> For the complete documentation index, see [llms.txt](https://docs.maiagent.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.maiagent.ai/maiagent-user-guide/maiagent-user-guide-en/application/km/finance.md). # Financial Analysis Assistant Enterprise finance teams often face challenges such as scattered data, time-consuming chart creation, and inconsistent analysis report formats when processing complex financial data. Traditional financial analysis tools typically require tedious manual chart creation processes, which are not only inefficient but also make it difficult to quickly respond to management's demand for real-time financial insights. Now, you can leverage MaiAgent's Canvas visualization technology to build a dedicated enterprise financial AI analysis assistant, enabling intelligent financial data visualization and analysis! ## Use Case: Build an Enterprise Financial Data Visualization AI Assistant Suppose you are a financial analyst at a publicly listed company who needs to produce revenue reports, cost analysis charts, and financial dashboards for the board of directors every month. In the past, you might have spent hours manually creating various charts in Excel — not only time-consuming and labor-intensive, but the chart formats were often inconsistent due to manual operations, affecting the professionalism of reports. For example, when the CEO requests a "gross margin trend analysis chart for all product lines over the past 12 months" 30 minutes before a board meeting, the traditional approach requires you to urgently dig through data and recreate charts, often making it impossible to complete before the meeting. Now, with MaiAgent Canvas technology, you simply describe your needs to the AI assistant in natural language, and the system immediately generates professional interactive financial charts. This not only dramatically improves work efficiency but also ensures the accuracy and consistency of charts, allowing you to focus on higher-value financial analysis insights! ## Workflow ### 1. Create a Financial Data Analysis AI Assistant Enter the AI assistant name.
Select RAG and language model, **and enable Canvas mode**.

Response mode must be set to Agent, with Canvas mode enabled under Agent mode

When selecting the response mode, choose "Agent Mode" and enable "Canvas Mode". Refer to the following role instructions: ``` ## Role Setting You are a professional financial analysis expert specializing in in-depth analysis and insights of corporate financial statements. Your task is to help users understand the financial status, operational performance, and future potential of specific companies. ## Core Task Search the knowledge base for financial data to create chart data, and call tools to use React for producing dynamic financial analysis reports. When users need reports, call the canvas tool to draw relevant charts. Present content using charts as much as possible. ## Output Requirements 1. **Structured Report:** Present analysis results in a clear, organized report format, including: * **Summary:** Brief overview of overall financial performance. * **Key Findings:** List the most important financial highlights and issues. * **Detailed Analysis:** Explain calculation results, trend analysis, and interpretation of each financial indicator. * **Chart Visualization:** **Must** use the canvas tool to draw relevant charts to visually present data trends and comparisons. * **Conclusions and Recommendations:** Synthesize all analyses to provide specific conclusions and action recommendations. 2. **Chart Visualization:** * Chart types should be diverse, such as: * Revenue and net profit trend line charts * Profitability ratio comparison bar charts * Asset-liability structure pie charts (showing composition ratios of assets and liabilities) * Cash flow trend charts (operating, investing, financing cash flows) * Annual trend charts of key financial ratios (e.g., ROE, ROA) 3. **Language and Tone:** Use Traditional Chinese with a professional, objective, and precise tone. Avoid vague or ambiguous wording. 4. **Interactivity:** If data is incomplete or requires further clarification, proactively ask for more information, such as: "Please provide more detailed cash flow statement data so I can conduct a more comprehensive analysis." ``` ### 2. Upload Financial Data Knowledge Base Upload the company's financial data files, including: * Monthly/quarterly income statements * Balance sheets * Cash flow statements * Departmental budget and actual expenditure data * Product line revenue data * Historical financial reports
### 3. Deploy the AI Assistant - Canvas Visualization Features #### Real-Time Chart Generation When you need to create financial charts, simply make a request to the AI assistant, and the system will automatically determine and use Canvas technology to generate the corresponding visualizations: **Example 1: Revenue Trend Analysis**\ Input: "Create a monthly revenue trend chart for 2024"\ → The AI assistant uses **React Canvas** to generate an interactive multi-line trend chart
**Example 2: Cost Structure Analysis**\ Input: "Generate a pie chart showing cost distribution by department"\ → The AI assistant uses **SVG Canvas** to generate a professional vector pie chart
**Example 3: Financial Dashboard**\ Input: "Create a financial performance monitoring dashboard for this quarter"\ → The AI assistant uses **HTML/React Canvas** to generate a complete interactive dashboard
**Example 4: Financial Audit Process**\ Input: "Create an expense reimbursement audit flowchart"\ → The AI assistant uses **Mermaid Canvas** to generate a clear flowchart
#### Demo Video {% embed url="" %} ### 4. Canvas Technology Advantages in Financial Applications #### 🚀 Efficiency Improvement * **Instant Generation**: From request to completed chart in just 30 seconds * **Consistent Formatting**: All charts follow corporate visual identity standards * **No Manual Operations**: Natural language is all you need to create complex charts #### 📊 Professional Quality * **Interactive Features**: Support for data filtering and time range adjustment * **Responsive Design**: Adapts to various screen sizes and output formats * **Vector Graphics**: SVG format ensures clarity for printing and projection #### 🔄 Flexible Adjustments * **Real-Time Modifications**: Instantly adjust chart styles and data ranges * **Multiple Output Formats**: Generate different visualization formats from the same data * **Customization**: Adjust presentation based on different usage scenarios #### 💼 Enterprise Integration * **Brand Consistency**: Integrates corporate color and font standards * **Localization Support**: Supports Taiwan accounting standards and currency formats * **Security**: Financial data is processed locally to ensure information security With MaiAgent Canvas technology, finance teams can not only dramatically improve work efficiency but also invest their time in higher-value financial analysis and strategy development, truly achieving the goals of financial digital transformation! **Experience the financial data analysis assistant now — make your financial reports not just numbers, but visualized insights!** --- # 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.maiagent.ai/maiagent-user-guide/maiagent-user-guide-en/application/km/finance.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.