remediation actions are available, Spark requests employee authorization for automated resolutions of device issues. ### Step 5: Spark follows up on the request Spark then communicates the outcome, confirms whether the issue is resolved, and asks the employee if further assistance is needed. 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 %} ## Spark communication channels Employees can access Nexthink Spark through Microsoft Teams, Copilot or through existing enterprise chat entry points integrated with Spark. This gives employees flexibility to start IT support conversations from the tools and conversational interfaces they already use. ### Spark in Microsoft Teams and Microsoft 365 Copilot Within Microsoft Teams and Microsoft 365 Copilot, employees can open Spark from the Applications or Agents panel and start a conversation to receive secure, AI-powered assistance. For more information about Spark Microsoft Teams and M365 Copilot app security, refer to [Spark Microsoft 365 app security](https://edocs.nexthink.com/nexthink-infinity/infinity-specifications/platform-security/spark-microsoft-365-app-security). ### Spark in enterprise AI agents #### Seamless integration with AI agents (A2A) Organizations using enterprise AI agents can integrate them with Spark through the Agent-to-Agent (A2A) protocol. With A2A, employees can start and continue their support journey in their existing chatbot while the agent discovers, invokes, and tracks Spark capabilities in the background. This allows Spark intelligence and Nexthink context to support the employee experience without disrupting the conversation flow. Refer to [Spark Agent2Agent integration](/platform/configuring_nexthink/bringing-data-into-your-nexthink-instance/integrating-nexthink-with-third-party-tools/spark-agent2agent-integration.md) for more information. #### Chatbot-to-Spark handoff 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). ## 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.
Supported languages ``` am, Amharic ar, Arabic az, Azerbaijani be, Belarusian bg, Bulgarian bho, Bhojpuri bn, Bengali bs, Bosnian ca, Catalan cs, Czech cy, Welsh da, Danish de, German el, Greek en, English es, Spanish et, Estonian fa, Persian fi, Finnish fil, Filipino fr, French ga, Irish gu, Gujarati ha, Hausa he, Hebrew hi, Hindi hr, Croatian hu, Hungarian hy, Armenian id, Indonesian ig, Igbo is, Icelandic it, Italian ja, Japanese jv, Javanese ka, Georgian kn, Kannada ko, Korean lb, Luxembourgish lt, Lithuanian lv, Latvian mk, Macedonian mr, Marathi ms, Malay mt, Maltese nan, Southern Min (Hokkien) nl, Dutch no, Norwegian pl, Polish pt, Portuguese rm, Romansh ro, Romanian ru, Russian sk, Slovak sl, Slovenian sq, Albanian sr, Serbian sv, Swedish sw, Swahili ta, Tamil te, Telugu th, Thai tr, Turkish uk, Ukrainian ur, Urdu vi, Vietnamese wuu, Wu Chinese yo, Yoruba yue, Cantonese zh, Mandarin Chinese ```
--- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.nexthink.com/platform/user-guide/spark/working-with-spark/understanding-employee-experience-with-spark.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.