{
  "schemaVersion": "wenbu-knowledge-v1",
  "id": "guide-compare-chatbot",
  "slug": "compare-chatbot",
  "category": "compare",
  "language": "en",
  "title": "Ask a chatbot, or use a calculator first?",
  "description": "Understand what a language model does, what needs an actual calculation, and how a tool-enabled assistant can use Wenbu.",
  "intro": "A chatbot can explain terms, discuss your circumstances and organize thoughts. A chart needs calendar rules to be executed; a draw needs a defined random process. This comparison is about a tool-backed answer versus text generated without a tool. A general assistant with the right tools can do the former too.",
  "rows": [
    [
      "Charts",
      "Code calculates BaZi or Zi Wei from stated inputs and returns the conventions",
      "A written chart alone does not show which calendar rules were executed"
    ],
    [
      "Draws and casts",
      "Code performs the draw and returns the original cards or line values",
      "A card name alone does not show how it was selected"
    ],
    [
      "Personal context",
      "The built-in Agent sends the conversation and your selected context to AI",
      "Context and data use depend on the host application’s settings"
    ],
    [
      "Interpretation",
      "AI interprets the tool result; the explanation can still be wrong",
      "Model-generated interpretation also needs its inputs and sources checked"
    ],
    [
      "Using both",
      "Continue in the web Agent or pass results to your own assistant through MCP",
      "An assistant that supports MCP or tool calls can use a calculator in the conversation"
    ]
  ],
  "conclusion": "Look for the inputs, tool output and calculation conventions before assessing the prose. Connect Wenbu MCP to an assistant you already use for calculations and reference tools; its own model provides the interpretation. Choose the web Agent if you want charts, context selection and follow-up questions in one place.",
  "updated": "2026-09-29",
  "reviewed": "2026-09-29",
  "reviewScope": "Public pages checked 2026-09-29. This comparison uses official sources; paid and signed-in features have not been tested.",
  "authorship": "Wenbu · AI-assisted editorial; no independent expert review claimed",
  "evidenceType": "editorial",
  "scope": "full",
  "truncated": false,
  "links": {
    "html": "https://wenbu.app/en/compare/chatbot/",
    "markdown": "https://wenbu.app/knowledge/en/compare-chatbot.md",
    "json": "https://wenbu.app/knowledge/en/compare-chatbot.json"
  },
  "outline": [
    {
      "id": "comparison-workflow",
      "title": "Compare the workflow first"
    },
    {
      "id": "comparison-table",
      "title": "Product comparison"
    },
    {
      "id": "comparison-choice",
      "title": "Making a choice"
    },
    {
      "id": "comparison-sources",
      "title": "Sources and their scope"
    }
  ],
  "sources": [
    {
      "title": "AI · how external tool calls work",
      "url": "https://api-docs.deepseek.com/guides/tool_calls/"
    },
    {
      "title": "Wenbu · calculation source code",
      "url": "https://github.com/wenbu-app/wenbu/tree/main/src/lib"
    },
    {
      "title": "Wenbu · Methodology",
      "url": "https://wenbu.app/en/methodology/"
    },
    {
      "title": "Wenbu · Free-use policy",
      "url": "https://wenbu.app/en/free/"
    }
  ],
  "content": "# Ask a chatbot, or use a calculator first?\n\nUnderstand what a language model does, what needs an actual calculation, and how a tool-enabled assistant can use Wenbu.\n\nCanonical: https://wenbu.app/en/compare/chatbot/\n\nPublic pages checked 2026-09-29. This comparison uses official sources; paid and signed-in features have not been tested.\n\nAuthorship: Wenbu · AI-assisted editorial. Listed sources have not been fetched again by this read; predictive accuracy was not compared.\n\n## Compare the workflow first\n\nA chatbot can explain terms, discuss your circumstances and organize thoughts. A chart needs calendar rules to be executed; a draw needs a defined random process. This comparison is about a tool-backed answer versus text generated without a tool. A general assistant with the right tools can do the former too.\n\nPublic pages checked 2026-09-29. This comparison uses official sources; paid and signed-in features have not been tested.\n\n## Product comparison\n\n| Dimension | Wenbu | Chatbot without tools |\n| --- | --- | --- |\n| Charts | Code calculates BaZi or Zi Wei from stated inputs and returns the conventions | A written chart alone does not show which calendar rules were executed |\n| Draws and casts | Code performs the draw and returns the original cards or line values | A card name alone does not show how it was selected |\n| Personal context | The built-in Agent sends the conversation and your selected context to AI | Context and data use depend on the host application’s settings |\n| Interpretation | AI interprets the tool result; the explanation can still be wrong | Model-generated interpretation also needs its inputs and sources checked |\n| Using both | Continue in the web Agent or pass results to your own assistant through MCP | An assistant that supports MCP or tool calls can use a calculator in the conversation |\n\n## Making a choice\n\nLook for the inputs, tool output and calculation conventions before assessing the prose. Connect Wenbu MCP to an assistant you already use for calculations and reference tools; its own model provides the interpretation. Choose the web Agent if you want charts, context selection and follow-up questions in one place.\n\n## Sources and their scope\n\n- [AI · how external tool calls work](https://api-docs.deepseek.com/guides/tool_calls/)\n- [Wenbu · calculation source code](https://github.com/wenbu-app/wenbu/tree/main/src/lib)\n- [Wenbu · Methodology](https://wenbu.app/en/methodology/)\n- [Wenbu · Free-use policy](https://wenbu.app/en/free/)\n\n[Find your starting point](https://wenbu.app/en/learn/choose-a-tool/)"
}