> For the complete documentation index, see [llms.txt](https://docs.harmony.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.harmony.io/ai-agents/getting-started/service-desk-agent.md). # Service Desk Agent The Service Desk Agent is an AI-powered assistant that handles incoming support requests by understanding user intent, searching your knowledge base, and delivering relevant answers in real time. It is designed to reduce resolution time by surfacing the right information automatically, without requiring agents or end users to search manually. This article walks you through what the Service Desk Agent does, how its response flow works, and how to get the most out of the knowledge base integration. *** ### How the Service Desk Agent Works When a user submits a request, the Service Desk Agent processes it through a sequence of live steps before returning a response. You can follow this pipeline in real time directly within the agent interface: 1. **Parsing intent** - The agent reads the incoming message and identifies what the user is asking for. 2. **Searching KB** - It queries your connected knowledge base using the parsed intent. 3. **Scanning articles** - Matching articles are retrieved and individually evaluated for relevance. 4. **Ranking results** - The top results are scored and ordered before being included in the response. These live status steps are visible as the agent works, so you always have a clear view of what is happening and why a particular response was generated. *** ### Knowledge Base Article References Alongside every Service Desk Agent response, you will see up to three knowledge base articles that are most relevant to the request. These references are designed to give users and agents quick access to supporting content without cluttering the main response. #### Collapsed View KB article references appear in a **collapsed view** by default. Each collapsed item shows the article title so you can quickly scan whether the results are relevant. #### Expanding an Article Reference Click on any collapsed article to expand it. The expanded view includes: * A **short summary** of the article content * A **direct link** to open the full article in your knowledge base This lets you verify the relevance of a source or share it directly with the user, all from within the same response view. *** ### Why This Matters Surfacing KB articles alongside agent responses means: * Users get supporting documentation immediately, reducing the need for follow-up questions. * Support agents can verify the sources behind a response in a single click. * Teams can identify gaps in their knowledge base when the ranked results are consistently off-topic or unhelpful. *** ### Prerequisites Before the Service Desk Agent can surface KB articles, make sure the following are in place: * A knowledge base is connected and indexed in your Harmony AI Agents workspace. * The Service Desk Agent is enabled for your account. * Articles in your knowledge base are published and accessible to the agent. If your knowledge base connection is not yet configured, refer to the knowledge base integration guide in this documentation space. *** ### Getting Started 1. Open the **Service Desk Agent** from your Harmony AI Agents dashboard. 2. Submit a test request that relates to a topic covered in your knowledge base. 3. Watch the live processing steps appear as the agent works through parsing, searching, scanning, and ranking. 4. Review the response and expand the KB article references to confirm the results are relevant. 5. If the surfaced articles do not match expectations, review your knowledge base content for coverage gaps or update article metadata to improve discoverability. --- # 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 dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.harmony.io/ai-agents/getting-started/service-desk-agent.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. 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.