Create your own AI dashboards in accounting

Fundamentals & Core Processes in Finance Dashboards

1. Introduction & Architecture

• Why AI in accounting? Benefits and limitations.
• Claude as a "finance co-pilot": functions, handling common files (CSV/Excel), and structured results.
• Traditional BI tools versus AI-powered, fast way to dashboards.

2. Prompting in a financial context

• Prompt framework: Target – Data context – Format – Validation – Follow-up task.
• Prompt patterns: Extract – Transform – Visualize – Explain.
• Anti-patterns: unclear objectives, lack of verification mechanisms, inconsistent units of measurement.

"KPI Starter" workshop

• Input: Sample file (sales – cost of goods sold – operating expenses – depreciation – inventories – receivables – liabilities).
• Output: KPI table (EBIT, EBITDA, net margin, working capital, cash conversion cycle, quick ratio).
• Accompanying: Formula glossary, plausibility check with verification prompts.

Mini Dashboard Workshop

• Creation of 3 to 4 charts (e.g., sales trend, cost structure, EBIT margin, cash flow overview).
• Management summary (≤150 words) with three key findings and a recommendation for action.

3. Data quality & data management

• Handling missing values and outliers, normalization, logic for date and measurement units.
• Documentation: sources, assumptions, calculation samples, versioning.

Deep dive and advanced applications

4. Working with open financial data sets

• Sources: World Bank, OECD, FRED (Federal Reserve Economic Data), IMF (e.g., CPI, interest rates, GDP growth), optional key figures from the US Securities and Exchange Commission.
• Methods: Harmonization of frequencies (monthly/quarterly), indexing (base year), calculation of annual and monthly changes.

Workshop: Macro-Finance Dashboard

• Comparison of countries (e.g., Switzerland, Germany, USA).
• Creation of 5 to 6 visuals including KPI headers (current value, trend, traffic light logic).
• 200-word briefing with uncertainties, revisions, and source references.

Workshop: "Scenario and Sensitivity Analyses"

• Development of base/optimistic/pessimistic scenarios.
• Calculation of the effects on EBITDA, operating cash flow, interest coverage ratio.
• Creation of sensitivity matrices, delta charts, recommendations for action (risks and countermeasures).

5. Automated reporting and alerts

• Recurring prompts, monthly templates, thresholds/notifications.
• Governance: Prompt versioning, KPI catalog, source references.

6. Best practices & case studies

• Success factors for AI implementation in accounting.
• Quick wins vs. scaling: from prototype to departmental solution.

7. Ethical and legal aspects

• Data protection, client protection, confidentiality.
• Traceability (explainability), responsibilities.

In our seminars, we explicitly address the data protection requirements for the use of AI in accounting. We explain GDPR-compliant deployment options (EU hosting via Azure, AWS Bedrock, etc.), point out risks such as hallucinations, and provide specific recommendations for operational implementation.