AutomationFlowsAI & RAG › Conversion Agent

Conversion Agent

Conversion Agent. Uses executeWorkflowTrigger, agent, toolCalculator, lmChatOpenAi. Event-driven trigger; 4 nodes.

Event trigger★★☆☆☆ complexityAI-powered4 nodesExecute Workflow TriggerAgentTool CalculatorOpenAI Chat
AI & RAG Trigger: Event Nodes: 4 Complexity: ★★☆☆☆ AI nodes: yes Added:

This workflow follows the Agent → Execute Workflow Trigger recipe pattern — see all workflows that pair these two integrations.

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

Download .json
{
  "name": "Conversion Agent",
  "nodes": [
    {
      "parameters": {
        "inputSource": "passthrough"
      },
      "type": "n8n-nodes-base.executeWorkflowTrigger",
      "typeVersion": 1.1,
      "position": [
        0,
        0
      ],
      "id": "943ecffe-c1c5-47c7-9d7a-e61f13eceb8b",
      "name": "When Executed by Another Workflow"
    },
    {
      "parameters": {
        "promptType": "define",
        "text": "={{ $json.query }}",
        "options": {
          "systemMessage": "## 1 \u00b7 ROLE  \nYou are **Data\u202fConverter**, a precise, unit\u2011conversion micro\u2011service that assists *Health\u202fAssistant* by converting numerical values between medical units.\n\n*You never provide clinical interpretations, only conversions.*\n\nThe calling agent sends you a request such as:\n\"Convert 123 lbs to kgs\"\n\nYou **must reply** with the correct value that is immediately usable by Health\u202fAssistant:\n\n\"55.79 kg\"\n\nIf the conversion is unsupported reply with:\n\"unsupported conversion\"\n\nNo additional keys or text.\n\n---\n\n## 2 \u00b7 TOOLS  \n\n| Tool            | Purpose                                                         | Usage |\n|-----------------|-----------------------------------------------------------------|-------|\n| **calculator**  | Performs arithmetic (add, subtract, multiply, divide, exponent) | Use for every conversion to avoid manual math and ensure precision. |\n\n---\n\n## 3 \u00b7 SUPPORTED CONVERSIONS  \n\n| Category | from_unit / to_unit pairs | Formula |\n|----------|---------------------------|---------|\n| **Weight** | `lb` \u2194 `kg` | `lb * 0.453592`, `kg / 0.453592` |\n| **Height / Length** | `in` \u2194 `cm`, `ft` \u2194 `cm`, `cm` \u2194 `m` | `in * 2.54`, `ft * 30.48`, `cm / 100` |\n| **Temperature** | `F` \u2194 `C` | `(F \u2212 32) * 5/9`, `(C * 9/5) + 32` |\n| **Glucose** | `mg/dL` \u2194 `mmol/L` | `mg/dL / 18`, `mmol/L * 18` |\n| **Cholesterol (TC/LDL/HDL)** | `mg/dL` \u2194 `mmol/L` | `mg/dL / 38.67`, `mmol/L * 38.67` |\n| **Triglycerides** | `mg/dL` \u2194 `mmol/L` | `mg/dL / 88.57`, `mmol/L * 88.57` |\n| **Creatinine** | `mg/dL` \u2194 `\u03bcmol/L` | `mg/dL * 88.4`, `\u03bcmol/L / 88.4` |\n| **Body Surface Area** | `m2` \u2194 `ft2` | `m\u00b2 * 10.7639`, `ft\u00b2 / 10.7639` |\n\n*Units are case\u2011insensitive; accept synonyms (`kilogram`, `lbs`) but always **return** the canonical unit abbreviation shown above.*\n\n---\n\n## 4 \u00b7 RULES  \n\n1. **No free\u2011text explanations.** \n2. Round to **3 significant digits** unless the input has higher precision.  \n3. Use the **calculator** tool for every numeric operation.  \n4. If either unit is missing or not in the table above, respond with the unsupported response.  \n\n---"
        }
      },
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 1.8,
      "position": [
        220,
        0
      ],
      "id": "5cbfb649-e3ef-4a85-b18f-47b83870a427",
      "name": "AI Agent"
    },
    {
      "parameters": {},
      "type": "@n8n/n8n-nodes-langchain.toolCalculator",
      "typeVersion": 1,
      "position": [
        460,
        280
      ],
      "id": "f7fdc62a-7fe4-4eb7-a172-4df74893d4ed",
      "name": "calculator"
    },
    {
      "parameters": {
        "model": {
          "__rl": true,
          "value": "qwen2.5-32-ctx:latest",
          "mode": "list",
          "cachedResultName": "qwen2.5-32-ctx:latest"
        },
        "options": {}
      },
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "typeVersion": 1.2,
      "position": [
        220,
        240
      ],
      "id": "9b717866-1e74-4fa8-996c-e73da677677e",
      "name": "Ollama",
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      }
    }
  ],
  "connections": {
    "When Executed by Another Workflow": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "calculator": {
      "ai_tool": [
        [
          {
            "node": "AI Agent",
            "type": "ai_tool",
            "index": 0
          }
        ]
      ]
    },
    "Ollama": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    }
  },
  "active": false,
  "settings": {
    "executionOrder": "v1"
  },
  "versionId": "05b5a0c2-4175-4d88-8354-417c5dac4981",
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "id": "gVJjwuKcZ09hlFj4",
  "tags": []
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

Pro

For the full experience including quality scoring and batch install features for each workflow upgrade to Pro

About this workflow

Conversion Agent. Uses executeWorkflowTrigger, agent, toolCalculator, lmChatOpenAi. Event-driven trigger; 4 nodes.

Source: https://github.com/DaveBben/apple-health-ai-agent/blob/036f691adbb1eb28201db877de2b90a8028660b0/n8n/Conversion_Agent.json — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.

AI & RAG

05B-Sub: Finance Calculator. Uses executeWorkflowTrigger, agent, lmChatOpenAi, toolCalculator. Event-driven trigger; 10 nodes.

Execute Workflow Trigger, Agent, OpenAI Chat +2
AI & RAG

Agent Access Control Template. Uses memoryBufferWindow, lmChatOpenAi, telegramTrigger, airtable. Event-driven trigger; 36 nodes.

Memory Buffer Window, OpenAI Chat, Telegram Trigger +9
AI & RAG

This workflow allows granular control over the access to tools connected to AI Agents (including Multi-Agent setups) using Role Based Access Control.

Memory Buffer Window, OpenAI Chat, Telegram Trigger +9
AI & RAG

Apertura. Uses executeWorkflowTrigger, dataTable, agent, lmChatOpenAi. Event-driven trigger; 20 nodes.

Execute Workflow Trigger, Data Table, Agent +7
AI & RAG

Enrich Company Data from Google Sheet with OpenAI Agent and Scraper Tool. Uses outputParserStructured, lmChatOpenAi, googleSheets, toolWorkflow. Event-driven trigger; 13 nodes.

Output Parser Structured, OpenAI Chat, Google Sheets +4