David Olusola
I design enterprise-grade automation systems that eliminate bottlenecks, cut manual work by 70%+, and unlock millions in lost revenue opportunities. My clients โ typically achieve 5โ10x ROI within the first 90 days. Currently partnering with select high-growth companies ready to scale faster with AI automation. david@daexai.com
Categories
Templates by David Olusola
Email support agent w/ Gemini & GPT fallback using Gmail + Google Sheets
๐ง Master Your First AI Email Agent with Smart Fallback! Welcome to your hands-on guide for building a resilient, intelligent email support system in n8n! This workflow is specifically designed as an educational tool to help you understand advanced AI automation concepts in a practical, easy-to-follow way. --- ๐ What You'll Learn & Build: This powerful template enables you to create an automated email support agent that: Monitors Gmail for new customer inquiries in real-time. Processes requests using a primary AI model (Google Gemini) for efficiency. Intelligently falls back to a secondary AI model (OpenAI GPT) if the primary model fails or for more complex queries, ensuring robust reliability. Generates personalized and helpful replies automatically. Logs every interaction meticulously to a Google Sheet for easy tracking and analysis. --- ๐ก Why a Fallback Model is Game-Changing (and Why You Should Learn It): Unmatched Reliability (99.9% Uptime): If one AI service experiences an outage or rate limits, your automation seamlessly switches to another, ensuring no customer email goes unanswered. Cost Optimization: Leverage more affordable models (like Gemini) for standard queries, reserving premium models (like GPT) only when truly needed, significantly reducing your API costs. Superior Quality Assurance: Get the best of both worlds โ the speed of cost-effective models combined with the accuracy of more powerful ones for complex scenarios. Real-World Application: This isn't just theory; it's a critical pattern for building resilient, production-ready AI systems. --- ๐ Perfect for Beginners & Aspiring Automators: Simple Setup: With drag-and-drop design and pre-built integrations, you can get this workflow running with minimal configuration. Just add your API keys! Clear Educational Value: Learn core concepts like AI model orchestration strategies, customer service automation best practices, and multi-model AI implementation patterns. Immediate Results: See your AI agent in action, responding to emails and logging data within minutes of setup. --- ๐ ๏ธ Getting Started Checklist: To use this workflow, you'll need: A Gmail account with API access enabled. A Google Sheets document created for logging. A Gemini API key (your primary AI model). An OpenAI API key (your fallback AI model). An n8n instance (cloud or desktop). --- Embark on your journey to building intelligent, resilient automation systems today!
By David OlusolaAutomate AI news videos to social media with GPT-4o & HeyGen and Postiz
๐ค Automated AI News Video Creation and Social Media Publishing Workflow โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ ๐ฏ Overview: This workflow fully automates the creation and social media distribution of AI-generated news videos. It fetches news, crafts captions, generates avatar videos via HeyGen, stores them, and publishes them across Instagram, Facebook, and YouTube via Postiz. --- ๐ WORKFLOW PROCESS: News Fetching: Reads the latest news from an RSS feed. AI Captioning: Generates concise, engaging captions using an AI agent (GPT-4o-mini). Video Generation: Creates an AI avatar video using HeyGen with the generated caption. Video Storage: Downloads the video and uploads it to Google Drive for archival. Data Logging: Records all news and video metadata into Google Sheets. Postiz Upload: Uploads the video to Postiz's internal storage for publishing. Social Publishing: Fetches Postiz integrations and routes the video to Instagram, Facebook, and YouTube after platform-specific content cleaning. --- โ๏ธ KEY TECHNOLOGIES: RSS Feeds: News source. LangChain (n8n nodes): AI Agent and Chat OpenAI for caption generation. HeyGen API: AI avatar video creation. Google Drive: Video file storage. Google Sheets: Data logging and tracking. Postiz API: Unified social media publishing platform. --- โ ๏ธCRITICAL CONFIGURATIONS: API Keys: Ensure HeyGen and Postiz API keys are correctly set in credentials and the 'Setup Heygen Parameters' node. HeyGen IDs: Verify avatarid and voiceid in 'Setup Heygen Parameters'. Postiz URL: Confirm https://postiz.yourdomain.com is your correct Postiz instance URL across all HTTP Request nodes. Credentials: All Google, OpenAI, and Postiz credentials must be properly linked. --- ๐BENEFITS: Automated content creation and distribution, saving significant time. Consistent branding and messaging across multiple platforms. Centralized logging for tracking and performance analysis. Scalable solution for high-volume content demands. ---
By David OlusolaAI-powered file management automation for Google Drive with MCP
This workflow contains community nodes that are only compatible with the self-hosted version of n8n. ๐ Google Drive MCP Workflow โ AI-Powered File Management Automation ๐ ๐ง Overview A secure and intelligent n8n workflow that connects with Google Drive via MCP (Model Control Protocol). Ideal for AI agent tasks, compliance-driven storage, and document automation. ๐ Key Features ๐ Built-In Safety Backs up files before edits (timestamped) Supports rollback using file history Validates file size, type, and permissions ๐ Smart Organization Automatically converts file types (PDF, DOCX, etc.) Moves files to structured folders Auto-archives old files based on age or rules ๐ MCP Integration Accepts standardized JSON via webhook Real-time execution for AI agents Fully customizable input (action, fileId, format, etc.) โ AI Callable MCP Actions These are the commands AI agents can perform via MCP: Download a file (with optional format conversion) Upload a new file to Google Drive Copy a file for backup Move a file to a specific folder Archive old or inactive files Organize documents into folders Convert files to a new format (PDF, DOCX, etc.) Retrieve and review file history for rollback ๐ Example Input { "action": "download", "fileId": "abc123", "folderPath": "/projects/clientA", "convertFormat": "pdf" } ๐ Security & Performance OAuth2 secured access to Google Drive API No sensitive data stored in transit Real-time audit logs and alerts Batch-friendly with built-in rate limiting ๐ Ideal For Businesses automating file management AI Agents retrieving, sorting, converting, or archiving files Compliance teams needing file versioning and backups โ๏ธ Requirements n8n + Google Drive API v3 MCP server + Webhook integration Google OAuth2 Credentials
By David OlusolaAnalyze images from forms using GPT-4o-mini Vision and deliver to Telegram
This workflow analyzes images submitted via a form using OpenAI Vision, then delivers the analysis result directly to your Telegram chat. โ Use case examples: โข Users submit screenshots for instant AI interpretation โข Automated document or receipt analysis with Telegram delivery โข Quick OCR or image classification workflows โธป โ๏ธ Setup Guide Form Submission Trigger โข Connect your form app (e.g. Typeform, Tally, or n8nโs own webhook form) to the On form submission trigger node. โข Ensure it sends the image file or URL as input. OpenAI Vision Analysis โข In the OpenAI node, select Analyze Image operation. โข Provide your OpenAI API key and configure the prompt to instruct the model on what to analyze (e.g. โDescribe this receipt in detailโ). Set Telegram Chat ID โข Use this manual node to input your Telegram Chat ID for delivery. โข Alternatively, automate this with a database lookup or user session if building for multiple users. Telegram Delivery Node โข Connect your Telegram Bot to n8n using your bot token. โข Set up the sendMessage operation, using the analysis result from the previous node as the message text. Testing โข Click Execute workflow. โข Submit an image via your form and confirm it delivers to your Telegram as expected.
By David OlusolaCreate a private document Q&A system with Llama3, Postgres, Qdrant and Google Drive
โ๏ธ How It Works: LocalRAG.AI โ ๏ธ Note: This system only works for self-hosted n8n instances. It will not function on n8n.cloud or other remote setups. LocalRAG.AI is a private, on-prem AI assistant that uses your own documents to answer questions intelligently. It combines LangChain, Ollama, Qdrant, and Postgres into a powerful AI pipeline โ all running locally for maximum data privacy. ๐ What It Does Monitors Your Google Drive Folders for new or updated files. Downloads the file, extracts the text, and prepares it. Generates Embeddings using your local Ollama model (e.g., LLaMA 3). Stores them in Qdrant, your local vector database. During a chat, it: Uses vector search to retrieve relevant chunks. Combines them with chat history stored in Postgres. Responds via a LangChain AI agent using your local model. ๐ ๏ธ Setup Steps (Self-hosted Only) Install and Self-host n8n (e.g., via Docker). Set up your Ollama instance locally and load your desired LLM (e.g., llama3). Deploy Qdrant locally for vector storage. Connect a Postgres DB to store chat history. Create and import the workflow in n8n. Authenticate Google Drive to monitor folders. Connect credentials for Ollama, Qdrant, Postgres in the n8n workflow. Start chatting through the Webhook Trigger or custom UI. ๐ง Perfect For: Research teams handling confidential data Internal documentation Q&A AI chatbots that donโt rely on OpenAI or cloud
By David OlusolaConvert RSS news to AI avatar videos with Heygen & GPT-4o
๐ฌ Automated News-to-Video Workflow (n8n + Heygen + GPT-4o) ๐ Overview: This n8n workflow turns news from an RSS feed (e.g., CNN) into short, AI-generated avatar videos using Heygen. It: Fetches news from an RSS feed. Logs headlines to Google Sheets. Uses GPT-4o or Google Gemini to generate a 30โ60 sec script. Sends the script to Heygen to create an avatar video. Monitors and retrieves the final video. Logs video metadata (title, link, etc.) to Google Sheets. ๐ฏ Ideal for content creators, marketers, or media pages repurposing written news into video content at scale. --- โ๏ธ Setup Guide (No Sensitive Info) ๐ 1. Heygen API Paid Heygen plan required. Add your API key in the Setup Heygen node: json "heygenapikey": "yourkeyhere" Optional: Set "avatarid" and "voiceid" as desired. ๐ก 2. AI Model: GPT-4o or Gemini GPT-4o: Use OpenAIโs node or HTTP request with your API key. Gemini: Link your Google Cloud project and connect the Gemini node using OAuth2 credentials. ๐ฅ 3. RSS Feed Add an RSS node (e.g., CNN). Extract title, link, and content. ๐ 4. Google Sheets + Drive Connect via OAuth2: "Google Sheets account 2" "Google Drive account 2" Replace sheet IDs in: Log news to sheets Log video URL and title to sheets ๐น 5. Create Video (Heygen) Send a POST request to Heygen's API using the generated script, avatar, and voice ID. โณ 6. Monitor Status Poll the status endpoint until video is ready. Capture the download link. ๐งพ 7. Log Final Output Save video metadata to a Google Sheet for publishing or archiving. Set up video: Link in Workflow ---
By David OlusolaAuto-generate tech news blog posts with NewsAPI & Google Gemini to WordPress
WordPress Daily News Digest Generator Overview: This automation automatically fetches trending tech news every morning, uses AI to create engaging blog posts from each article, and publishes them directly to your WordPress site. What it does: Fetches top 10 US technology news stories every day at 8 AM via NewsAPI Splits articles into individual items for processing Processes each article through a loop system AI creates expanded, engaging blog posts (600-800 words) from each news article Parses AI response to extract clean titles and content Publishes individual blog posts to WordPress automatically Setup Required: NewsAPI Configuration Get free API key from newsapi.org (1,000 requests/day free) Replace YOURAPIKEY in the HTTP Request URL with your actual key Customize country/category parameters in URL if needed WordPress Connection Configure WordPress credentials in the "Publish to WordPress" node Enter your WordPress site URL, username, and password/app password AI Configuration Set up Google Gemini API credentials Connect the Gemini model to the "AI News Summarizer" node Customization Options Publishing Schedule: Modify schedule trigger (default: daily 8 AM) News Sources: Change country, category, or pageSize in NewsAPI URL Content Style: Adjust AI system message for different writing tones Post Status: Change from "publish" to "draft" for manual review Testing Run workflow manually to test all connections Verify news articles are fetched correctly Check that blog posts appear properly on your WordPress site Features: Automatic daily content creation AI-generated unique titles and expanded content Loop processing for multiple articles per day Duplicate content filtering (removes incomplete articles) SEO-optimized blog post formatting Automatic tagging and categorization Customization: Change news categories (technology, business, science, etc.) Adjust posting frequency (hourly, twice daily, etc.) Modify AI prompts for different writing styles Add custom categories and tags Change article limits (currently 5 articles max) Need Help? For n8n coaching or one-on-one consultation
By David OlusolaAutomatically save Gmail attachments to Google Drive
Gmail Attachment Extractor to Google Drive Description: This workflow monitors your Gmail inbox for new emails, specifically those with attachments, and automatically saves those attachments to a designated folder in your Google Drive. Use Case: Automatically archive invoices, client documents, reports, or photos sent via email to a structured cloud storage. How It Works This workflow operates in three main steps: Gmail New Email Trigger: The workflow starts with a Gmail Trigger node, set to monitor for new emails in your specified Gmail inbox (e.g., your primary inbox). It checks for emails that contain attachments. Conditional Check (Optional but Recommended): An If node checks if the email actually has attachments. This prevents errors if an email without an attachment somehow triggers the workflow. Upload to Google Drive: A Google Drive node receives the email data and its attachments. It's configured to upload these attachments to a specific folder in your Google Drive. The attachments are named dynamically based on their original filenames. Setup Steps To get this workflow up and running, follow these instructions: Step 1: Create Gmail and Google Drive Credentials in n8n In your n8n instance, click on Credentials in the left sidebar. Click New Credential. Search for and select "Gmail OAuth2 API" and follow the authentication steps with your Google account. Save it. Click New Credential again. Search for and select "Google Drive OAuth2 API" and follow the authentication steps with your Google account. Save it. Make note of the Credential Names (e.g., "My Gmail Account", "My Google Drive Account"). Step 2: Create a Destination Folder in Google Drive Go to your Google Drive (drive.google.com). Create a new folder where you want to save the email attachments (e.g., Email Attachments Archive). Copy the Folder ID from the URL (e.g., https://drive.google.com/drive/folders/YOURFOLDERID_HERE).
By David OlusolaMedical records automation with Mistral OCR & Google Sheets
This plug-and-play n8n workflow automates medical record digitization using Mistralโs OCR API and stores clean, structured data in Google Sheets. Whether you run a clinic or healthtech product, this no-code solution simplifies data entry from scanned or uploaded medical documents. ๐ Works seamlessly on both self-hosted and cloud-based n8n environments. ๐ฅ Who is this for? Hospitals and private clinics Healthtech platforms & startups Medical admin and document processing teams Clinical researchers and labs ๐ What problem does it solve? โ Manual entry from printed forms โ Unstructured, scattered records โ Errors in data transcription โ Inconsistent document storage โ This automation brings consistency, structure, and speed to the way you handle medical documents. โ What this workflow does Captures uploaded documents through a public form Uploads file to Mistral for OCR processing Extracts clean text from each page (PDF or image) Parses patient fields (Name, DOB, Diagnosis, Medications, etc.) Saves records into a structured Google Sheet ๐ ๏ธ Setup Instructions Step 1: Google Sheet Prep Create a Google Sheet with these columns (case-sensitive): Name, Date of Birth, Patient ID, Date of Visit, Referring Physician, Department, Symptoms, Blood Pressure, Heart Rate, Temperature, Lab Results, Diagnosis, Medications, Next Appointment, Notes Step 2: Mistral API Access Sign up at Mistral AI Get your API key Ensure your plan supports file upload & OCR endpoints Step 3: Google OAuth Credentials (Self-hosted or Cloud) Go to n8n โ Settings โ Credentials, and add: Google Sheets OAuth2 Scopes needed: https://www.googleapis.com/auth/spreadsheets Step 4: Import Workflow Go to Workflows > Import from File Upload your JSON file Replace: Google Sheet document ID in the "Google Sheets" node Your Mistral API key in HTTP Header Auth Step 5: (Optional) Make Form Public In Cloud-based n8n: You can expose the form as a public page Otherwise, connect it to your website form via webhook ๐งฉ Customization Tips Extract More Fields Update the "Data cleaning" node and extend the list of fields: const fields = ["Name", "Diagnosis", "Medications", "Symptoms", ...]; Add EHR or Database Integration After Google Sheets, chain your custom system: PostgreSQL Airtable Supabase MongoDB Change Output Format Want JSON or Markdown output for internal tools? Use the Set or Code node before the final output step. ๐งช Troubleshooting Issue Fix File upload fails Check Mistral API key and file type Google Sheets not updating Verify credentials and document ID No data parsed Check OCR quality; verify field labels in document Workflow not triggering Ensure webhook or form is configured correctly ๐ Self-Hosted vs Cloud Comparison Feature Self-Hosted n8n Cloud Public Form Access Manual setup Built-in OAuth App Config Required Pre-configured Storage Limits Depends on server Included with plan Scalability Fully customizable Scales automatically ๐ฃ Getting Support n8n Docs Mistral API Docs n8n Community Or reach out to: David Olusola (dimejicole21@gmail.com) ๐ Like this template? Give it a star in the template library and help other no-code builders discover it. "Turn scanned documents into structured data with zero code."
By David OlusolaAutomate outbound sales calls to qualified leads with VAPI.ai and Google Sheets
This workflow automates outbound calls to qualified leads using VAPI.ai and Google Sheets. Here's how it works and how to set it up. How It Works Read Leads: The workflow starts by reading leads from a Google Sheet where the "AI call status" is marked as "NO" Batch Processing: Leads are processed one at a time (batch size = 1) to ensure proper sequencing Variable Setup: Extracts the phone number and row number from each lead record Trigger VAPI Call: Makes an API call to VAPI.ai to initiate an AI-powered outbound call Update Status: Marks the lead as "YES" in the Google Sheet after the call is triggered to prevent duplicate calls Detailed Setup Guide Prerequisites n8n instance (self-hosted or cloud) Google Sheets account with OAuth2 credentials VAPI.ai account with API access Step 1: Google Sheets Setup Create a Google Sheet with your leads data Ensure you have these columns (adjust if needed): Phone number (column E in the current setup) AI call status (column F in the current setup) Mark all leads you want to call with "NO" in the status column Step 2: Google Sheets Credentials In n8n, go to Credentials > Add New Select "Google Sheets OAuth2 API" Follow the prompts to authenticate with your Google account Name it (e.g., "Google Sheets account 3" as in the example) Step 3: VAPI.ai Setup Get your VAPI.ai API credentials In n8n, go to Credentials > Add New Select "HTTP Header Auth" Add your VAPI authorization header (typically "Bearer YOURAPIKEY") Name it (e.g., "Header Auth account 4" as in the example)
By David OlusolaLearn JavaScript coding with an interactive RPG-style tutorial game
๐ฏ JavaScript Master Class - Interactive Code Tutorial ๐ How It Works This tutorial is designed as a self-paced learning experience where you explore working JavaScript code examples. Unlike traditional tutorials, you learn by examining real implementations and understanding how they work. ๐ The Learning Method: Execute first - See the workflow in action Open each node - This is where the real learning happens! Study the code - Read JavaScript implementations and comments Understand the flow - See how data transforms between nodes Experiment - Modify code to test your understanding ๐ฎ The "Game" Concept: It's not a real game - it's a gamified learning experience Uses RPG elements (XP, levels, achievements) to make learning engaging Simulates progression through 3 difficulty levels Main learning happens when you open nodes and read the code! --- ๐ Setup Steps Step 1: Import the Template Copy the JSON template provided Open your n8n instance Create a new workflow Press Ctrl+A (or Cmd+A on Mac) to select all Press Ctrl+V (or Cmd+V) to paste the JSON Click "Save" and name it: JavaScript Master Class - Interactive Tutorial Step 2: Execute the Workflow Click "Test workflow" or "Execute workflow" Watch it run through all nodes automatically See the final results and progression simulation Step 3: Start Learning (The Important Part!) Now the real learning begins - you must open each node manually: ๐ For Each Code Node: Double-click the node to open it Read the JavaScript code carefully Study the comments - they explain key concepts Understand the logic - how input becomes output Note the techniques used in each challenge ๐ For Each Sticky Note: Read the explanations and context Understand the learning objectives Note the skills being taught --- ๐ฏ Learning Path Level 1: Data Warrior (Beginner) ๐ Open Node: ๐ฒ Level 1: Data Warrior Focus: Data deduplication using filter() and findIndex() Key Skills: Array methods, duplicate detection What to Study: How the deduplication algorithm works Level 2: API Ninja (Intermediate) ๐ Open Node: โ๏ธ Level 2: API Ninja Focus: Data transformation and validation Key Skills: String manipulation, validation logic, error handling What to Study: How to clean and validate messy API data Level 3: Automation Master (Advanced) ๐ Open Node: ๐ Final Boss: Automation Master Focus: Complex workflow processing Key Skills: Task orchestration, priority sorting, error handling What to Study: How to build robust automation systems --- ๐ก Learning Tips ๐ Active Exploration: Don't just run it - open every single node! Read all comments - they contain key insights Compare approaches - see how complexity increases Try modifications - change values and see what happens ๐ Study Techniques: Take notes on patterns you see Copy interesting code snippets for reference Try to explain each function to yourself Test your understanding by modifying the code ๐งช Experimentation: Change filter conditions in Level 1 Modify validation rules in Level 2 Adjust workflow logic in Level 3 Break something and fix it - great for learning! --- โ ๏ธ Important Notes ๐ฎ "Game" Reality Check: This is NOT an interactive game where you make choices It's a code tutorial with game-like progression themes The "game" runs automatically when executed Real learning happens when you manually open and study each node ๐ Educational Value: Primary learning: Understanding JavaScript implementations Secondary learning: n8n workflow patterns Bonus learning: Problem-solving approaches ๐ง Technical Requirements: Working n8n instance Basic JavaScript knowledge helpful but not required Willingness to explore and experiment --- ๐ฏ Success Metrics You'll know you're learning when you can: โ Explain how each deduplication algorithm works โ Identify the validation patterns used โ Understand the workflow orchestration logic โ Modify the code to handle different scenarios โ Apply these patterns to your own projects --- ๐ค Next Steps After completing this tutorial: Apply the patterns to your own workflows Experiment with variations Build something using these techniques Share your learnings with the community --- Remember: The magic happens when you open each node and study the code! ๐
By David OlusolaCreate a webhook-ready conversational assistant with Google Gemini and session memory
Universal AI Assistant - Webhook-Ready Conversational AI Transform any platform into an intelligent conversational experience with this plug-and-play n8n workflow. This AI assistant can be seamlessly integrated into websites, mobile apps, or any system that supports webhook connections. Key Features: ๐ Universal Integration - Connect to any platform via webhook (websites, apps, bots) ๐ง Powered by Google Gemini 2.0 Flash - Fast, accurate, and context-aware responses ๐พ Session Memory - Maintains conversation context for natural follow-up interactions โก Real-time Responses - Instant webhook responses for smooth user experiences ๐ฏ Customizable Personality - Easy prompt modification for brand-specific tone Perfect For: Website Chat Widgets - Add AI support to any website instantly WhatsApp/Telegram Bots - Power messaging platforms with intelligent responses Mobile App Integration - Embed conversational AI into iOS/Android apps Customer Support Systems - Automate first-line support with context retention Lead Qualification - Intelligent pre-screening of prospects before human handoff Simple Implementation: Just send POST requests to the webhook URL with: json{ "message": "User's question here", "sessionId": "unique-session-identifier" } Ready to deploy in minutes - No complex setup required. Perfect for small businesses wanting to add AI capabilities without technical overhead. This workflow gives you a production-ready foundation that you can customize for specific client needs. The session-based memory makes it ideal for customer support scenarios where context matters, and the webhook approach means it integrates with virtually any platform your clients are already using.
By David Olusola