Workflow Templates

Analyzing uploaded Liveblocks comments attachments with AI This example uses Liveblocks Comments, collaborative commenting components for React. When an AI assistant is mentioned in a thread (e.g. "@AI Assistant"), it will automatically leave a response. Additionally, it will analyze any PDf or image attachments in the comments, and use them to help it respond. Using webhooks, this workflow is triggered when a comment is created in a thread. If the agent's ID ("__AI_AGENT") it will create a response. If a PDF or image file is uploaded, these will be analyzed by Anthropic and used as context. This response is then added, and users will see it appear in their apps in real time. Set up This workflow requires a Comments app installed and webhooks set up in the Liveblocks dashboard. You can try it with a demo application: Download the Next.js comments example, and run it with a secret key. Find database.ts inside the example and uncomment the AI assistant user. Insert the secret key from the project into n8n nodes: "Get a comment", "Get a thread", "Create a comment". Go to the Liveblocks dashboard, open your project and go to "Webhooks". Create a new webhook in your project using a placeholder URL, and selecting "commentCreated" events. Copy your webhook secret from this page and paste it into the "Liveblocks Trigger" node. Expose the webhook URL from the trigger, for example with localtunnel or ngrok. Copy the production URL from the "Liveblocks Trigger" and replace localhost:5678 with the new URL. Your workflow is now set up! Tag @AI Assistant in the application and add attachments to trigger it. Localtunnel The easiest way to expose your webhook URL: npx localtunnel --port 5678 --subdomain your-name-here This creates a URL like: https://honest-months-fix.loca.lt The URL you need for the dashboard looks like this: https://honest-months-fix.loca.lt/webhook/9cc66974-aaaf-4720-b557-1267105ca78b/webhook `

Automated YouTube SEO, Thumbnail Generation & Video Upload via AI, Google Drive & LemonFox Pre-requesties: Video uploaded to gdrive. And sponsor file with the similar formart "videotitle_sponsors.txt" Node-by-Node Functional Breakdown This workflow is an end-to-end "Content-to-Publish" engine. I’ve broken it down by the specific stage of production: Stage 1: The Intake & Access | Node Name | What it does | | :--- | :--- | | When File Added in Drive | The Trigger: Watches your "transcript" folder. The moment you drop a video file here, the engine starts. | | If Video Mime Type | The Gatekeeper: Ensures the file is actually a video (e.g., .mp4) and not a random document or image before proceeding. | | Grant Temp File Access | The Key: Temporarily changes the Drive file's permissions to "Anyone with link" so external AI tools (LemonFox) can download and process it. | Stage 2: Transcription & Data Prep | Node Name | What it does | | :--- | :--- | | Post Audio to Lemonfox | The Ears: Sends the video to LemonFox AI to extract the spoken word into a structured SRT (subtitle) format. | | Clean SRT Content | The Editor: A JavaScript node that cleans up technical formatting issues and unescapes characters to make the text readable for the AI. | | Create Text File in Drive | The Archive: Saves your clean transcript back to Google Drive for your records. | | Search/Fetch Sponsor Info | The Researcher: Looks for a specific .txt file named after your video that contains sponsor details (Name/Email) so they can be credited. | Stage 3: AI Strategy & Creative | Node Name | What it does | | :--- | :--- | | Content Analysis Agent | The Strategist: Uses Gemini to analyze the transcript and find the "Big Idea." It then writes a high-CTR Title, SEO Description, and Tags. | | Parse Structured Output | The Translator: Ensures the AI's creative writing is formatted as strict JSON so the next "Upload" step can understand it. | | Generate Thumbnail Image | The Artist: Takes a specific "Thumbnail Prompt" written by the AI and uses Gemini (Nano Banana) to generate a high-quality 16:9 image. | Stage 4: Publishing & Cleanup | Node Name | What it does | | :--- | :--- | | Upload to YouTube API | The Publisher: Hits your upload endpoint, sending the original video link, the AI-generated metadata, and the AI-generated thumbnail. | | Delete Original File Permissions | The Security Guard: Immediately revokes the "Anyone with link" access to your Google Drive file, locking it back down for privacy. |

HOW IT WORKS This workflow automates end-to-end data intelligence processing by ingesting structured data (CSV, JSON), enriching it through multiple AI analysis pathways, and generating actionable insights. Designed for business analysts, data scientists, and operations teams, it solves the problem of manual data enrichment and fragmented analysis by consolidating diverse AI models (GPT-4, LLM analysis, sentiment detection) into a unified pipeline. Data flows from source ingestion → enrichment/validation → branching into three specialized analysis paths (Competitive Intelligence, Sentiment Analysis, Market Insights) → aggregation → result storage (Google Sheets) and notifications (Slack, Gmail). Each path applies distinct AI models for comprehensive intelligence gathering. SETUP STEPS Configure OpenAI API key in credentials Set up Google Sheets connection with service account Add Slack webhook for notifications Connect Gmail for automated report distribution Configure NVIDIA API (if using specialized models) Map input data source (CSV upload or API endpoint) Test each branch independently before full deployment PREREQUISITES OpenAI API key, Google Sheets access, Slack workspace, Gmail account, basic n8n familiarity. USE CASES Market research automation, competitive intelligence monitoring, customer feedback analysis at scale CUSTOMIZATION Swap AI models (Claude, Gemini, Llama), add/remove analysis branches, modify output destinations BENEFITS Eliminates manual data processing (80% time savings), enables simultaneous multi-perspective analysis

This workflow creates an automated Product Intelligence Engine that continuously collects signals from multiple product sources and generates structured PRD updates using AI. It ingests conversations, feedback, support tickets, analytics, and design comments, standardizes them, analyzes them with an AI PRD Agent, and automatically updates a Google Doc with structured PRD recommendations. Instead of manually reviewing Slack threads, Zoom calls, Jira comments, support tickets, and customer forms, this workflow centralizes everything into one intelligent PRD analysis system. High-Level Architecture - The workflow runs in 4 layers: 1. Signal Ingestion Layer Captures product signals from: • Slack (channel messages + app mentions) • Customer Form submissions • Zoom recordings (scheduled) • Jira comments (scheduled) • Zendesk tickets (scheduled) • Figma comments (file updates) • Platform analytics via webhook • (Extendable to Salesforce / HubSpot) 2. Standardization Layer Each source passes through a Format Node that: • Extracts relevant text • Normalizes metadata • Adds timestamps • Labels source type All inputs are converted into a unified "product signal" object. 3. Intelligence Layer (AI PRD Agent) All signals are merged into a single stream using a Merge node. The PRD Analysis Agent then: • Extracts feature requests • Detects scope changes • Identifies risks and constraints • Evaluates priority signals • Detects target user shifts • Generates structured PRD updates 4. PRD Governance Layer - output in a Google Doc The structured AI output is appended to a Google Doc, which is fully traceable. This creates a living PRD that continuously evolves based on real product signals. Required Credentials (And How To Add Them): You will need to configure the following credentials in n8n: 1. Slack Used for Slack Trigger. Steps: Create a Slack App at api.slack.com Enable: app_mentions:read channels:history chat:write (optional if you want replies) Install app to workspace Copy Bot OAuth Token In n8n → Create Slack API credential Paste token Reference - https://www.youtube.com/watch?v=qk5JH6ImK0I 2. Zoom (OAuth2) Used to fetch recordings. Steps: Create an OAuth App in Zoom Marketplace Add the Redirect URL from n8n Copy Client ID + Secret Add Zoom OAuth2 credential in n8n Connect account Reference - https://www.youtube.com/watch?v=BC6O_3LYgac 3. Google Docs (OAuth2) Used to update PRD document. Steps: Create Google Cloud Project Add Doc URl to n8n Replace the example Google Doc URL with your own PRD document. Reference - https://www.youtube.com/watch?v=iieEHvu93dc 4. Jira (Cloud) Steps: Generate API token from Atlassian Create Jira Software Cloud credential Enter: Email API token Domain Reference - https://www.youtube.com/watch?v=T4z7lzqSZDY 5. Zendesk Steps: Generate API token Add Zendesk credential Enter: Subdomain Email API token 6. Figma Steps: Generate a personal access token in Figma Add Figma credentials with the team ID Paste token 7. Platform Analytics Webhook Replace: <PLACEHOLDER_VALUE__your_analytics_api_endpoint> With your real analytics endpoint. You can: • Send Mixpanel exports • Send Amplitude exports • Or POST custom JSON What Makes This Powerful • Eliminates product signal silos • Creates AI-driven PRD governance • Ensures traceability of decisions • Enables continuous PRD evolution • Scales across teams

Skool Community Scraper Using Olostep API This n8n template automates scraping content from Skool communities using the Olostep API. It collects structured data from Skool pages and stores it in a clean format, making it easy to analyze communities, extract insights, or build datasets for research and outreach. Who’s it for Community builders researching Skool groups Marketers analyzing competitor or niche communities SaaS founders validating ideas through community data Automation builders collecting structured social data Anyone who wants Skool data without manual scraping How it works / What it does Trigger The workflow starts with a manual trigger or form input containing a Skool URL or query. Skool Page Scraping The workflow uses the Olostep API to scrape Skool community pages. Extracts structured data using LLM-based parsing. Data Extraction Depending on configuration, the workflow can extract: Community name Post titles and content Author names Engagement metrics (likes, comments) URLs to posts or discussions Parse & Normalize The raw response is cleaned and split into individual items. Ensures consistent fields across all scraped entries. Deduplication Duplicate posts or entries are automatically removed. Data Storage The final structured data is stored in a table (Google Sheets or n8n Data Table). Ready for filtering, exporting, or further automation. This workflow allows you to turn Skool communities into structured datasets without browser automation or manual copy/paste. How to set up Import the template into your n8n workspace. Add your Olostep API key. Define the Skool page or community URL you want to scrape. Connect your storage destination (Google Sheets or Data Table). Run the workflow and collect structured Skool data automatically. Requirements n8n account (cloud or self-hosted) Olostep API key Google Sheets account or n8n Data Table How to customize the workflow Change extraction schema to capture more fields (timestamps, tags, replies). Add pagination to scrape older posts. Store data in Airtable, Notion, or a database. Trigger scraping on a schedule instead of manually. Combine with AI agents to summarize or analyze community discussions. 👉 This template makes it easy to extract, analyze, and reuse Skool community data at scale.

📘 Description This workflow automates document understanding by accepting uploaded PDF or TXT files, extracting their text, generating a structured summary and question–answer set using GPT-4o, validating the AI output, and returning a clean JSON response to the requester. It also sends an internal Slack preview and logs malformed outputs for debugging. It performs intelligent file-type detection, handles binary text extraction, enforces strict JSON formatting from the AI model, and ensures that the final response is clean, structured, and ready for use in downstream systems. All errors—missing text, invalid JSON, or malformed AI output—are captured automatically in Google Sheets. The workflow is designed as a plug-and-play document-analysis engine that converts any uploaded document into meaningful insights instantly. ⚙️ What This Workflow Does (Step-by-Step) 📥 Receive Document Upload via Webhook Captures incoming files (PDF or TXT) posted to the webhook endpoint. 🔍 Check If Uploaded File Is PDF / TXT Detects file extension and routes it correctly for extraction: PDF → PDF extractor TXT → text extractor Other file types are ignored. 📝 Extract Text from Document Extracts readable text from PDF binaries Reads raw plain text from TXT files The extracted text becomes input for the AI analysis. 🤖 Generate Summary & Q&A Using AI Uses GPT-4o to produce: A 150–200 word summary Five structured Q&A pairs Output must strictly follow the specified JSON schema. 🧠 LLM Engine + Memory Context GPT-4o provides the reasoning engine Memory buffer maintains short context for stability Output parser ensures schema compliance ⚠️ Validate AI Output Before Processing Checks whether output is non-empty and correctly structured. Invalid → logged to Google Sheets. 📊 Log Invalid AI Output to Google Sheet Records failures for audit, debugging, and retraining. 🧹 Unwrap AI Output Object Removes unnecessary array wrappers and normalizes the result. 📤 Prepare Final Response Payload Ensures the workflow responds with a single clean JSON object. 🔁 Send Final Summary & Q&A Response to Webhook Returns the final structured JSON to the requesting system. 💬 Send Summary Preview to Slack Shares a short preview (first 300 characters) for internal visibility. 🧩 Prerequisites Webhook endpoint configured for uploads Azure OpenAI GPT-4o credentials Google Sheets OAuth connection Slack bot token 💡 Key Benefits ✔ Fully automated PDF/TXT understanding ✔ AI-powered summary + structured Q&A ✔ Strict JSON compliance for downstream systems ✔ Error-proof: logs all failures for investigation ✔ Slack visibility for quick internal review ✔ Works with minimal human involvement 👥 Perfect For Research teams Documentation workflows Customer-support intelligence Interview screening document parsing Internal knowledge extraction systems

Automated Brand DNA Generator Using JotForm, Google Search, AI Extraction & Notion The Brand DNA Generator workflow automatically scans and analyzes online content to build a company’s Brand DNA profile. It starts with input from a form, then crawls the company’s website and Google search results to gather relevant information. Using AI-powered extraction, the system identifies insights such as value propositions, ideal customer profiles (ICP), pain points, proof points, brand tone, and more. All results are neatly formatted and automatically saved to a Notion database as a structured Brand DNA report, eliminating the need for manual research. 🛠️ Key Features Automated data capture, collects company data directly from form submissions and Google search results. Uses AI-powered insight extraction with LLMs to extract and summarize brand-related information from website content. Fetches clean text from multiple web pages using HTTP requests and a content extractor. Merges extracted data from multiple sources into a single Brand DNA JSON structure. Automatically creates a new page in Notion with formatted sections (headings, paragraphs, and bullet points). Handles parsing failures and processes multiple pages efficiently in batches. 🔧 Requirements JotForm API Key, to capture company data from form submissions. SerpAPI Key, to perform automated Google searches. OpenRouter / LLM API, for AI-based language understanding and information extraction. Notion Integration Token & Database ID, to save the final Brand DNA report to Notion. 🧩 Setup Instructions Connect your JotForm account and select the form containing the fields Company Name and Company Website. Add your SerpAPI Key. Configure the AI model using OpenRouter or LLM. Enter your Notion credentials and specify the databaseId in the Create a Database Page node. Customize the prompt in the Information Extractor node to modify the tone or structure of AI analysis (Optional). Activate the workflow, then submit data through the JotForm to test automatic generation and Notion integration. 💡 Final Output A complete Brand DNA Report containing: Company Description Ideal Customer Profile Pain Points Value Proposition Proof Points Brand Tone Suggested Keywords All generated automatically from the company’s online presence and stored in Notion with no manual input required.

Recruiter Mirror is a proof‑of‑concept ATS analysis tool for SDRs/BDRs. Compare your LinkedIn or CV to job descriptions and get recruiter‑ready insights. By comparing candidate profiles against job descriptions, it highlights strengths, flags missing keywords, and generates actionable optimization tips. Designed as a practical proof of concept for breaking into tech sales, it shows how automation and AI prompts can turn LinkedIn into a recruiter‑ready magnet. Got it ✅ — based on your workflow (Webhook → LinkedIn CV/JD fetch → GhostGenius API → n8n parsing/transform → Groq LLM → Output to Webhook), here’s a clear list of tools & APIs required to set up your Recruiter Mirror (Proof of Concept) project: 🔧 Tools & APIs Required 1. n8n (Automation Platform) Either n8n Cloud or self‑hosted n8n instance. Used to orchestrate the workflow, manage nodes, and handle credentials securely. 2. Webhook Node (Form Intake) Captures LinkedIn profile (LinkedIn_CV) and job posting (LinkedIn_JD) links submitted by the user. Acts as the starting point for the workflow. 3. GhostGenius API Endpoints Used: /v2/profile → Scrapes and returns structured CV/LinkedIn data. /v2/job → Scrapes and returns structured job description data. Auth**: Requires valid credentials (e.g., API key / header auth). 4. Groq LLM API (via n8n node) Model Used: moonshotai/kimi-k2-instruct (via Groq Chat Model node). Purpose: Runs the ATS Recruiter Check, comparing CV JSON vs JD JSON, then outputs a structured JSON per the ATS schema. Auth**: Groq account + saved API credentials in n8n. 5. Code Node (JavaScript Transformation) Parses Groq’s JSON output safely (JSON.parse). Generates clean, recruiter‑ready HTML summaries with structured sections: Status Reasoning Recommendation Matched keywords / Missing keywords Optimization tips 6. n8n Native Nodes Set & Aggregate Nodes** → Rebuild structured CV & JD objects. Merge Node** → Combine CV data with job description for comparison. If Node** → Validates LinkedIn URL before processing (fallback to error messaging). Respond to Webhook Node** → Sends back the final recruiter‑ready insights in JSON (or HTML). ⚠️ Important Notes Credentials**: Store API keys & auth headers securely inside n8n Credentials Manager (never hardcode inside nodes). Proof of Concept: This workflow demonstrates feasibility but is **not production‑ready (scraping stability, LinkedIn terms of use, and API limits should be considered before real deployments).

AI-Powered Quiz Generator for Instructors 📝🤖 Instantly turn any document into a shareable online quiz! This n8n workflow automates the entire quiz creation process: a new Jotform submission triggers the flow, the Google Gemini AI extracts key concepts and generates multiple-choice questions with correct answers, saves the questions to a Google Sheet for record-keeping, and finally creates a fully built, ready-to-share Jotform quiz using an HTTP request. How it Works This powerful workflow acts as a complete "document-to-quiz" automation tool, simplifying the process of creating educational or testing materials: Trigger & Input: The process starts when a user fills out the main Jotform submission form, providing a document (PDF/file upload), the desired Quiz Title, and the Number of Questions to generate. Create a jotform like this: https://form.jotform.com/252856893250062 having fields for Quiz Name, File Upload and Number of questions. Document Processing: The workflow retrieves the uploaded document via an HTTP request and uses the Extract from File node to parse and extract the raw text content from the file. AI Question Generation: The extracted text, quiz title, and desired question count are passed to the Google Gemini AI Agent. Following strict instructions, the AI analyzes the content and generates the specified number of multiple-choice questions (with four options and the correct answer indicated) in a precise JSON format. Data Structuring: The generated JSON is validated and formatted using a Structured Output Parser and split into individual items for each question. Record Keeping (Google Sheets): Each generated question, along with all its options and the confirmed correct answer, is appended as a new row in a designated Google Sheet for centralized record-keeping and review. Jotform Quiz Creation (HTTP Request): The workflow dynamically constructs the required API body, converting the AI-generated questions and options into the necessary fields for a new Jotform. It then uses an HTTP Request node to call the Jotform API, creating a brand-new, ready-to-use quiz form. Final Output: The final output provides the link to the newly created quiz, which can be shared immediately for submissions. Requirements To deploy this automated quiz generator, ensure you have the following accounts and credentials configured in your n8n instance: Jotform Credentials:* An *API Key* is required for both the *Jotform Trigger* (to start the workflow) and for the final *HTTP Request* (to create the new quiz form via the API). *Sign up for Jotform here:** https://www.jotform.com/?partner=zainurrehman Google Gemini API Key:* An API key for the *Google Gemini Chat Model* to power the *AI Agent** for question generation. Google Sheets Credentials:* An *OAuth2* or *API Key* credential for the *Google Sheets** node to save the generated questions. Initial Jotform:* A source Jotform that accepts the user input: a *File Upload* field, a *Text* field for the Quiz Title, and a *Number** field for the Number of Questions. Pro Tip: After the final HTTP Request, add an additional step (like an Email or Slack node) to automatically send the generated quiz link back to the user who submitted the initial request!

Description This n8n template turns any website or documentation portal into a fully functional AI-powered support chatbot — no manual copy-pasting, no static FAQs. It uses MrScraper to crawl and extract your site's content, OpenAI to generate embeddings, and Pinecone to store and retrieve that knowledge at chat time. The result is a retrieval-augmented chatbot that answers questions using only your actual website content, always cites its sources, and never hallucinates policies or pricing. How It Works Phase 1 – URL Discovery:** The Map Agent crawls your target domain using include/exclude patterns to discover all relevant documentation or help center pages. It returns a clean, deduplicated list of URLs ready for content extraction. Phase 2 – Page Content Extraction:** Each discovered URL is processed in controlled batches by the General Agent, which extracts the readable content (title + main text) from every page. Low-quality or near-empty pages are automatically filtered out. Phase 3 – Chunking & Embedding:** Page text is split into overlapping chunks (default: ~1,100 chars with 180-char overlap) to preserve context at boundaries. Each chunk is sent to OpenAI Embeddings to generate a vector, then stored in Pinecone with metadata including the source URL, page title, and chunk index. Phase 4 – Chat Endpoint:** A Chat Trigger exposes a webhook endpoint your website or widget can connect to. When a user asks a question, the Support Chat Agent queries Pinecone for the most relevant chunks and generates a grounded answer using GPT-4.1-mini — always with source URLs included and strict anti-hallucination rules enforced. How to Set Up Create 2 scrapers in your MrScraper account: Map Agent Scraper (for crawling and discovering page URLs) General Agent Scraper (for extracting title + content from each page) Copy the scraperId for each — you'll need these in n8n. Set up your Pinecone index: Create a Pinecone index with dimensions that match your chosen OpenAI embedding model (e.g. 1536 for text-embedding-ada-002) Choose a namespace (recommended format: docs-yourdomain) Add your credentials in n8n: MrScraper API token OpenAI API key (used for both embeddings and the chat model) Pinecone API key Configure the Map Agent node: Set your target domain or docs root URL (e.g. https://docs.yoursite.com) Set includePatterns to focus on relevant sections (e.g. /docs/, /help/, /support/) Optionally set excludePatterns to skip noise (e.g. /assets/, /tag/, /static/) Configure the General Agent node: Enter your General Agent scraperId Adjust the batch size in the SplitInBatches node (start with 1–5 to stay within rate limits) Configure the Pinecone nodes: Select your Pinecone index in both the Upsert and Retriever nodes Set the correct namespace in both nodes so indexing and retrieval use the same data Customise the chatbot system prompt: Edit the Support Chat Agent's system message to set the chatbot's name, tone, and rules Adjust topK in the Pinecone Retriever (default: 8) based on how much context you want per answer Connect your chat widget or frontend to the Chat Trigger webhook URL generated by n8n Requirements MrScraper** account with API access enabled OpenAI** account (for embeddings and GPT-4.1-mini chat) Pinecone** account with an index created and ready Good to Know The overlap between chunks (default 180 chars) is intentional — it prevents answers from being cut off at chunk boundaries and significantly improves retrieval quality. The chatbot is configured to cite 1–3 source URLs per answer, so users can always verify the information themselves. The anti-hallucination rules in the system prompt instruct the agent to say it can't find an answer rather than guess — making it safe to use for support, pricing, or policy questions. Re-indexing is as simple as re-running the workflow. Use a consistent Pinecone namespace and upsert mode to update existing vectors without duplicating them. Customising This Workflow Swap the chat model:** Replace GPT-4.1-mini with GPT-4o or another OpenAI model for higher-quality answers on complex queries. Scheduled re-indexing:** Add a Schedule Trigger to automatically re-crawl and re-index your docs whenever content changes. Multiple knowledge bases:** Use different Pinecone namespaces (e.g. docs-product, docs-api) and route questions to the right namespace based on user intent. Embed on your website:** Connect the Chat Trigger webhook to any chat widget library to give your users a live support experience powered entirely by your own documentation. Multilingual support:** Add a translation node before chunking to index content in multiple languages and serve a global audience.

This n8n workflow lets you effortlessly tailor your resume for any job using Telegram and LinkedIn. Simply send a LinkedIn job URL or paste a job description to the Telegram bot, and the workflow will: Extract the job information (using optional proxy if needed) Fetch your resume in JSON Resume format (hosted on GitHub Gist or elsewhere) Use an OpenRouter-powered LLM agent to automatically adapt your resume to match the job requirements Generate both HTML and PDF versions of your tailored resume Return the PDF file and shareable download links directly in Telegram The workflow is open-source and designed with privacy in mind. You can host the backend yourself to keep your data entirely under your control. It requires a Telegram Bot, a public JSON Resume, and an OpenRouter account. Proxy support is available for LinkedIn scraping. Perfect for anyone looking to quickly customize their resume for multiple roles with minimal manual effort!

Scrape & Import Products to Shopify from Any Site (with Variants & Images)-(Optimized for shoes) This advanced n8n template automates e-commerce operations by scraping product data (including variants and images) from any URL and creating fully detailed products in your Shopify store. This workflow is essential for dropshippers, e-commerce store owners, and anyone looking to quickly import product catalogs from specific websites into their Shopify store. Self-Hosted Only This Workflow uses a community contribution and is designed and tested for self-hosted n8n instances only. How it works The workflow reads a list of product page URLs from a Google Sheet. Your sheet, with its columns for Product Name and Product Link, acts as a database for your workflow. The Loop Over Items node processes products one URL at a time. Two BrowserAct nodes run sequentially to scrape all product details, including the Name, price, description, sizes, and image links. A custom Code node transforms the raw scraped data (where fields like sizes might be a single string) into a structured JSON format with clean lists for sizes and images. The Shopify node creates the base product entry using the main details. The workflow then uses a series of nodes (Set Option and Add Option via HTTP Request) to dynamically add product options (e.g., "Shoe Size") to the new product. The workflow intelligently uses HTTP Request nodes to perform two crucial bulk tasks: Create a unique variant for each available size, including a custom SKU. Upload all associated product images from their external URLs to the product. A final Slack notification confirms the batch has been processed. Requirements BrowserAct** API account for web scraping BrowserAct* "Bulk Product Scraping From (URLs) and uploading to Shopify (Optimized for shoe - NIKE -> Shopify)*" Template BrowserAct** n8n Community Node -> (n8n Nodes BrowserAct) Google Sheets** credentials for the input list Shopify** credentials (API Access Token) to create and update products, variants, and images Slack** credentials (optional) for notifications Need Help? How to Find Your BrowseAct API Key & Workflow ID How to Connect n8n to Browseract How to Use & Customize BrowserAct Templates How to Use the BrowserAct N8N Community Node Workflow Guidance and Showcase Automate Shoe Scraping to Shopify Using n8n, BrowserAct & Google Sheets