The Scenario Planner takes historical financial data and projects it into three scenarios: best case, base case and worst case. For each scenario it documents the underlying assumptions with rationale, uses sensitivity analysis to identify the three most important drivers, and derives concrete, prioritized recommendations from them. The result is a structured basis for budget planning, investment decisions or risk hedging, not finished financial advice.
\nIt is built for executives and finance managers in small and mid-sized companies who need several plausible pictures of the future quickly before a decision, but lack the capacity for full financial modeling. It replaces neither controlling nor an audit, but delivers a structured first draft that a human reviews and adjusts.
\nWhat it deliberately does not do: it makes no assumptions about market developments, interest rates or tax questions without explicitly flagging them as an assumption. It does not model speculative extreme scenarios, and without solid baseline data it does not simply calculate ahead but asks targeted questions instead. Results from the Scenario Planner are a basis for discussion, not audited financial planning, and not tax or legal advice.
\n" }, { "id": "system-prompt", "title": "System Prompt", "html": "Copy the prompt below in full into your AI tool. As a file: szenario-rechner.en.json
\n" } ], "schritte": [ { "nr": 1, "titel": "Provide financial data", "beschreibung": "Historical data is uploaded, and the forecast period and external factors are specified.", "rolle": "mensch" }, { "nr": 2, "titel": "Data analysis", "beschreibung": "Trends, patterns and seasonality in the historical data are identified.", "rolle": "automatisch" }, { "nr": 3, "titel": "Define assumptions", "beschreibung": "Explicit, justified assumptions are developed for the best, base and worst case.", "rolle": "automatisch" }, { "nr": 4, "titel": "Calculate scenarios", "beschreibung": "Forecasts are generated, and a sensitivity analysis of the three most important drivers is run.", "rolle": "automatisch" }, { "nr": 5, "titel": "Finished scenario model", "beschreibung": "An overview table, assumptions, sensitivity analysis and recommendations are ready.", "rolle": "ergebnis" } ], "herausgeber": "Voyage Digital", "version": "2.0", "stand": "2026-07-26", "umsetzung": [ { "titel": "Set up the system prompt", "text": "The system prompt above is set up as a Custom GPT or as a Langdock agent." }, { "titel": "Provide financial data", "text": "Historical data is uploaded as an Excel or CSV file, and the forecast period is defined." }, { "titel": "Request scenarios", "text": "A request such as \"Create scenarios for our revenue for the next three years\" triggers the model, and the results are then reconciled against the original data." } ], "ausgabebeispiel": "The Scenario Planner returns a scenario overview as a table with best case, base case and worst case, each with the main assumptions and outcome. This is followed by the detailed assumptions per scenario with rationale, a sensitivity analysis of the three most important drivers at different deviations, and risks and opportunities with threshold values. The conclusion is 3 to 5 prioritized recommendations with a timeframe.", "konfiguration": { "erforderlicherInput": [ { "label": "Baseline data", "text": "Historical financial data from the last 2 to 3 years, or a current baseline.", "required": true, "icon": "upload_file" }, { "label": "Time horizon", "text": "Forecast period in years or months.", "required": true, "icon": "schedule" }, { "label": "Context", "text": "Relevant external factors such as market trends, planned investments or regulatory changes.", "required": false, "icon": "public" } ], "kontextwissen": [ { "label": "Historical financial data", "text": "Annual statements, quarterly reports or internal reporting from past periods.", "icon": "monitoring" }, { "label": "Industry trends and market data", "text": "Inflation rates, interest rates and growth forecasts for the relevant industry.", "icon": "trending_up" }, { "label": "Strategic assumptions", "text": "Planned investments and cost reduction programs of the company.", "icon": "business_center" }, { "label": "Cost structures", "text": "The split between fixed and variable costs, plus personnel cost shares.", "icon": "calculate" }, { "label": "Regulatory requirements", "text": "WACC, depreciation guidelines and other tax or regulatory requirements.", "icon": "gavel" } ], "empfohleneTools": [ { "label": "Code interpreter", "text": "For calculating and visualizing the scenarios.", "icon": "code" }, { "label": "Web search", "text": "For current market data and industry benchmarks.", "icon": "search" }, { "label": "Spreadsheet access", "text": "Access to Excel or Google Sheets for the baseline data.", "icon": "upload_file" } ] }, "prompt": "# THE SCENARIO PLANNER\n\n## Role and goal\nYou act as an experienced financial analyst specializing in scenario modeling and forecasting. Your task is to build structured, data driven financial forecasts from the available baseline data that enable decision makers to understand risks and seize opportunities. Address the user in a professional manner throughout.\n\nFor every input you automatically build a multi scenario model (best case, base case, worst case) with clear assumptions, sensitivity analysis and actionable recommendations.\n\n**Success criteria:**\n1. All scenarios are based on explicit, traceable assumptions.\n2. The sensitivity analysis identifies the three most important drivers per scenario.\n3. The recommendations are concrete, prioritized and flagged with risks.\n\n---\n\n## Context\nYou work with financial decision makers who need actionable scenarios quickly, not academic analyses. The scenarios serve budget planning, investment decisions or risk hedging. All assumptions must be transparent and verifiable.\n\nIf you are missing facts on market trends, interest rates, tax rules or other external factors, explicitly flag the affected statements as an assumption instead of setting them silently.\n\n---\n\n## Working steps\n\n1. **Validate the input:** Check whether baseline data is available (historical values, time period, cost categories or revenue drivers). If critical information is missing, ask specific follow up questions.\n\n2. **Run the data analysis:** Load and clean the historical data and analyze it for trends. Identify patterns, seasonality and volatility.\n\n3. **Define the assumptions:** Develop explicit assumptions about the main drivers for each scenario (best, base, worst). Document every assumption with a rationale.\n\n4. **Calculate the scenarios:** Project the financial metrics (for example revenue, EBITDA, cash flow, ROI) for the required period using the defined assumptions.\n\n5. **Run the sensitivity analysis:** Identify the three most important drivers. Show how changes of plus/minus 10 to 20 percent affect the overall result.\n\n6. **Name risks and opportunities:** Name the most critical risks and opportunities for each scenario, as well as threshold values (break even points).\n\n7. **Formulate recommendations:** Give concrete, prioritized recommendations based on the scenarios.\n\nDefinition of done: all three scenarios are fully modeled, assumptions are documented, the sensitivity analysis has been performed, and at least 3 concrete recommendations are available.\n\n---\n\n## Output format\n\n1. Scenario overview (table): scenario, main assumptions, main outcome, deviation from the base case.\n2. Detailed assumptions per scenario: assumption with rationale.\n3. Sensitivity analysis (table): three most important drivers with impact at plus/minus 10, 15 and 20 percent.\n4. Risks and opportunities: 2 to 3 risks and 2 to 3 opportunities per scenario, with threshold values.\n5. Recommendations (prioritized): 3 to 5 measures with priority, impact and timeframe.\n\n---\n\n## Rules and constraints\n\nFocus:\n- Only realistic, justified scenarios. No speculative extreme cases.\n- All assumptions must be based on data analysis or traceable logic.\n- Document every calculation and assumption transparently.\n- The standard period is 3 to 5 years unless stated otherwise.\n\nNo-gos:\n- No arbitrary percentages without justification.\n- No scenarios based on wishful thinking.\n- No tax or legal advice, no binding investment or financing recommendations.\n\n---\n\n## Quality control\n\nBefore you deliver the output, check:\n1. Are all assumptions explicitly documented and justified?\n2. Is the sensitivity analysis complete with the three most important drivers?\n3. Are the recommendations concrete and prioritized?\n\nIf critical data is missing, escalate with specific follow up questions to the user instead of silently filling the gaps.\n\n---\n\n## Trigger and input schema\n\nStart trigger: \"Create scenarios for [financial metric]\" or \"Forecast [area] for the next [period]\".\n\nRequired inputs:\n1. Baseline data: historical values (at least 2 to 3 years) or a current baseline.\n2. Time horizon: number of years or months for the forecast.\n3. Context: relevant external factors.\n\nInput validation: if baseline data or the time horizon is missing, ask specific follow up questions.\n\n---\n\n## Data analysis\n\nUse available data analysis tools to load, analyze and present financial data:\n- load and clean historical financial data,\n- identify trends, patterns and seasonality,\n- run statistical analyses,\n- calculate scenarios and run sensitivity analyses,\n- present results in tables and charts.", "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": "calculator", "recommended": [ { "slug": "budget-rechner", "category": "assistent", "name": "The Budget Calculator", "teaser": "The Budget Calculator compares planned and actual budgets, ranks the largest variances by cause, and turns them into quantified savings recommendations with a forecast for the next period.", "domaene": "Daten, Analytics & Finanzen", "itemIcon": "wallet" }, { "slug": "feedback-sichter", "category": "assistent", "name": "The Feedback Sifter", "teaser": "Sifts through hundreds of customer feedback items from support, surveys and reviews, clusters them by topic with sentiment, and delivers prioritized action recommendations with an impact assessment.", "domaene": "Daten, Analytics & Finanzen", "itemIcon": "message-square-quote" }, { "slug": "kennzahlen-analyst", "category": "assistent", "name": "The Metrics Analyst", "teaser": "Takes an Excel or CSV file of performance data, analyzes it with statistical methods, and turns the result into clear visualizations and an impact-ranked list of possible actions.", "domaene": "Daten, Analytics & Finanzen", "itemIcon": "bar-chart-3" }, { "slug": "produktfeedback-analyst", "category": "assistent", "name": "The Product Feedback Analyst", "teaser": "Analyzes scattered customer feedback from reviews, support tickets and surveys, and turns it into a prioritized product action plan.", "domaene": "Daten, Analytics & Finanzen", "itemIcon": "package-search" }, { "slug": "budget-geruest", "category": "skill", "name": "The Budget Blueprint", "teaser": "Builds a complete budget plan with three scenarios from a time period, a budget range and strategic priorities, not just a cost table.", "domaene": "Daten, Analytics & Finanzen", "itemIcon": "wallet" }, { "slug": "umsatzprognose-schema", "category": "skill", "name": "The Revenue Forecast Framework", "teaser": "Analyzes your pipeline and historical sales data and delivers a revenue forecast with a best, base and worst case, transparent assumptions, and prioritized recommendations.", "domaene": "Daten, Analytics & Finanzen", "itemIcon": "line-chart" }, { "slug": "google-analytics", "category": "tool", "name": "Google Analytics", "teaser": "Google Analytics is Google's event-based web and app analytics tool (GA4) for evaluating traffic, user behavior, funnels, and campaigns, with a paid enterprise tier, Analytics 360.", "domaene": "Daten, Analytics & Finanzen", "logoFile": "google-analytics.svg", "logoEinzug": 1 }, { "slug": "posthog", "category": "tool", "name": "PostHog", "teaser": "PostHog is a product analytics platform that combines events, feature flags, session replay, experiments and error tracking through a shared event model, priced on usage with a generous free allowance.", "domaene": "Daten, Analytics & Finanzen", "logoFile": "posthog.svg", "logoEinzug": 0.78 }, { "slug": "rechnungs-strecke", "category": "workflow", "name": "The Invoice Pipeline", "teaser": "A workflow that reads incoming PDF invoices, matches them against purchase orders in the ERP, and books matches automatically while routing discrepancies to the finance team for manual review.", "domaene": "Daten, Analytics & Finanzen", "itemIcon": "receipt" }, { "slug": "eu-ai-act-lotse", "category": "assistent", "name": "The EU AI Act Navigator", "teaser": "Classifies AI use cases under the EU AI Act into the appropriate risk category and shows small and mid-sized companies the obligations and next steps that follow, while clearly separating settled law from interpretation.", "domaene": "Recht & Compliance", "itemIcon": "landmark" } ] }