Emir Belkahia
Strategic Customer Success · Builder · Writer
Templates by Emir Belkahia
E-commerce bestseller video generator (Algolia + Google VEO 3)
E-commerce Weekly Bestseller Video Generator (Algolia + Google VEO 3) This workflow automatically identifies your weekly bestselling product from your Algolia-powered e-commerce store and generates a cinematic product video using Google VEO 3.0 AI, helping marketing teams create engaging video content without manual editing or expensive production tools. Who's it for E-commerce stores using Algolia for search. Ideal for marketing teams who want to automate video content creation for top-performing products and maximize conversion potential with engaging visual content. What it does (and doesn't do) ✅ It DOES: Identify your weekly bestseller automatically via Algolia custom ranking Validate product images before video generation Generate 6-second cinematic product videos using Google VEO 3.0 Store videos in Supabase for easy frontend integration Update Algolia records with video URLs automatically Send email alerts if products lack images ❌ It DOESN'T: Generate videos for all products at once Edit or customize videos after generation Create multi-product compilation videos Replace manual video editing for complex productions Work without Google Cloud Storage (VEO 3.0 requirement) Think of it as: An automated video production assistant that doubles down on your bestsellers with engaging content, not a full video editing suite. How it works Weekly trigger - Runs every Monday at 9:00 PM (or manually for testing) Bestseller fetch - Queries Algolia index with empty search to get top-ranked product Video check - Skips products that already have videos Image validation - Ensures product has a valid, accessible image URL Video generation - Converts image to base64 and sends to Google VEO 3.0 with cinematic prompt Polling loop - Waits and checks generation status until video is ready Storage transfer - Downloads MP4 from Google Cloud Storage and uploads to Supabase Index update - Marks product as having video and adds public URL to Algolia Set up steps Setup time: ~20 minutes Connect your Algolia credentials (Search API key + Application ID) Replace placeholders: ALGOLIAAPPID with your Algolia Application ID YOURINDEXNAME with your product index name PROJECT-ID-GOOGLE-CLOUD with your Google Cloud Project ID GOOGLESTORAGEBUCKET_NAME with your GCS bucket name YOURSUPABASEPROJECT with your Supabase project ID YOURBUCKETNAME with your Supabase bucket name admin@example.com with your email address Configure Algolia custom ranking (inStock + popularity recommended) Ensure your products have hasVideo, images[], name, description attributes Set up Google Vertex AI with VEO 3.0 API access Create Google Cloud Storage bucket for VEO 3.0 outputs Create Supabase storage bucket for final video hosting Requirements Algolia account with product index (free tier works) Algolia index with products containing image URLs Google Vertex AI account with VEO 3.0 API access Google Cloud Storage bucket (mandatory for VEO 3.0) Supabase account with storage bucket (free tier works) Gmail account for error notifications Products with attributes: hasVideo, images[], name, description, objectID Why both Google Cloud Storage AND Supabase? VEO 3.0 can only output videos as base64 strings or MP4 files in Google Cloud Storage. Base64 strings are too large for n8n to process (even with code nodes), making Google Cloud Storage mandatory. The workflow then downloads the MP4 and uploads it to Supabase because: Supabase is where your other product assets already live Supabase offers generous free tier and simpler pricing Easier to serve videos to your frontend from a single storage provider Think of Google Cloud Storage as a temporary staging area required by VEO 3.0's limitations, and Supabase as your actual production storage. Cost breakdown For a typical 6-second product video: Google VEO 3.0 generation: ~$0.15-0.30 per video Google Cloud Storage: ~$0.002 (temporary staging) Supabase storage: Free tier covers hundreds of videos 💰 Bottom line: About $0.15-0.30 per video. Running weekly for a year = $8-16 in video generation costs. 💡 Pro tips Customize the video prompt: The default prompt creates a cinematic studio dolly shot. Edit the jsonBody in "Generate video with Google VEO 3" to match your brand style (fast-paced, minimalist, lifestyle, etc.). Adjust bestseller logic: Modify the Algolia query to add filters like category:electronics or brand:Nike to focus on specific product segments. Use manual execution during setup: Don't wait until Monday! Run the workflow manually to catch configuration issues like broken image URLs or missing credentials immediately. Monitor your email alerts: If you frequently get "no image" or "broken image" alerts, audit your product data quality in Algolia. Missing images = lost video opportunities. Start with test products: Before going live, manually trigger the workflow on a product you know has good images. Verify the video appears correctly in your Supabase bucket and Algolia record. Check your GCS bucket occasionally: Videos accumulate in Google Cloud Storage after each run. Set up a lifecycle policy to auto-delete files older than 7 days to avoid unnecessary storage costs. Adjust the schedule: If Monday 9PM doesn't work for your team's workflow, change the trigger to run on a different day or time that aligns with your content calendar. How it identifies the bestseller This workflow leverages Algolia's custom ranking feature. When you send an empty search query to Algolia, the first result returned follows your custom ranking criteria. This is an Algolia best practice that ensures your most relevant products appear first even without search terms. In the example configuration, custom ranking uses: inStock attribute - Prioritizes available products popularity attribute - A computed metric based on sales volume, views, and other signals You'll need to configure your own custom ranking in your Algolia index settings to match your business criteria. The workflow assumes your index is already configured to return your bestselling product first when queried with no search terms.
By Emir BelkahiaGenerate LinkedIn activity reports via Slack commands with GPT-4.1 and email
This workflow helps Customer Success Managers and customer success professionals quickly gather intelligence on clients or prospects by analyzing their recent LinkedIn activity via a simple Slack command. Who's it for CSMs, Account Managers, and Sales professionals who need fast, structured insights about a person's LinkedIn presence before a call, meeting, or outreach. What it does (and doesn't do) ✅ It DOES: Fetch recent LinkedIn posts from any profile Analyze posting frequency and cadence patterns Identify top themes and focus areas Extract recent highlights with context Generate a clean HTML report sent via email ❌ It DOESN'T: Access private/non-public LinkedIn content Provide real-time updates (it's a snapshot) Replace actual researches when needed Think of it as: Your personal LinkedIn research assistant that turns a name into actionable intelligence in under a minute. How it works Slack command - Type /check-linkedin [Full Name] in Slack Name validation - AI verifies you provided a full name (not just "John") Profile discovery - Finds the correct LinkedIn profile via Apify Content scraping - Pulls their recent posts (last 20) AI analysis - GPT-4.1 analyzes posting patterns, topics, and highlights Report generation - Creates a formatted HTML email report Email delivery - Sends the intelligence brief to your inbox Set up steps Setup time: ~15 minutes Create or use your existing Slack app and add a Slash Command (it can be done here https://api.slack.com/apps) Configure the webhook URL in your Slack app Connect credentials: Slack OAuth Apify API OpenAI API Gmail OAuth Update the email recipient in "Send report via Email" node Test with a known LinkedIn profile Requirements Slack workspace (with app installation permissions) Apify account with credits OpenAI API key (GPT-4.1 access) Gmail account Apify actors: LinkedIn Profile Finder LinkedIn Post Scraper Cost estimation ~$0.05-0.09 per profile check. You could research 11-20 people for $1. ⚠️ Cost Disclaimer: The costs displayed above are indicative only and may vary significantly depending on which n8n actors you select. Some actors incur monthly charges—for example, one of the two actors used in this workflow costs $35/month. So, I recommend using this actor only when there's a clear business need for it. For cost optimization, consider switching to alternative actors that can deliver similar / simpler functionality at a lower cost. If you plan to use this workflow extensively, I strongly suggest performing a budget assessment and evaluating other actor options to maximize cost efficiency. The workflow uses GPT-4.1-mini for lightweight classification and GPT-4.1 for the heavy analysis to balance quality and cost. Known Limitations Common names have limited accuracy: Very common names (e.g., "John Smith") often fail to identify the correct person accurately. An improved version could support company name in the slash command as an additional input to help narrow down results and improve first-try matching accuracy. 💡 Pro tips Check before important meetings: Run this 15-30 minutes before a call. The email report gives you conversation starters and context about what they care about. Batch your research: If you have multiple clients or prospects, queue them up. Just remember each lookup costs ~$0.05-0.09. Watch your Apify credits: The LinkedIn scrapers are the main cost driver. Monitor your Apify usage if you're doing high volume. Don't spam the same profile: LinkedIn may rate-limit. Space out repeat checks on the same person by at least a few hours. Review the "Quick Scan" section first: The email report starts with key stats and top focus areas. Perfect for a 30-second pre-call prep. What to do after the workflow runs Check your email - Report arrives in 30-90 seconds Review the report - Latest post date, cadence, and top themes Read Recent Activity Summary - High-level overview of their content Dive into Detailed Analysis - Two main topics with keywords and rationale Use it strategically: Reference their recent posts in your outreach Ask about topics they're clearly passionate about Tailor your pitch to their demonstrated interests Avoid generic "saw you on LinkedIn" messages Questions or Feedback? 📧 emir.belkahia@gmail.com 💼 linkedin.com/in/emirbelkahia
By Emir BelkahiaAutomated weekly product promotion emails for e-commerce with Algolia and Gmail
Automated Weekly Newsletter for E-commerce Promotions (based on Algolia) This workflow automatically sends a beautifully designed HTML newsletter every Sunday at 8 AM, featuring products currently on sale from your Algolia-powered e-commerce store. Who's it for Perfect for e-commerce store owners, marketing teams, and anyone running promotional campaigns who wants to automate their weekly newsletter without relying on expensive email marketing platforms. How it works Triggers every Sunday at 8:00 AM - Scheduled to start each new promotion week Fetches discounted products - Queries your Algolia index for 6 products marked with on_sale:true Calculates promotion dates - Automatically generates the week's date range (Sunday to Saturday) Builds HTML newsletter - Populates a responsive email template with product images, prices, and descriptions Retrieves subscribers - Pulls the latest subscriber list from your Google Sheets Sends personalized emails - Delivers the newsletter to all subscribers via Gmail Set up steps Setup time: ~15 minutes Connect your Algolia credentials (Search API key + Application ID) Update the Algolia index name to match your store (currently set to dogtreatsprodproducts) Create a Google Sheet with subscriber emails (column named "Email") Connect your Google Sheets and Gmail accounts (Optional) Customize the HTML template colors and branding to match your store Requirements Algolia account with a product index containing onsale, priceeur, originalpriceeur, image, name, and description fields Google Sheets with subscriber list Gmail account for sending emails How to customize Change promotion criteria: Modify the filter in "Request products from Algolia" node (e.g., category:shoes instead of on_sale:true) Adjust product count: Change hitsPerPage value (currently 6) Modify schedule: Update the trigger node to run on different days/times Personalize email design: Edit the HTML template node to match your brand colors and style Add unsubscribe logic: Extend the workflow to handle unsubscribe requests 💡 Pro tip: Use the manual execution button to test the workflow mid-week - it's "smart" enough to calculate the current promotion week even when not running on Sunday.
By Emir BelkahiaValidate newsletter quality with GPT-5 quality gate before sending
Newsletter Quality Assurance with LLM Judge This sub-workflow validates newsletter quality before sending to customers. It's triggered by the main newsletter workflow and acts as an automated quality gate to catch data issues, broken layouts, or missing content. Who's it for E-commerce teams who want to automate newsletter quality checks and prevent broken or incomplete emails from reaching customers. Perfect for ensuring consistent brand quality without manual review. How it works Receives newsletter HTML - Triggered by parent workflow with the generated newsletter content Sends to test inbox - Delivers newsletter to LLM Judge's Gmail inbox to validate actual rendering Retrieves rendered email - Fetches the email back from Gmail to analyze how it actually renders (catches Gmail-specific issues) AI-powered validation - GPT-5 analyzes the newsletter against quality criteria: Verifies all 6 product cards have images, prices, and descriptions Checks layout integrity and date range formatting Detects broken images or unprocessed template variables Validates sale prices are lower than original prices Decision gate - Based on Judge's verdict: PASS: Returns approval to parent workflow → sends to customers BLOCK: Alerts admin via email → requires human review Set up steps Setup time: ~5 minutes Connect your Gmail account for sending test emails Update the Judge's email address in "Send newsletter to LLM Judge" node Update the admin alert email in error handling nodes Connect your OpenAI API credentials (GPT-5 recommended for heavy HTML processing) (Optional) Adjust quality thresholds in the Judge's system prompt Requirements Gmail account for test sends and retrieving rendered emails OpenAI API key (GPT-5 recommended) Parent workflow that passes newsletter HTML content How to customize Adjust validation strictness: Modify the Judge's system prompt to change what triggers BLOCK vs PASS Change product count: Update prompt if your newsletters have different numbers of products Add custom checks: Extend the system prompt with brand-specific validation rules Modify alert recipients: Update email addresses in error handling nodes 💡 Pro tip: The workflow validates the actual Gmail-rendered version to catch image loading issues and ensure consistent customer experience.
By Emir BelkahiaTransform voice notes into business reviews with Groq Whisper & GPT-5 to Google Slides
🎙️ Voice-to-Slides: Business Review Kickstarter for Customer Success This workflow helps Customer Success Managers brain dump their client knowledge via voice notes and kickstart business review preparation by auto-generating a structured Google Slides draft in their official slide deck template. Who's it for CSMs and Account Managers who want to capture meeting insights quickly via voice and get a head start on business review prep, not a finished presentation, but a solid first draft to build from. What it does (and doesn't do) ✅ It DOES: Transcribe your (potentially unstructured) voice notes accurately Organize your thoughts into Value Realized / Recommendations / Next Steps Create a Google Slides file in your official template Pre-populate placeholders with structured content ❌ It DOESN'T: Generate a client-ready presentation Add charts, metrics, or data visualizations Write polished, final copy Replace the actual work of crafting your business review Think of it as: A smart assistant that turns your brain dump into a structured starting point, not a finished product. How it works Brain dump via voice - Speak freely to your Telegram bot about your client: wins, challenges, recommendations, next steps (no need to be perfectly organized) AI transcription - Groq Whisper converts audio to text Security check - Scans for sensitive data (PII, confidential info) and alerts if found Content structuring - AI categorizes your rambling into three sections Review & approve - You receive an email with extracted content to validate and add client details Template generation - Creates a Google Slides from your template in the client's Drive folder First draft ready - Slides are populated with placeholders filled: now you refine, add data, polish Set up steps Setup time: ~20 minutes Create Telegram bot via @BotFather Prepare your own Google Slides template with placeholders: valuerealizedplaceholder recommendations_placeholder nextstepsplaceholder Connect credentials: Telegram, Groq, OpenAI, Gmail, Google Drive, Google Slides Update template ID in "Copy template to customer Folder" node Set your company name in "Set CSM's company name" node Add your email in all "human in the loop" nodes Requirements Telegram account Groq API key (Whisper transcription) OpenAI API key Google Workspace (Gmail, Drive, Slides) Google Slides template with required placeholders Client Google Drive folders (shared access) Cost breakdown For a typical 3-5 minute voice note: Transcription (Groq Whisper): Free AI Processing (GPT-5-nano + GPT-5-mini): ~$0.005 💰 Bottom line: Half a cent per business review. You could run 200+ business reviews for $1. The workflow uses cost-effective models (GPT-5-nano for security checks, GPT-5-mini for content extraction) to keep costs negligible while maintaining quality. Note: Costs may vary based on voice note length and verbosity. Prices based on GPT-5-Nano and GPT-5-Mini pricing as of Nov 2025. 💡 Pro tips Be mindful of the guardrail: It's designed to catch sensitive info (full names + company + financials), but it can sometimes be overzealous. If you find it blocking legitimate content, consider: Adjusting the confidence threshold (currently 0.7) to be less strict Removing the guardrail entirely if you're experienced and know what to avoid Reviewing the "Sensitive information" custom prompt to fine-tune detection rules Structure your thoughts loosely: While speaking, try to mentally organize around Value Realization → Recommendations → Next Steps. It's totally fine if things mix or overlap, the AI will reorganize, but having this structure in mind helps you cover everything. Record with your tools open: This is key! Have your previous BRs, CS platform, analytics dashboards, or CRM open while recording. Reference specific metrics, feature adoption rates, and data points directly from your systems. The AI can't look up data for you, feed it the good stuff. Don't overthink it: Your first recording will probably feel awkward. That's normal. The AI is surprisingly good at cleaning up "umms," tangents, and unstructured rambling. Just brain dump. Keep it under 5 minutes: Better transcription accuracy, faster processing, and cheaper API costs. If you have more to say, split into multiple voice notes. Review the email summary carefully: The AI extracts content well but loses the nuance and context you have. Use the email review step to catch misinterpretations before they hit the slides. What to do after the workflow runs Open the generated slides in the client's folder Refine the AI-generated text (add nuance, fix tone) Add charts, screenshots, data visualizations Polish formatting and visual hierarchy
By Emir Belkahia