Workflow Templates

Introduction Automate peer review assignment and grading with AI-powered evaluation. Designed for educators managing collaborative assessments efficiently. How It Works Webhook receives assignments, distributes them, AI generates review rubrics, emails reviewers, collects responses, calculates scores, stores results, emails reports, updates dashboards, and posts analytics to Slack. Workflow Template Webhook → Store Assignment → Distribute → Generate Review Rubric → Notify Slack → Email Reviewers → Prepare Response → Calculate Score → Store Results → Check Status → Generate Report → Email Report → Update Dashboard → Analytics → Post to Slack → Respond to Webhook Workflow Steps Receive & Store: Webhook captures assignments, stores data. Distribute & Generate: Assigns peer reviewers, AI creates rubrics. Notify & Email: Alerts via Slack, sends review requests. Collect & Score: Gathers responses, calculates peer scores. Report & Update: Generates reports, emails results, updates dashboard. Analyze & Alert: Posts analytics to Slack, confirms completion. Setup Instructions Webhook & Storage: Configure endpoint, set up database. AI Configuration: Add OpenAI key, customize rubric prompts. Communication: Connect Gmail, Slack credentials. Dashboard: Link analytics platform, configure metrics. Prerequisites OpenAI API key Gmail account Slack workspace Database or storage system Dashboard tool Use Cases University peer review assignments Corporate training evaluations Research paper assessments Customization Multi-round review cycles Custom scoring algorithms LMS integration (Canvas, Moodle) Benefits Eliminates manual distribution Ensures consistent evaluation Provides instant feedback and analytics

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Accelerate your research analysis with this Automated Research Intelligence System! This workflow uses AI and web scraping to analyze research papers and articles, extracting key insights, validating content quality, and generating comprehensive research documents. Perfect for research teams, academics, and AI enthusiasts staying current with the latest developments in artificial intelligence and machine learning. What This Template Does Triggers via form submission for on-demand research URL analysis. Validates URL accessibility and prepares for processing. Uses Decodo scraper to extract research content from target URLs. Analyzes research papers with AI for comprehensive understanding. Validates summaries for accuracy, completeness, and relevance. Generates key insights and actionable takeaways from research. Creates professional Google Docs with formatted research summaries. Evaluates research quality with AI-powered rating system. Saves all research to Google Sheets for historical tracking. Sends Slack alerts for high-quality research findings (9+ rating). Key Benefits Automated research analysis saves hours of manual reading time AI-powered insights extraction from complex research papers Quality validation ensures accurate and relevant summaries Centralized research database for team collaboration Real-time alerts for breakthrough research findings Professional documentation automatically generated Features Form-based trigger for easy research submission URL validation and accessibility checking AI-powered research analysis and summarization Decodo web scraping for reliable content extraction Multi-stage validation for accuracy and relevance Automated Google Docs report generation Quality assessment with structured rating system Google Sheets integration for research tracking Slack notifications for premium research findings Quality threshold filtering for optimal results Requirements Decodo API credentials for research scraping OpenAI API credentials for AI analysis Google Docs OAuth2 credentials for document creation Google Sheets OAuth2 credentials with edit access Slack Bot Token with chat:write permission Environment variables for configuration settings Target Audience AI research teams and data scientists Academic researchers and university labs Machine learning engineers and developers Technology innovation teams Research and development departments Content creators in AI/ML space Step-by-Step Setup Instructions Connect Decodo API credentials for research scraping functionality Set up OpenAI credentials for AI analysis and quality assessment Configure Google Docs for automated research document generation Add Google Sheets credentials for research tracking and history Set up Slack credentials for high-quality research alerts Customize quality thresholds for research rating (default: 6+ for processing, 9+ for alerts) Test with sample research URLs to verify analysis and formatting Deploy the form for team access to research analysis requests Monitor research database for trends and insights Pro Tip: Use coupon code "YARON" for free Decodo credits to enhance your research intelligence capabilities! This workflow transforms complex research into actionable intelligence with automated analysis, quality validation, and professional documentation!

Overview The workflow automatically gathers weekly user and page view metrics. It then uses AI to analyze, compare, and compile a summary report. Finally, it sends the report to the manager's email. How it works Get Data from GA Automatically retrieve data from Google Analytics (GA) for the two most recent weeks. Compare the data and calculate the variances between the two weeks. Generate Report Automatically analyze the data and generate reports using Artificial Intelligence (AI). Generate charts to visualize the data. Export the report to PDF. Send Report Send the report via email to the manager. Set up steps Google cloud account Create the credentials and replace them in the workflow. Please enable the following APIs: Gmail API Google Analytics Admin API Google Analytics Data API HTML to PDF account You need to install node HTML to PDF. Get API key and replace in the workflow.

This workflow is designed to automatically process AI news emails, extract and summarize articles, categorize them, and store the results in a structured Google Sheet for daily tracking and insights. This automated workflow processes a daily AI newsletter from AlphaSignal, extracting individual articles, summarizing them, categorizing them, and saving the results to a Google Sheet. Key Features 1. ✅ Fully Automated Daily News Pipeline No manual work is required — the workflow runs autonomously every time a new email arrives. This eliminates repetitive human tasks such as opening, reading, and summarizing newsletters. 2. ✅ Cross-AI Model Integration It combines multiple AI systems: Google Gemini* and *OpenAI GPT-5 Mini** for natural language processing and categorization. Scrapegraph AI** for external web scraping and summarization. This multi-model approach enhances accuracy and flexibility. 3. ✅ Accurate Content Structuring The workflow transforms unstructured email text into clean, structured JSON data, ensuring reliability and easy export or reuse. 4. ✅ Multi-Language Support The summaries are generated in Italian, which is ideal for local or internal reporting, while the metadata and logic remain in English — enabling global adaptability. 5. ✅ Scalable and Extensible New newsletters, categories, or destinations (like Notion, Slack, or a database) can be added easily without changing the core logic. 6. ✅ Centralized Knowledge Repository By appending to Google Sheets, the team can: Track daily AI developments at a glance. Filter or visualize trends across categories. Use the dataset for further analysis or content creation. 7. ✅ Error-Resilient and Maintainable The JSON validation and loop-based design ensure that if a single article fails, the rest continue to process smoothly. How it Works Email Trigger & Processing: The workflow is automatically triggered when a new email arrives from news@alphasignal.ai. It retrieves the full email content and converts its HTML body into clean Markdown format for easier parsing. Article Extraction & Scraping: A LangChain Agent, powered by Google Gemini, analyzes the newsletter's Markdown text. Its task is to identify and split the content into individual articles. For each article it finds, it outputs a JSON object containing the title, URL, and an initial summary. Crucially, the agent uses the "Scrape" tool to visit each article's URL and generate a more accurate summary in Italian based on the full page content. Data Preparation & Categorization: The JSON output from the previous step is validated and split into individual data items (one per article). Each article is then processed in a loop: Categorization: An OpenAI model analyzes the article's title and summary, assigning it to the most relevant pre-defined category (e.g., "LLM & Foundation Models," "AI Automation & WF"). URL Shortening: The article's link is sent to the CleanURI API to generate a shortened URL. Data Storage: Finally, for each article, a new row is appended to a specified Google Sheet. The row includes the current date, the article's title, the shortened link, the Italian summary, and its assigned category. Set up Steps To implement this workflow, you need to configure the following credentials and nodes in n8n: Email Credentials: Set up a Gmail OAuth2 credential (named "Gmail account" in the workflow) to allow n8n to access and read emails from the specified inbox. AI Model APIs: Google Gemini: Configure the "Google Gemini(PaLM)" credential with a valid API key to power the initial article extraction and scraping agent. OpenAI: Configure the "OpenAi account (Eure)" credential with a valid API key to power the article categorization step. Scraping Tool: Set up the ScrapegraphAI account credential with its required API key to enable the agent to access and scrape content from the article URLs. Google Sheets Destination: Configure the "Google Sheets account" credential via OAuth2. You must also specify the exact Google Sheet ID and sheet name (tab) where the processed article data will be stored. Activation: Once all credentials are tested and correctly configured, the workflow can be activated. It will then run automatically upon receiving a new newsletter from the specified sender. Need help customizing? Contact me for consulting and support or add me on Linkedin.

This automated workflow monitors your website's keyword rankings daily and sends instant alerts to your team when significant ranking drops occur. It fetches current ranking positions, compares them with historical data, and triggers notifications through Slack and email when keywords drop beyond your defined threshold. Good to know The workflow uses SERP API for accurate ranking data; API costs apply based on your usage volume Ranking checks are performed daily to avoid overwhelming search engines with requests The system tracks ranking changes over time and maintains historical data for trend analysis Slack integration requires workspace permissions and proper bot configuration False positives may occur due to personalized search results or data center variations How it works Daily SEO Check Trigger** initiates the workflow on a scheduled basis Get Keywords Database** retrieves your keyword list and current ranking data Filter Active Keywords Only** processes only keywords marked as active for monitoring Fetch Google Rankings via SERP API** gets current ranking positions for each keyword Wait For Response** Wait for gets current ranking positions Parse Rankings & Detect Changes** compares new rankings with historical data and identifies significant drops Filter Significant Ranking Drops** isolates keywords that dropped beyond your threshold (e.g., 5+ positions) Send Slack Ranking Alert** notifies your team channel about ranking drops Send Email Ranking Alert** sends detailed email reports to stakeholders Update Rankings in Google Sheet** saves new ranking data for historical tracking Generate SEO Monitoring Summary** creates a comprehensive report of all ranking changes How to use Import the workflow into n8n and configure your SERP API credentials Set up your Google Sheet with the required keyword database structure Configure Slack webhook URL and email SMTP settings Define your ranking drop threshold (recommended: 5+ position drops) Test the workflow with a small keyword set before full deployment Schedule the workflow to run daily during off-peak hours Requirements SERP API account** with sufficient credits for daily keyword checks Google Sheets access** for keyword database and ranking storage Slack workspace** with webhook permissions for team notifications Email service** (SMTP or API) for stakeholder alerts Keywords database** properly formatted in Google Sheets Database/Sheet Columns Required Google Sheet: "Keywords Database" Create a Google Sheet with the following columns: | Column Name | Description | Example | |-------------|-------------|---------| | keyword | Target keyword to monitor | "best seo tools" | | domain | Your website domain | "yourwebsite.com" | | current_rank | Latest ranking position | 5 | | previous_rank | Previous day's ranking | 3 | | status | Monitoring status | "active" | | target_url | Expected ranking URL | "/best-seo-tools-guide" | | search_volume | Monthly search volume | 1200 | | difficulty | Keyword difficulty score | 65 | | date_added | When keyword was added | "2025-01-15" | | last_checked | Last monitoring date | "2025-07-30" | | drop_threshold | Custom drop alert threshold | 5 | | category | Keyword grouping | "Product Pages" | Customising this workflow Modify ranking thresholds** in the "Filter Significant Ranking Drops" node to adjust sensitivity (e.g., 3+ positions vs 10+ positions) Add competitor monitoring** by duplicating the SERP API node and tracking competitor rankings for the same keywords Customize alert messages** in Slack and email nodes to include your brand voice and specific stakeholder information Extend to multiple search engines** by adding Bing or Yahoo ranking checks alongside Google Implement ranking improvement alerts** to celebrate when keywords move up significantly Add mobile vs desktop tracking** by configuring separate SERP API calls for different device types

AI-Powered Invoice Processing from Gmail to Google Sheets with Slack Approval This workflow completely automates your invoice processing pipeline. It triggers when a new invoice email arrives in Gmail, uses AI to extract key data from the PDF attachment, logs it in a Google Sheet, and sends a request to Slack with simple links for one-click approval or rejection. Who's it for? This template is perfect for small business owners, finance teams, freelancers, and anyone looking to eliminate the manual work of processing invoices. It saves hours of data entry, reduces human error, and streamlines the approval process. How it works Trigger: The workflow starts when an email with a specific subject (e.g., "Invoice") arrives in Gmail. Extraction: It automatically downloads the first PDF attachment from the email and extracts all its text content. AI Processing: The extracted text is sent to an AI model, which intelligently identifies and pulls out key details: invoice number, issue date, company name, total amount, and due date. Logging: This structured data is appended as a new row in your Google Sheet. The status is automatically set to "pending". The full, raw text from the PDF is also saved for easy verification. Approval Request: A formatted message is sent to a designated Slack channel. This message includes the key invoice details and two unique links: one to approve and one to reject the invoice. Handle Response: When a user clicks either the "Approve" or "Reject" link, the corresponding Webhook in the workflow is triggered. Update Sheet: The workflow finds the correct row in the Google Sheet using the invoice number and updates its status to "approved" or "rejected". Confirmation: A final confirmation message is sent to the Slack channel, closing the loop and informing the team of the action taken. How to set up Credentials: Add your credentials for Gmail, OpenAI, Google Sheets, and Slack in the designated nodes. Gmail Trigger: In the "1. New Invoice Email Received" node, change the search query q from "incoice" to the keyword you use for invoice emails (e.g., "invoice"). Google Sheets: In the three Google Sheets nodes ("6. Log Invoice...", "9a. Update Status to Approved", and "9b. Update Status to Rejected"), enter your Google Sheet ID and the name of the sheet. Slack: In the three Slack nodes ("7. Send Approval Request...", "10a. Send Approval Confirmation", and "10b. Send Rejection Confirmation"), enter your Slack Channel ID. Webhook URLs: First, activate the workflow using the toggle in the top-right corner. Open the "Webhook (Approve)" node, go to the Production URL tab, and copy the URL. Paste this URL into the "7. Send Approval Request to Slack" node, replacing the https://YOUR_WEBHOOK_BASE_URL/webhook/approval part of the approval link. Repeat this process for the "Webhook (Reject)" node and the rejection link. Activate Workflow: Ensure the workflow is active for the Webhooks to work continuously. How to customize AI Prompt: You can modify the prompt in the "5. Extract Invoice Data with AI" node to extract different or additional fields to match your specific invoice formats. Slack Messages: Feel free to customize the text in all three Slack nodes to better fit your team's tone and communication style.

This workflow is the AI analysis and alerting engine for a complete social media monitoring system. It's designed to work with data scraped from X (formerly Twitter) using a tool like the Apify Tweet Scraper, which logs the data into a Google Sheet. The workflow then automatically analyzes new tweets with Google Gemini and sends tailored alerts to Slack. How it works This workflow automates the analysis and reporting part of your social media monitoring: tweet Hunting:** It finds tweets for the query entered in the set node and passes the data to the google sheets Fetches New Tweets:** It gets all new rows from your Google Sheet that haven't been processed yet (it looks for "Notmarked" in the 'action taken' column). Prepares for AI:** It combines the data from all new tweets into a single, clean prompt for the AI to analyze. AI Analysis with Gemini:* It sends the compiled data to Google Gemini, asking for a full summary report *and a separate, machine-readable JSON list of any urgent items. Splits the Response:** The workflow intelligently separates the AI's text summary from the JSON data for urgent alerts. Sends Notifications:** The high-level summary is sent to a general Slack channel (e.g., #brand-alerts). Each urgent item is sent as a separate, detailed alert to a high-priority Slack channel (e.g., #urgent). Set up steps It should take about 5-10 minutes to get this workflow running. Prerequisite - Data Source: Ensure you have a Google Sheet being populated with tweet data. For a complete automation, you can set up a new google sheet with the same structure for saving the tweets data and run the Tweet Scraper on a schedule. Configure Credentials: Make sure you have credentials set up in your n8n instance for Google Sheets, Google Gemini (PaLM) API, and Slack. Google Sheets Node ("Get row(s) in sheet"): Select your Google Sheet containing the tweet data. Choose the specific sheet name from the dropdown. Ensure your sheet has a column named action taken so the filter works correctly. Google Gemini Chat Model Node: Select your Google Gemini credential from the dropdown. Slack Nodes ("Send a message" & "Send a message1"): In the first Slack node, choose the channel for the summary report. In the second Slack node, choose the channel for urgent alerts. Save and Activate: Once configured, save your workflow and turn it on!

This workflow automates the entire process of running a Print-on-Demand (POD) business by combining market trend analysis with autonomous AI design and quality control. It acts as a virtual product team that researches, designs, vets, and publishes new products to your store every week. Who is it for? This template is ideal for e-commerce entrepreneurs, content creators, and print-on-demand store owners who want to scale their merchandise inventory without spending hours on design and market research. What it does Market Research: Fetches real-time search data from Google Trends and customer preference data from Typeform. AI Design: Uses OpenAI (GPT-4o) to brainstorm t-shirt concepts based on the gathered trends, then generates high-quality vector-style images using Replicate (Flux/Stable Diffusion). Quality Control: A "Vision AI" agent analyzes the generated image, rates it on a scale of 1-10, and filters out any design scoring below 7. Dynamic Pricing & Publishing: Automatically calculates a premium price for higher-rated designs and publishes the product directly to your Printify store. Logging: Saves the product details to Airtable for your records. How to set up Configure Credentials: Open the "Workflow Configuration" node. Replace the placeholder values with your API keys for OpenAI, Replicate, Printify, and Typeform. Set Printify Details: In the "Workflow Configuration" node, add your Shop ID. In the "Publish to Printify" node, update the blueprint_id (the specific t-shirt model, e.g., Bella+Canvas 3001) and print_provider_id. Airtable Setup: Create a table with columns for Title, Description, Price, Quality Score, and Image URL, then map the IDs in the Airtable node. Requirements n8n: Cloud or Self-hosted instance. API Keys: OpenAI (with GPT-4o access), Replicate, Printify, Typeform, and Airtable. Printify Account: A connected store (e.g., Shopify, Etsy, or Pop-up). How to customize Prompt Engineering: Modify the "Chief Designer AI" system prompt to change the artistic style (e.g., from "vector" to "pixel art" or "vintage"). Pricing Logic: Adjust the JavaScript in the "Dynamic Pricing Calculator" to change your base margins or markup rules. Schedule: Change the "Weekly Schedule Trigger" to run daily or monthly depending on your volume needs.

Send personalized pet care tips from Google Sheets with AI Automate weekly pet wellness emails with AI-generated, location and age-specific advice. Who's it for Pet care businesses, veterinary clinics, pet subscription services, and animal shelters sending regular wellness content to pet owners. How it works Loads pets data from Google Sheets Filters pets who haven't received email in 7+ days Calculates age from birthdate (formats as "2 years and 3 months") AI generates tip - GPT-4o-mini creates climate-aware, veterinary-aligned advice based on pet type, age, and location Sends email via Gmail or SendGrid Updates timestamp in sheet to prevent duplicates Logs activity to tracking sheet Requirements APIs: Google Sheets, Airtable, Typeform or similar OpenAI (GPT-4o-mini) Gmail OAuth2 OR SendGrid, you can use Brevo, Mailchimp or any other. Google Sheet Structure: Sheet 1: Pets | Email | Owner_Name | Pet_Name | Pet_Type | Date_of_Birth | Country (ISO) | Status | Last_Email_Sent | |-------|------------|----------|----------|---------------|---------------|--------|-----------------| Sheet 2: Email_Log | Timestamp | Parent_Email | Pet_Name | Tip_Category | Status | |-----------|--------------|----------|--------------|--------| How to set up Create Google Sheet with structure above, add 2-3 test pets. Import workflow and add credentials. Update nodes: "Load Pet Info": Set your Sheet ID "Update Last_Email_Sent Date": Set Sheet ID "Log to Email_Log Sheet": Set Sheet ID Test manually with 1 active pet Enable schedule (default: Mondays 9am) How to customize Switch email provider: Enable "Send via SendGrid" node Disable "Send Health Tip using Gmail" node Update template ID Modify AI prompt: Edit "Generate Personalized Tip" node Adjust temperature Add/remove categories Use cases beyond pets Same workflow works for: Plant care** (growth stage tips) Baby milestones** (age-based parenting advice) Fitness coaching** (experience level workouts) Language learning** (study streak motivation) Just update sheet columns and AI prompt. Notes Choose only one mailing service. Country codes use ISO format (US, UK, AU, CA, etc.) AI considers location for seasonal advice.

Description Fully automated pipeline where you send an email to yourself with a rough idea (subject contains “thread”), n8n’s Gmail trigger picks it up, OpenAI ChatGPT rewrites/apply a viral-thread template, and Blotato posts the long-form thread to X/Twitter, Bluesky, and Meta Threads (optionally schedule or include images/videos). Template is easily extensible to other social platforms. Who Is This For? Digital creators, content marketers, social media managers, agencies, entrepreneurs, and influencers who want fast, automated long-form thread posting. 📄 Documentation Full Step-by-Step Tutorial How It Works 1. Trigger: Gmail Connect your Gmail account. n8n monitors emails sent from you and filters for subjects containing the word “thread”. 2. AI Thread Writer: OpenAI ChatGPT Connect your OpenAI account. Prompt ChatGPT to clean up your draft and format a long-form viral thread. 3. Publish to Social Media via Blotato Connect your Blotato account and choose social accounts (X/Twitter, Threads, Bluesky). Schedule or post immediately. Supports optional image/video URLs via a mediaUrls array (publicly accessible URLs). Example email to trigger the workflow: Email Subject: thread Email Body: I'm obsessed with voice AI apps. Super Whisper is my current favorite because it runs locally and keeps my voice data private. I talk to it instead of typing. Way faster. Setup & Required Accounts Gmail account (used as trigger) n8n Gmail OAuth doc: https://docs.n8n.io/integrations/builtin/credentials/google/oauth-single-service OpenAI Platform account (access to ChatGPT) Blotato account: https://blotato.com Generate Blotato API Key: Settings > API > Generate API Key (paid feature only) Sign in to Blotato and create an API Key (required for posting) n8n: Ensure "Verified Community Nodes" enabled in your n8n Admin Panel Install the "Blotato" community node and create Blotato credentials Optional: Media & Style Tweaks Attach images/videos: insert publicly accessible URLs into the mediaUrls array (advanced). To emulate a specific tone/structure, provide ChatGPT examples of your favorite viral threads or replace the example viral-thread prompt with your preferred example. Voice-to-text tip: record ideas (e.g., Superwhispr) and send the transcript by email — ChatGPT will clean it up. Tips & Tricks During testing, use “Scheduled Time” in Blotato instead of immediate posting to preview before going live. Start with a single social platform while testing. If your script is long or includes media, processing may take longer. Many users prefer speaking their ideas (voice notes) then letting AI edit — faster than typing. Troubleshooting Check your Blotato API Dashboard to inspect each request, response, and error. Confirm API key validity, n8n node credentials, and that emails sent have subject containing “thread”. Need Help? In the Blotato web app, click the orange support button in the bottom right to access Blotato support.

🎯 Accounting Alerts Automation Purpose: Automatically track Companies House filing deadlines for UK accounting firms and prevent costly penalties (£150-£1,500 per missed deadline). How it works: Daily automated checks pull live deadline data from Companies House API Color-coded email alerts (Red/Orange/Yellow/Green) prioritize urgent deadlines Interactive "Yes/No" buttons let recipients confirm completion status All data syncs back to Google Sheets for complete audit trail Value: Saves 2-3 hours/week per firm while eliminating manual tracking errors. ⚙️ Daily Deadline Check & Alert System Runs: Every weekday at 5 PM (Mon-Fri) What happens: Read Company Database - Fetches all tracked companies from Google Sheets Get Company Data - Pulls live filing deadlines from Companies House API for each company Update Due Dates - Syncs latest deadline data back to the tracking sheet Build Interactive Email - Creates HTML email with: Color-coded urgency indicators (days remaining) Sortable table by due date Clickable Yes/No confirmation buttons for each company Send via Gmail - Delivers consolidated report to accounting team Why automated: Manual deadline checking across 10-50+ companies is time-consuming and error-prone. This ensures nothing falls through the cracks. ✅ Email Response Handler (Webhook Flow) Triggered when: Recipient clicks "Yes" or "No" button in the alert email What happens: Webhook - Receives confirmation status (company_number, company_name, yes/no) Process Data - Extracts response details from the webhook payload Update Sheet - Records confirmation status in Google Sheets with timestamp Confirmation Page - Displays success message to user Why this matters: Provides instant feedback to the user and creates an audit trail of who confirmed what and when. No separate tracking system needed—everything updates automatically in the same spreadsheet. Result: Accountability without administrative burden. 📋 Setup Requirements Google Sheets Database Structure: Create a sheet with these columns: company_number (manually entered) company_name (manually entered) accounts_due (auto-updated) confirmation_due (auto-updated) confirmation_submitted (updated via email clicks) last_updated (auto-timestamp) Required Credentials: Google Sheets OAuth (for reading/writing data) Companies House API key (free from api.company-information.service.gov.uk) Gmail OAuth (for sending alerts) Webhook Configuration: Update webhook URL in "Build Interactive Email" node to match your n8n instance. Time to Setup: ~15 minutes once credentials are configured.

Shopify Multilingual Product Copy with n8n & Gemini 2.5 Flash-Lite Use for free Created by <Weiser22> · Last update 2025-09-02 Categories: E-commerce, Product Content, Translation, Computer Vision Description Generate language-specific Shopify product copy (ES, DE, EN, FR, IT, PT) from each product’s main image and metadata. The workflow performs a vision analysis to extract objective, verifiable details, then produces product names, descriptions, and handles per language, and stores the results in Google Sheets for review or publishing. Good to know Model:** models/gemini-2.5-flash-lite (supports image input). Confirm pricing/limits in your account before scaling. Image requirement:** products should have images[0].src; add a fallback if some products lack a primary image. Sheets mapping:** the sheet node uses Auto-map; ensure your matching column aligns with the field you emit (id vs product_id). Strict output:** the Agent enforces a multilingual JSON contract (es,de,en,fr,it,pt), each with shopify_product_name, shopify_description, handle. How it works Manual Trigger:** start a test run on demand. Get many products (Shopify):** fetch products and their images. Analyze image (Gemini Vision):** send images[0].src with an objective, 3–5 sentence prompt. AI Agent (Gemini Chat):** merge Shopify fields + vision text under anti-hallucination rules and a strict JSON schema. Structured Output Parser:** validates the exact JSON shape. Expand Languages & Sanitize (Code):** split into 6 items and normalize handles/HTML content as needed. Append row in sheet (Google Sheets):** add one row per language to your spreadsheet. Requirements Shopify Access Token with product read permissions. Google AI Studio (Gemini) API key for Vision + Chat Model nodes. Google Sheets credentials (OAuth or Service Account) with access to the target spreadsheet. How to use Connect credentials: Shopify, Gemini (same key for Vision and Chat), and Google Sheets. Configure nodes: Get many products: adjust limit/filters. Analyze image: verify ={{ $json.images[0].src }} resolves to a public image URL. AI Agent & Parser: keep the strict JSON contract as provided. Code (Expand & Sanitize): emits product_id, lang, handle, shopify_product_name, shopify_description, base_handle_es. Google Sheets (Append): set documentId and tab name; confirm the matching column. Run a test: execute the workflow and confirm six rows per product (one per language) appear in the sheet. Data contract (Agent output) { "es": {"shopify_product_name": "", "shopify_description": "", "handle": ""}, "de": {"shopify_product_name": "", "shopify_description": "", "handle": ""}, "en": {"shopify_product_name": "", "shopify_description": "", "handle": ""}, "fr": {"shopify_product_name": "", "shopify_description": "", "handle": ""}, "it": {"shopify_product_name": "", "shopify_description": "", "handle": ""}, "pt": {"shopify_product_name": "", "shopify_description": "", "handle": ""} } Customising this workflow Publish to Shopify:** after review in Sheets, add a product.update step to write finalized copy/handles. Handle policy:** tweak slug rules (diacritics, separators, max length) in the Code node to match store conventions. No-image fallback:** add an IF/Switch to skip vision when images[0].src is missing and generate copy from title + body only. Tone/length:** adjust temperature and token limits on the Chat Model for brand-fit. Troubleshooting No rows in Sheets:** confirm spreadsheet ID, tab name, Auto-map status, and that the matching column matches your emitted field. Vision errors:** ensure images[0].src is reachable. Parser failures:* the Agent must return *bare JSON** with the six root keys and three fields per language—no extra text.