Rendex Demo

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 →

{
  "name": "Rendex Demo",
  "nodes": [
    {
      "parameters": {
        "content": "## Rendex n8n Demo \u2014 Setup\n\n**1. On each of the 3 Rendex nodes**: click Credentials dropdown \u2192 pick **Rendex API**\n\n**2. On OpenAI Chat Model**: pick/create your OpenAI credential\n\n**3. Add Rendex as an AI tool** \u2014 see the sticky note near the AI Agent (bottom of canvas)\n\n**4. Recording order:**\n- Flow 1 (top):  'Test workflow' on Trigger - Sync\n- Flow 2 (middle): 'Test workflow' on Trigger - Async\n- Flow 3 (bottom): Click 'Chat' on the Chat Trigger and type: `Take a screenshot of https://google.com`",
        "height": 280,
        "width": 440
      },
      "id": "sticky-overview",
      "name": "Instructions",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -280,
        280
      ]
    },
    {
      "parameters": {},
      "id": "trigger-sync",
      "name": "Trigger - Sync",
      "type": "n8n-nodes-base.manualTrigger",
      "typeVersion": 1,
      "position": [
        200,
        300
      ]
    },
    {
      "parameters": {
        "resource": "screenshot",
        "operation": "capture",
        "source": "url",
        "url": "https://rendex.dev",
        "format": "png",
        "binaryPropertyName": "data",
        "additionalOptions": {
          "fullPage": true
        }
      },
      "id": "rendex-sync-capture",
      "name": "Rendex - Sync Capture",
      "type": "n8n-nodes-rendex.rendex",
      "typeVersion": 1,
      "position": [
        440,
        300
      ]
    },
    {
      "parameters": {},
      "id": "trigger-async",
      "name": "Trigger - Async",
      "type": "n8n-nodes-base.manualTrigger",
      "typeVersion": 1,
      "position": [
        200,
        540
      ]
    },
    {
      "parameters": {
        "resource": "screenshot",
        "operation": "captureAsync",
        "source": "url",
        "url": "https://example.com",
        "format": "png",
        "webhookUrl": "",
        "additionalOptions": {}
      },
      "id": "rendex-async-capture",
      "name": "Rendex - Async Capture",
      "type": "n8n-nodes-rendex.rendex",
      "typeVersion": 1,
      "position": [
        440,
        540
      ]
    },
    {
      "parameters": {
        "resource": "job",
        "operation": "getStatus",
        "jobId": "={{ $json.data.jobId }}"
      },
      "id": "rendex-job-status",
      "name": "Rendex - Job Status",
      "type": "n8n-nodes-rendex.rendex",
      "typeVersion": 1,
      "position": [
        680,
        540
      ]
    },
    {
      "parameters": {
        "public": false,
        "options": {}
      },
      "id": "chat-trigger",
      "name": "When chat message received",
      "type": "@n8n/n8n-nodes-langchain.chatTrigger",
      "typeVersion": 1.1,
      "position": [
        200,
        820
      ]
    },
    {
      "parameters": {
        "options": {
          "systemMessage": "You are a screenshot assistant. When the user mentions a website, URL, or domain, you MUST:\n\n1. Normalize it to a full URL (add https:// if the user omitted it \u2014 e.g., \"google.com\" \u2192 \"https://google.com\")\n2. Call the Rendex tool, passing the normalized URL as the `url` argument\n3. Wait for the tool's actual response before replying\n4. Summarize the real metadata from the tool response (format, bytesSize, contentType)\n\nNever claim a screenshot succeeded without seeing actual tool response data. If the tool returns an error, report the error honestly."
        }
      },
      "id": "ai-agent",
      "name": "AI Agent",
      "type": "@n8n/n8n-nodes-langchain.agent",
      "typeVersion": 1.7,
      "position": [
        460,
        820
      ]
    },
    {
      "parameters": {
        "model": "gpt-4o",
        "options": {}
      },
      "id": "lm-openai",
      "name": "OpenAI Chat Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "typeVersion": 1,
      "position": [
        380,
        1020
      ]
    },
    {
      "parameters": {
        "content": "### Add Rendex as an AI tool\n\nCommunity nodes can't auto-wire to the AI Agent's **ai_tool** socket on import \u2014 add via the UI:\n\n**1.** On the AI Agent, click **+** on its **Tool** socket (rightmost of 3 circles at the bottom)\n\n**2.** Search: **Rendex** \u2192 select \u2192 Rendex node appears, connected by dotted line\n\n**3.** Configure it:\n- Resource: **Screenshot**\n- Operation: **Capture**\n- Source: **URL**\n- Format: **png**\n- Credential: **Rendex API**\n\n**4. CRITICAL \u2014 register URL as an AI-controllable parameter:**\nHover over the **URL** field label. A \u2728 **sparkle button** appears to the right. **Click it.** n8n auto-generates the `$fromAI()` expression AND registers the parameter with the agent's tool schema.\n\n\u26a0\ufe0f **Typing `$fromAI()` manually into Expression mode DOES NOT register the param with the schema.** The \u2728 click is required.\n\n**5. Add a fallback** (optional but recommended). The \u2728 button inserts something like `={{ $fromAI('URL', '', 'string') }}`. Replace with:\n```\n{{ ($fromAI('URL', 'The full URL to screenshot, including https://', 'string')) || 'https://rendex.dev' }}\n```\nThe `|| 'https://rendex.dev'` catches cases where the AI passes an empty string.\n\n**6. Save workflow.**\n\n**7. Test prompt in chat:** `Take a screenshot of https://google.com`",
        "height": 560,
        "width": 480
      },
      "id": "sticky-tool",
      "name": "Add Rendex Tool Here",
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        680,
        920
      ]
    }
  ],
  "connections": {
    "Trigger - Sync": {
      "main": [
        [
          {
            "node": "Rendex - Sync Capture",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Trigger - Async": {
      "main": [
        [
          {
            "node": "Rendex - Async Capture",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Rendex - Async Capture": {
      "main": [
        [
          {
            "node": "Rendex - Job Status",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "When chat message received": {
      "main": [
        [
          {
            "node": "AI Agent",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "OpenAI Chat Model": {
      "ai_languageModel": [
        [
          {
            "node": "AI Agent",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  }
}

About this workflow

Rendex Demo. Uses n8n-nodes-rendex, chatTrigger, agent, lmChatOpenAi. Event-driven trigger; 10 nodes.

Source: https://github.com/copperline-labs/rendex-n8n/blob/main/demo/rendex-demo.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.