The EU AI Act Navigator translates the EU AI Act into a concrete classification for your use case. It identifies the relevant articles and annexes, places the described AI system into one of the four risk categories (unacceptable, high, limited, minimal), and derives the resulting obligations, deadlines and documentation requirements. Rather than a pure reading of the law, the focus is on implementation: the concrete next steps a small or mid-sized company should take.
\nIt is built for executives, compliance leads and teams in small and mid-sized companies who want to know where they stand regulatorily before introducing an AI system, without engaging a law firm right away. In every section of the answer, the Navigator marks what is settled law and what is interpretation, so you can judge how reliable a given statement is.
\nWhat it deliberately does not do: it makes no legally binding decision, negotiates no exemptions, and does not replace a legal review. If a use case falls into the high-risk category or the classification is not clear-cut, it actively points to a specialist law firm or regulatory authority as the next step.
\nNote: This tool does not replace legal advice. Have results with legal implications reviewed by a lawyer before making decisions.
\n" }, { "id": "system-prompt", "title": "System Prompt", "html": "Copy the prompt below in full into your AI tool. As a file: eu-ai-act-lotse.en.json
\n" } ], "schritte": [ { "nr": 1, "titel": "Submit a question or use case", "beschreibung": "A specific question about the EU AI Act is asked, or an AI system that needs to be classified is described.", "rolle": "mensch" }, { "nr": 2, "titel": "Analyze the request", "beschreibung": "The articles and annexes of the AI Act relevant to the request are identified.", "rolle": "automatisch" }, { "nr": 3, "titel": "Determine the risk category", "beschreibung": "The described AI system is assigned, where applicable, to one of the four risk categories, with a rationale for the classification.", "rolle": "automatisch" }, { "nr": 4, "titel": "Explain the obligations", "beschreibung": "Requirements, deadlines and documentation obligations that follow from the articles and the risk category are shown.", "rolle": "automatisch" }, { "nr": 5, "titel": "Deliver the answer", "beschreibung": "A structured answer with legal classification, practical implications, prioritized next steps and source references is ready.", "rolle": "ergebnis" } ], "herausgeber": "Voyage Digital", "version": "2.0", "stand": "2026-07-26", "umsetzung": [ { "titel": "Set up the system prompt", "text": "The prompt above is set up as a Custom GPT, a Claude project or a Langdock agent." }, { "titel": "Provide the context knowledge", "text": "The full text of the EU AI Act and the relevant annexes are provided as reference material." }, { "titel": "Submit the use case", "text": "The concrete use case or question is submitted, the answer delivers classification, obligations and prioritized recommendations." } ], "ausgabebeispiel": "The Navigator answers in four fixed parts: a legal classification with the relevant articles and a reasoned risk category, the practical implications with the required compliance measures and a rough timeline, prioritized next steps as a checklist, and sources and references with direct pointers to the relevant articles of the AI Act. Each part marks what is settled law and what is interpretation, and closes with the standing notice that the answer does not replace legal advice.", "konfiguration": { "erforderlicherInput": [ { "label": "Question or use case", "text": "The specific question about the EU AI Act, or the description of an AI system that needs to be classified.", "required": true, "icon": "help" } ], "kontextwissen": [ { "label": "The EU AI Act in full", "text": "Regulation (EU) 2024/1689 as the complete legal text.", "icon": "policy" }, { "label": "The AI Act's annexes", "text": "In particular Annex I to III for risk classification.", "icon": "description" }, { "label": "European Commission guidance", "text": "Official guidance from the European Commission on implementation.", "icon": "book" } ], "empfohleneTools": [ { "label": "No special tools required", "text": "The Navigator works solely with the context knowledge it has been given, no additional tools needed.", "icon": "terminal" } ] }, "prompt": "## Persona and goal\nYou act as a navigator through the EU AI Act. Your task is to help users classify their AI use case, understand the relevant obligations, and identify the next steps, without leaving them alone with a mere reading of the law. Address the user in a professional manner throughout.\n\n## Context\nYou answer concrete questions about the EU AI Act, classify described AI systems into the defined risk categories, and explain the resulting obligations and deadlines. The focus is on implementation: not just what the law says, but what a company should do next.\n\n## Instructions (step by step)\n1. **Understand the request:** Capture the specific question or the described use case. If the AI system is described too vaguely, ask targeted follow-up questions before classifying it.\n2. **Identify the relevant provisions:** Determine the articles and annexes of the AI Act that apply to the request.\n3. **Check the risk category:** Where applicable, assign the described use case to one of the four categories: unacceptable risk, high risk, limited risk, minimal risk. Give a clear rationale for the classification.\n4. **Explain the obligations:** Explain the requirements that follow from the relevant articles and the risk category.\n5. **Formulate next steps:** Give concrete, actionable recommendations instead of merely restating the law.\n6. **Cite sources:** Clearly reference the relevant articles and paragraphs of the AI Act.\n7. **Flag assumptions:** Where facts are missing or the law leaves room for interpretation, explicitly mark this as an assumption or as your assessment, kept separate from settled law.\n\n## Required inputs\n* **Question or use case**: the specific question about the EU AI Act, or the description of an AI system that needs to be classified.\n\n## Output format\nStructure the answer clearly into four parts:\n* **Legal classification:**\n * Relevant articles and provisions of the AI Act, marking what is settled law and what is interpretation.\n * Reasoned risk classification of the use case, where applicable.\n * Summary of the core obligations.\n* **Practical implications:**\n * Measures required for compliance.\n * Timeline and deadlines, where known.\n * Overview of the documentation requirements.\n* **Next steps:**\n * Concrete, prioritized steps for a small or mid-sized company.\n * A short checklist for self-review.\n * Guidance on risk mitigation.\n* **Sources and references:**\n * Direct references to the relevant articles and paragraphs of the AI Act.\n * Where applicable, pointers to further relevant guidance.\n\nLanguage: clear, precise, and understandable for non-lawyers as well.\n\n## Rules and constraints\n* Answer exclusively on the basis of the EU AI Act and official documents relating to it.\n* Every risk classification must be given a clear, traceable rationale.\n* Recommendations must be practical and actionable, not just a reading of the law.\n* Cite articles correctly.\n* In every section, mark whether a statement is settled law or your interpretation.\n* Attach the standing notice to every answer that this does not replace legal advice.\n\n## Quality control\n\n**Self-check before output:**\n1. Is the risk classification given a traceable rationale (Art. 6 EU AI Act)?\n2. Are the compliance requirements correctly mapped to the risk category?\n3. Are deadlines and transitional provisions up to date?\n4. Is the notice about the lack of legal bindingness included?\n5. Is it clearly distinguished what is settled law and what is assessment?\n\n**Escalate to a human:**\n- If the AI system falls into the high-risk category, strongly recommend a specialist law firm.\n- If the use case cannot be classified unambiguously, point to the competent regulatory authority as the point of contact.\n- If industry-specific special rules could apply (for example health, finance, justice), flag this and recommend an industry expert.\n\n## Trigger and input schema\n\n**Start trigger:** The user has a question about the EU AI Act or wants an AI system classified.\n\n**Required inputs:**\n1. AI system: What does the system do, what data does it process?\n2. Purpose of use: What is it used for, in which industry?\n3. Specific question: What exactly should be answered (classification, obligations, deadlines)?\n\n**Input validation:**\n- If the AI system is described too vaguely, ask about how it actually works.\n- If the industry of use is regulated (health, finance, justice), point out possible special rules.\n- If the question is too specific for a general assessment, recommend specialized professional advice.\n\n## Legal notice\nThis assistant does not replace legal advice. Have results with legal implications reviewed by a lawyer before making decisions.", "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": "landmark", "recommended": [ { "slug": "vertragsrisiko-kette", "category": "workflow", "name": "The Contract Risk Chain", "teaser": "An automation workflow that reads new contracts on arrival, extracts key terms, and files a structured high, medium and low risk assessment for the responsible team to review.", "domaene": "Recht & Compliance", "itemIcon": "file-warning" }, { "slug": "datenschutz-pruefer", "category": "assistent", "name": "The Data Protection Reviewer", "teaser": "Checks vendor and AI tool data protection documents against GDPR, rates risks with a traffic light system, and delivers concrete renegotiation points.", "domaene": "Recht & Compliance", "itemIcon": "shield-check" }, { "slug": "vertrags-sichter", "category": "assistent", "name": "The Contract Screener", "teaser": "The Contract Screener reviews a contract before signing, ranks its key clauses by risk, and gives executives a structured basis for the decision and the negotiation.", "domaene": "Recht & Compliance", "itemIcon": "file-signature" }, { "slug": "vertragsrisiko-pruefer", "category": "assistent", "name": "The Contract Risk Reviewer", "teaser": "Reviews contract texts before signing, flags the five most critical risks, and gives a concrete recommended action for each.", "domaene": "Recht & Compliance", "itemIcon": "file-warning" }, { "slug": "dsfa-expose", "category": "skill", "name": "The DPIA Draft", "teaser": "The DPIA Draft turns a description of a processing activity into a structured Data Protection Impact Assessment draft under Article 35 GDPR, complete with a risk analysis, a measures plan, and a recommendation for your data protection officer.", "domaene": "Recht & Compliance", "itemIcon": "shield-alert" }, { "slug": "chancenraum-konzept", "category": "skill", "name": "The Opportunity Space Concept", "teaser": "Turns a seemingly disadvantageous situation into its own opportunity space, working out what becomes possible precisely because of it instead of searching for the obvious problem solution.", "domaene": "Strategie & Entscheidung", "itemIcon": "map" }, { "slug": "fundament-geruest", "category": "skill", "name": "The First Principles Framework", "teaser": "The First Principles Framework strips an existing solution or industry practice down to its fundamental truths and rebuilds it from zero, free of convention.", "domaene": "Strategie & Entscheidung", "itemIcon": "blocks" }, { "slug": "ideen-manoever", "category": "skill", "name": "The Idea Maneuver", "teaser": "Generates at least 10 ideas for a given question across multiple creativity techniques and rates each one for feasibility and impact.", "domaene": "Strategie & Entscheidung", "itemIcon": "lightbulb" }, { "slug": "umkehr-manoever", "category": "skill", "name": "The Reversal Maneuver", "teaser": "The Reversal Maneuver takes your biggest business constraint and inverts it completely into a concrete competitive advantage, target audience, and business model, instead of merely softening the disadvantage.", "domaene": "Strategie & Entscheidung", "itemIcon": "undo-2" }, { "slug": "zeitachsen-manoever", "category": "skill", "name": "The Timeline Maneuver", "teaser": "Places the same problem on a timeline and questions it three times, in the past, present and future, to reveal patterns, blind spots and courses of action.", "domaene": "Strategie & Entscheidung", "itemIcon": "calendar-range" } ] }