Analyze Screenshots with AI

Automatically analyze website screenshots using AI to extract valuable insights and descriptions. This powerful workflow connects the URLbox API to capture high-quality screenshots and then leverages OpenAI's advanced AI capabilities to interpret the visual content. It's ideal for marketing teams needing quick content summaries, developers performing automated UI testing, or product managers gathering feedback on new features. By automating the visual analysis of web pages, this workflow significantly reduces the manual effort and time spent on content review, allowing for faster iterations and more efficient decision-making.
9 nodesmanual trigger288 views0 copiesOther
OpenAI

Workflow JSON

{"id": "wDD4XugmHIvx3KMT", "meta": {"instanceId": "149cdf730f0c143663259ddc6124c9c26e824d8d2d059973b871074cf4bda531"}, "name": "Analyze Screenshots with AI", "tags": [], "nodes": [{"id": "6d7f34b8-6203-4512-a428-7b5a18c63db6", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [240, 1100], "parameters": {"width": 373.2796418305297, "height": 381.1230421279239, "content": "## Setup \n**For Testing use the Setup node to put in test name & url.**\n\nIf you want to use this workflow in production, you can expand it to load data from other sources like a DB or Google Sheet"}, "typeVersion": 1}, {"id": "ae568c65-e8f6-45bb-9c96-a870da1fc7d6", "name": "Setup", "type": "n8n-nodes-base.set", "position": [360, 1320], "parameters": {"values": {"string": [{"name": "website_name", "value": "=n8n"}, {"name": "url", "value": "https://n8n.io/"}]}, "options": {}}, "typeVersion": 2}, {"id": "ca9f0357-a596-4453-b351-fdd8d47c81ad", "name": "URLbox API Request", "type": "n8n-nodes-base.httpRequest", "position": [780, 1120], "parameters": {"url": "https://api.urlbox.io/v1/render/sync", "method": "POST", "options": {}, "sendBody": true, "sendHeaders": true, "bodyParameters": {"parameters": [{"name": "url", "value": "={{ $json.url }}"}, {"name": "full_page", "value": true}]}, "headerParameters": {"parameters": [{"name": "Authorization", "value": "YOUR_API_KEY"}]}}, "retryOnFail": true, "typeVersion": 4.1}, {"id": "3caffa3c-657a-4f74-a3cb-daf7beb67890", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [640, 920], "parameters": {"width": 373.2796418305297, "height": 381.1230421279239, "content": "## URLbox API call \n[URLbox](https://urlbox.com/) is a Screenshot API. With this API you can automate making screenshots based on website url's.\n\nYou have to replace the Placeholder with your API Key"}, "typeVersion": 1}, {"id": "d2b81b41-1497-4733-8130-67f8de0acff4", "name": "Analyze the Screenshot", "type": "@n8n/n8n-nodes-langchain.openAi", "position": [1220, 1120], "parameters": {"text": "=Your Input is a Screenshot of a Website.\nDescribe the content of the Website in one sentence.", "options": {}, "resource": "image", "imageUrls": "renderURL", "operation": "analyze"}, "typeVersion": 1.1}, {"id": "68d86931-69bb-4b78-a7fe-44969172672f", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [1080, 920], "parameters": {"width": 373.2796418305297, "height": 381.1230421279239, "content": "## Analyze the Screenshot \nAnalyze the screenshot using OpenAI.\n\nAdd your OpenAI Credentials on the top of the node.\n\nThe prompt is an example. Change it based on what you want to extract from the screenshot."}, "typeVersion": 1}, {"id": "8a22fca5-7f06-45fb-a03f-585a7eb35b40", "name": "Merge Name & Description", "type": "n8n-nodes-base.merge", "position": [1620, 1300], "parameters": {"mode": "combine", "options": {}, "combinationMode": "mergeByPosition"}, "typeVersion": 2.1}, {"id": "4f902a0a-ee93-4190-9b1e-ab3fa15eb4aa", "name": "Sticky Note3", "type": "n8n-nodes-base.stickyNote", "position": [1480, 1200], "parameters": {"width": 371.85912137154685, "height": 300.15337596590155, "content": "## Merge\nMerge the description with the name of the website & the url."}, "typeVersion": 1}, {"id": "8b3eb3f4-b31a-48f0-94bb-35379d07a81f", "name": "Manual Execution", "type": "n8n-nodes-base.manualTrigger", "position": [20, 1320], "parameters": {}, "typeVersion": 1}], "active": false, "pinData": {}, "settings": {"executionOrder": "v1"}, "versionId": "ff37faa1-c61c-44be-89f0-62f8e1b8317c", "connections": {"Setup": {"main": [[{"node": "URLbox API Request", "type": "main", "index": 0}, {"node": "Merge Name & Description", "type": "main", "index": 1}]]}, "Manual Execution": {"main": [[{"node": "Setup", "type": "main", "index": 0}]]}, "URLbox API Request": {"main": [[{"node": "Analyze the Screenshot", "type": "main", "index": 0}]]}, "Analyze the Screenshot": {"main": [[{"node": "Merge Name & Description", "type": "main", "index": 0}]]}}}

How to Import This Workflow

  1. 1Copy the workflow JSON above using the Copy Workflow JSON button.
  2. 2Open your n8n instance and go to Workflows.
  3. 3Click Import from JSON and paste the copied workflow.

Don't have an n8n instance? Start your free trial at n8nautomation.cloud

Related Templates

KB Tool - Confluence Knowledge Base

Quickly retrieve information from your Confluence knowledge base with this n8n workflow. It connects to your Confluence instance via an HTTP Request node, allowing you to query for specific content directly from n8n. This workflow is ideal for support teams needing to rapidly access articles, developers looking up documentation, or anyone who frequently references Confluence pages and wants to integrate that data into other automated processes. By centralizing Confluence queries within n8n, you save significant time and effort previously spent manually navigating and searching, streamlining information retrieval and improving operational efficiency.

7 nodes

Analyze the sentiment of feedback and send a message on Mattermost

Automatically analyze customer feedback sentiment and notify your team on Mattermost with this n8n workflow. This automation connects Typeform submissions directly to Google Cloud Natural Language for sentiment analysis, then routes the results to your Mattermost channel. When a user submits a form through Typeform, the workflow extracts the feedback, sends it to Google Cloud Natural Language for sentiment scoring, and based on that score, sends a message to a designated Mattermost channel, allowing for immediate team awareness of positive, negative, or neutral feedback. This workflow is ideal for product managers, customer support teams, or marketing departments who need to quickly gauge public opinion or customer satisfaction from surveys, support tickets, or product reviews, enabling faster response times to critical feedback and reducing the manual effort of monitoring and reporting. It saves significant time and ensures that important customer insights are never missed, fostering a more responsive and customer-centric operation.

5 nodes

Hacker News Throwback Machine - See What Was Hot on This Day, Every Year!

Discover what was trending on Hacker News on this exact day, every year, with the Hacker News Throwback Machine. This n8n workflow automates the process of fetching historical Hacker News front pages and summarizing the top stories, delivering a daily dose of tech nostalgia directly to your Telegram chat. A Schedule Trigger initiates the workflow, which then dynamically generates a list of past years. For each year, it uses an HTTP Request node to retrieve the Hacker News front page for today's date, then an HTML Extract Details node parses the headlines and links. These headlines are then compiled and fed into a Google Gemini Chat Model via a Basic LLM Chain, which summarizes the most interesting stories. Finally, the summarized insights are sent to your designated Telegram chat, providing a unique historical perspective without any manual effort. This workflow is perfect for tech enthusiasts, developers, or anyone curious about the evolution of tech news, saving significant time and effort compared to manually searching through archives.

13 nodes

Ready to automate with n8n?

Get affordable managed n8n hosting with 24/7 support.