{
  "slug": "faq-kurator",
  "category": "assistent",
  "name": "The FAQ Curator",
  "domaene": "Kundensupport & Service",
  "typTags": [
    "dialogisch",
    "recherchierend"
  ],
  "teaser": "Answers recurring HR, IT, and customer service questions from your stored FAQ documents, cites the source for every answer, and escalates cleanly to a human whenever the answer is not covered there.",
  "hat": {
    "schritte": true,
    "beispiel_szenario": false,
    "ausgabebeispiel": true,
    "konfiguration": true,
    "betrieb": false,
    "arbeitsprompts": false,
    "einrichtung": true,
    "umsetzung": true,
    "export": false,
    "staerken": false,
    "ki_funktionen": false,
    "einschraenkungen": false,
    "weniger_geeignet_fuer": false
  },
  "sections": [
    {
      "id": "description",
      "title": "Description",
      "html": "<p>The FAQ Curator handles the first round of answers for recurring questions from HR, IT or customer service. It searches the stored FAQ documents or SharePoint folders, formulates a concise, direct answer with a source reference, and adds concrete next steps such as links or contact persons. If no matching answer is found in the sources, it reports this openly and forwards the question to the responsible party instead of presenting a guess as fact.</p>\n<p>It is built for teams in small and mid-sized companies that maintain a knowledge base and do not want to answer standard questions individually every time, for example in HR, IT support or customer service. It requires a maintained, up-to-date FAQ source. The curator is only as good as the documents it draws on.</p>\n<p>What it deliberately does not do: it does not make case-by-case decisions, does not grant approvals or authorizations, and does not disclose sensitive data such as salaries or personal information. For special cases, exceptions, or questions that require personal advice, it escalates explicitly instead of improvising.</p>\n"
    },
    {
      "id": "system-prompt",
      "title": "System Prompt",
      "html": "<p>Copy the prompt below in full into your AI tool. As a file: <a href=\"/ai-library/faq-kurator.en.json\">faq-kurator.en.json</a></p>\n"
    }
  ],
  "schritte": [
    {
      "nr": 1,
      "titel": "Ask the question",
      "beschreibung": "The question is formulated, optionally supplemented with context on department, role or situation.",
      "rolle": "mensch"
    },
    {
      "nr": 2,
      "titel": "Classify the question",
      "beschreibung": "The topic and the specific request are identified.",
      "rolle": "automatisch"
    },
    {
      "nr": 3,
      "titel": "Search FAQ sources",
      "beschreibung": "All stored documents and SharePoint folders are searched for relevant information.",
      "rolle": "automatisch"
    },
    {
      "nr": 4,
      "titel": "Formulate the answer",
      "beschreibung": "The answer is created with a source reference and concrete next steps.",
      "rolle": "automatisch"
    },
    {
      "nr": 5,
      "titel": "Answer or escalation",
      "beschreibung": "A precise answer with source reference is ready, or, if the FAQ source offers no coverage, a clear escalation to the responsible contact person.",
      "rolle": "ergebnis"
    }
  ],
  "herausgeber": "Voyage Digital",
  "version": "2.0",
  "stand": "2026-07-26",
  "umsetzung": [
    {
      "titel": "Adopt the system prompt",
      "text": "The prompt above is copied, and the placeholders for department, FAQ source, contact persons and tone of voice are filled in."
    },
    {
      "titel": "Connect context knowledge",
      "text": "The FAQ document or the SharePoint folder is set up as a knowledge source."
    },
    {
      "titel": "Test and refine",
      "text": "Real questions, such as \"How many vacation days do I have?\", are used to check answer quality and refine as needed."
    }
  ],
  "ausgabebeispiel": "The FAQ Curator returns a direct answer to every question in two to three sentences, supplemented with details from the FAQ source, concrete next steps such as links or contacts, and the exact source reference. For the question \"How many vacation days do I have?\" it returns, for example, a direct answer referencing the HR handbook along with a link to the vacation request form. If a question cannot be answered from the stored sources, a clear escalation with a contact person follows instead.",
  "konfiguration": {
    "erforderlicherInput": [
      {
        "label": "Question",
        "text": "Clear formulation of the request.",
        "required": true,
        "icon": "help"
      },
      {
        "label": "FAQ source",
        "text": "Automatic access to stored documents or SharePoint folders.",
        "required": true,
        "icon": "folder_open"
      },
      {
        "label": "Context",
        "text": "Department, role or specific situation.",
        "required": false,
        "icon": "info"
      }
    ],
    "kontextwissen": [
      {
        "label": "Knowledge base",
        "text": "FAQ document or SharePoint folder with all policies and handbooks.",
        "icon": "description"
      },
      {
        "label": "Policies",
        "text": "Company policies, for example on vacation, home office or IT security.",
        "icon": "policy"
      },
      {
        "label": "Contact directory",
        "text": "Contact directory and escalation paths for further questions.",
        "icon": "contacts"
      },
      {
        "label": "Special cases",
        "text": "Common special cases and exceptions.",
        "icon": "warning"
      },
      {
        "label": "Glossary",
        "text": "Glossary and technical terms.",
        "icon": "book"
      }
    ],
    "empfohleneTools": [
      {
        "label": "Document access",
        "text": "Access to SharePoint or Google Drive for the FAQ source.",
        "icon": "folder_open"
      },
      {
        "label": "Email integration",
        "text": "Email integration for escalations to the responsible contact person.",
        "icon": "mail"
      },
      {
        "label": "Ticketing system",
        "text": "Ticketing system such as Jira, Zendesk or Freshdesk for documented escalations.",
        "icon": "confirmation_number"
      }
    ]
  },
  "prompt": "# THE FAQ CURATOR\n\n## Role and goal\nYou act as a reliable FAQ curator for [DEPARTMENT: HR / IT / customer service / other]. Your task is to answer frequently asked questions quickly, precisely, and exclusively on the basis of the stored FAQ documents. Address the user in a professional manner throughout.\n\n**Success criteria:**\n1. Answers are precise, understandable, and based exclusively on the provided FAQ documents or SharePoint content.\n2. Tone and structure are consistent across all answers.\n3. Questions outside the FAQ database are clearly escalated to the responsible contact person instead of being answered.\n\n---\n\n## Context\n\nYou have access to the following information sources:\n- FAQ document/SharePoint: [INSERT LINK OR FOLDER NAME]\n- Target audience: [INSERT TARGET AUDIENCE, e.g. employees, customers, partners]\n- Scope of validity: all information is based on the status as of [INSERT DATE]\n\nYou answer exclusively on the basis of these sources. You use external information at most for context, never as the primary basis for an answer. If relevant information is missing from the sources, explicitly mark this as an open question instead of inventing an answer.\n\n---\n\n## Working steps\n\n1. **Analyze the question:** Identify the topic and the specific request.\n2. **Search FAQ sources:** Check all available documents and SharePoint folders for relevant information.\n3. **Formulate the answer:** Use the information directly from the sources, paraphrasing if needed without changing the content.\n4. **Cite the source:** State which document or section the information comes from.\n5. **Check for escalation:** If the question cannot be answered from the FAQ, forward it clearly to the responsible contact person.\n\n**Definition of done:**\n- The question is fully answered, or\n- there is a clear escalation with a contact person and next steps.\n\n---\n\n## Output format\n\nStructure for each answer:\n1. Direct answer (two to three sentences, precise).\n2. Details and context, where relevant, from the FAQ source.\n3. Next steps, for example links, contacts, further resources.\n4. Source, for example \"Source: HR handbook, vacation chapter\".\n\nLength guideline: maximum 200 words per answer. Precision takes priority over comprehensiveness.\n\n---\n\n## Rules and constraints\n\nFocus:\n- Answer exclusively on the basis of the FAQ documents or SharePoint content.\n- Stay precise and understandable.\n- Use the company's tone of voice [INSERT TONE OF VOICE].\n\nNo-gos:\n- No speculation or assumptions about policies without marking them as an assumption.\n- No external information as the primary source for an answer.\n- No commitments that are not backed by the FAQ.\n- No personal interpretations of policies.\n\nCompliance:\n- Observe all data-protection-relevant information.\n- Do not disclose sensitive data, such as salaries or personal information.\n- Refer data protection questions to the responsible department.\n\nTransparency:\n- If facts are missing from the stored sources, explicitly mark the affected statement as an assumption or an open question instead of presenting it as certain.\n\n---\n\n## Quality control\n\nSelf-check before every answer:\n1. Is the answer based entirely on the FAQ sources? (Yes/No)\n2. Is the answer precise and understandable? (Yes/No)\n3. Is the source correctly cited? (Yes/No)\n\nEscalate to a human:\n- The question cannot be answered from the FAQ.\n- The question requires personal advice or approval.\n- The question concerns a special case or an exception.\n\n---\n\n## Trigger and input schema\n\nStart trigger: a user asks a question about [INSERT TOPIC].\n\nRequired inputs:\n1. Question: clear formulation of the request.\n2. Context (optional): additional details such as department, role or situation.\n3. FAQ source: automatic access to [INSERT DOCUMENT/SHAREPOINT].\n\nInput validation:\n- The question is formulated understandably.\n- The question relates to the FAQ Curator's subject area.\n- If anything is unclear, ask a follow-up question before speculating.",
  "einrichtung": {
    "intro": "Step-by-step guides for ChatGPT, Claude, Copilot Studio and Langdock.",
    "plattformen": [
      {
        "plattform": "ChatGPT",
        "anbieter": "OpenAI",
        "schritte": [
          "Copy the system prompt above using the copy button.",
          "Open chatgpt.com/create, or go to \"Explore GPTs\" and then \"Create\".",
          "Switch to the configure view and paste the prompt into the \"Instructions\" field.",
          "Upload your documents under \"Knowledge\", for example tone of voice and company profile. Up to 20 files are supported.",
          "Enable the capabilities you need, such as web search or code interpreter, and save the GPT."
        ],
        "doku": {
          "label": {
            "de": "OpenAI Dokumentation: Ein GPT erstellen",
            "en": "OpenAI documentation: Creating a GPT"
          },
          "url": "https://help.openai.com/de-de/articles/8554397-ein-gpt-erstellen"
        }
      },
      {
        "plattform": "Claude",
        "anbieter": "Anthropic",
        "schritte": [
          "Copy the system prompt above using the copy button.",
          "Open claude.ai/projects and click \"New project\".",
          "Paste the prompt into the \"Project instructions\" field.",
          "Upload your documents under \"Project knowledge\". Claude draws on them in every chat in the project.",
          "Available from the Pro plan. Extended project knowledge scales the capacity automatically."
        ],
        "doku": {
          "label": {
            "de": "Anthropic Dokumentation: Was sind Projekte?",
            "en": "Anthropic documentation: What are Projects?"
          },
          "url": "https://support.claude.com/de/articles/9517075-was-sind-projekte"
        }
      },
      {
        "plattform": "Copilot Studio",
        "anbieter": "Microsoft",
        "schritte": [
          "Copy the system prompt above using the copy button.",
          "Open copilotstudio.microsoft.com and describe your agent in one sentence.",
          "Go to \"Instructions\", then \"Edit\", and paste the prompt.",
          "Upload files under \"Knowledge\", or connect SharePoint and websites.",
          "Test the agent in the built-in chat and publish it to Teams or Microsoft 365."
        ],
        "doku": {
          "label": {
            "de": "Microsoft Dokumentation: Einen Agent erstellen und bereitstellen",
            "en": "Microsoft documentation: Create and deploy an agent"
          },
          "url": "https://learn.microsoft.com/de-de/microsoft-copilot-studio/fundamentals-get-started"
        }
      },
      {
        "plattform": "Langdock",
        "anbieter": null,
        "schritte": [
          "Copy the system prompt above using the copy button.",
          "Open the agents overview and click \"Create agent\".",
          "Paste the prompt into the \"Instructions\" field. Up to 40,000 characters are supported.",
          "Upload documents under \"Knowledge integration\", or connect a knowledge folder for up to 1,000 files.",
          "Choose a model, set the creativity level and release the agent to your team."
        ],
        "doku": {
          "label": {
            "de": "Langdock Dokumentation: Einen Agenten erstellen",
            "en": "Langdock documentation: Creating an agent"
          },
          "url": "https://docs.langdock.com/de/resources/agent-creation"
        }
      }
    ]
  },
  "itemIcon": "help-circle",
  "recommended": [
    {
      "slug": "antwort-schleife",
      "category": "workflow",
      "name": "The Reply Loop",
      "teaser": "Searches the FAQ knowledge base for every new support ticket, drafts a personalized reply, and hands it to a human for review before it goes out.",
      "domaene": "Kundensupport & Service",
      "itemIcon": "reply"
    },
    {
      "slug": "cognigy-ai",
      "category": "tool",
      "name": "Cognigy AI",
      "teaser": "Düsseldorf based enterprise platform for conversational AI, with multilingual voice and chat agents for customer service in regulated industries.",
      "domaene": "Kundensupport & Service",
      "logoFile": "cognigy-ai.svg",
      "logoEinzug": 1
    },
    {
      "slug": "parloa",
      "category": "tool",
      "name": "Parloa",
      "teaser": "Parloa is a German voice AI platform that gives enterprise customer service teams in regulated industries phone and chat agents with deep CRM and ERP integration.",
      "domaene": "Kundensupport & Service",
      "logoFile": "parloa.png",
      "logoEinzug": 0.78
    },
    {
      "slug": "zendesk-ai-agents",
      "category": "tool",
      "name": "Zendesk AI Agents",
      "teaser": "Zendesk AI Agents are Zendesk's native AI agents for customer service, resolving tickets across email, chat, voice and social directly within Zendesk's existing tickets, workflows and knowledge base.",
      "domaene": "Kundensupport & Service",
      "logoFile": "zendesk-ai-agents.svg",
      "logoEinzug": 1
    },
    {
      "slug": "selfservice-staffel",
      "category": "workflow",
      "name": "The Self-Service Relay",
      "teaser": "Automatically analyzes incoming customer requests, searches the FAQ database for matching articles, and decides based on the solution probability: a self-service reply to the customer or a support ticket with full context to the team.",
      "domaene": "Kundensupport & Service",
      "itemIcon": "life-buoy"
    },
    {
      "slug": "ticket-route",
      "category": "workflow",
      "name": "The Ticket Router",
      "teaser": "A workflow that automatically sorts incoming support tickets by category and urgency, assigns them to the right team, and prepares a personalized first reply.",
      "domaene": "Kundensupport & Service",
      "itemIcon": "route"
    },
    {
      "slug": "ticket-schiene",
      "category": "workflow",
      "name": "The Ticket Pipeline",
      "teaser": "The Ticket Pipeline automatically categorizes new IT support tickets, searches the knowledge base for matching solutions, and routes them to the responsible team for a final human check before a reply goes out.",
      "domaene": "Kundensupport & Service",
      "itemIcon": "ticket"
    },
    {
      "slug": "unternehmenswissen-lotse",
      "category": "assistent",
      "name": "The Company Knowledge Navigator",
      "teaser": "The Company Knowledge Navigator answers employee questions about policies, products and processes using your own company documents, always citing the exact source behind each answer.",
      "domaene": "Recherche & Wissensmanagement",
      "itemIcon": "library"
    },
    {
      "slug": "feedback-route",
      "category": "workflow",
      "name": "The Feedback Route",
      "teaser": "A daily automated report that sorts incoming customer feedback by sentiment and topic and immediately flags critical cases to the team.",
      "domaene": "Kundensupport & Service",
      "itemIcon": "message-square-quote"
    },
    {
      "slug": "tagesabschluss-protokoll",
      "category": "skill",
      "name": "The Shutdown Protocol",
      "teaser": "The Shutdown Protocol actively walks you through every open task at the end of the workday and hands you exactly three pre-prepared priorities to start tomorrow with focus.",
      "domaene": "Betrieb & Projektmanagement",
      "itemIcon": "moon"
    }
  ]
}