Sandeep Patharkar | www.FastTrackAiMastery.com
AI and automation enthusiast with a strong background in building intelligent workflows. As an AWS Certified Solutions Architect, I design secure, scalable, cost-effective cloud solutions. Passionate about integrating AI to streamline processes and solve real-world challenges. Always eager to collaborate, share knowledge, and empower the community to push the boundaries of cloud and AI.
Templates by Sandeep Patharkar | www.FastTrackAiMastery.com
Automate HR recruitment with OpenAI resume screening & interview QnA generator
<br> <div> Build an AI HR Assistant to Screen Resumes and Send Telegram Alerts A step-by-step guide to creating a fully automated recruitment pipeline that screens candidates, generates interview questions, and notifies your team. This template provides a complete, step-by-step guide to building an AI-powered HR assistant from scratch in n8n. You will learn how to connect a web form to an intelligent screening agent that reads resumes, evaluates candidates against your job criteria, and prepares unique interview questions for the most promising applicants. <br> | Services Used | Features | | :---------------------------------------------- | :----------------------------------------------------------------------------- | | 🤖 OpenAI / LangChain | Uses AI Agents to screen, score, and analyze candidates. | | 📄 Google Drive & Google Sheets | Stores resumes and manages a database of open positions and applicants. | | 📥 n8n Form Trigger | Provides a public-facing web form to capture applications. | | 💬 Telegram | Sends real-time alerts to the hiring team for qualified candidates. | --- How It Works ⚙️ 📥 Application Submitted: The workflow starts when a candidate fills out the n8n Form Trigger with their details and uploads their CV. 📂 File Processing: The CV is automatically uploaded to a specific Google Drive folder for record-keeping, and the Extract from File node reads its text content. 🧠 AI Screening Agent: A LangChain Agent analyzes the resume text. It uses the Google Sheets Tool to look up the requirements for the applied role, then scores the candidate and decides if they should be shortlisted. 📊 Log Results: The agent's decision (name, score, shortlisted status) is logged in your master "Applications" Google Sheet. ✅ Qualification Check: An IF node checks if the candidate was shortlisted. ❓ AI Question Generator: If shortlisted, a second LangChain Agent generates three unique, relevant interview questions based on the candidate's resume and the job description. ✍️ Update Sheet: The generated questions are added to the candidate's row in the Google Sheet. 🔔 Notify Team: A final alert is sent via Telegram to notify the HR team that a new candidate has been qualified and is ready for review. --- 🛠️ How to Build This Workflow Follow these steps to build the recruitment assistant from a blank canvas. Step 1: Set Up the Application Intake Add a Form Trigger node. Configure it with fields for Name, Email, Phone Number, a File Upload for the CV, and a Dropdown for the "Job Role". Connect a Google Drive node. Set the Operation to Upload and connect your credentials. Set it to upload the CV file from the Form Trigger into a specific folder. Add an Extract from File node. Set it to extract text from the PDF CV file provided by the trigger. Step 2: Build the AI Screening Agent Add a Langchain Agent node. This will be your main screening agent. In its prompt, instruct the AI to act as a resume screener. Tell it to use the input text from the Extract from File node and the tools you will provide to score and shortlist candidates. Add an OpenAI Chat Model node and connect it to the Agent's Language Model input. Add a Google Sheets Tool node. Point it to a sheet with your open positions and their requirements. Connect this to the Agent's Tool input. Add a Structured Output Parser node and define the JSON structure you want the agent to return (e.g., candidate_name, score, shortlisted). Connect this to the Agent's Output Parser input. Step 3: Log Results & Check for a Match Connect a Google Sheets node after the Agent. Set its operation to Append or Update. Use it to add the structured output from the agent into your main "Applications" sheet. Add an IF node. Set the condition to continue only if the shortlisted field equals "yes". Step 4: Generate Interview Questions On the 'true' path of the IF node, add a second Langchain Agent node. Write a prompt telling this agent to generate 3 interview questions based on the candidate's resume and the job requirements. Connect the same OpenAI Model and Google Sheets Tool to this agent. Add another Google Sheets node. Set it to Update the existing row for the candidate, adding the newly generated questions. 💬 Need Help or Want to Learn More? Join my Skool community for n8n + AI automation tutorials, live Q&A sessions, and exclusive workflows: 👉 https://www.skool.com/n8n-ai-automation-champions --- Template Author: Sandeep Patharkar Category: Website Chatbots / AI Automation Difficulty: Beginner Estimated Setup Time: ⏱️ 15 minutes
By Sandeep Patharkar | www.FastTrackAiMastery.comOutlook inbox tamer: GPT-4.1 powered categorization, auto replies & team alerts
Outlook Inbox Tamer: AI-Powered Categorization, Auto Replies & Team Alerts This workflow automatically classifies and routes incoming Outlook emails into smart categories using n8n + OpenAI GPT-4.1-mini. It helps professionals and teams stay organized by intelligently sorting and responding to high-priority messages, customer support emails, promotions, and finance-related messages — all without manual effort. --- 🧠 Who’s It For Professionals or teams overwhelmed by email volume. Customer support, operations, or finance teams needing real-time triage. Anyone who wants AI to help manage and prioritize their Outlook inbox. --- ⚙️ How It Works Microsoft Outlook Trigger monitors your inbox for new emails. OpenAI GPT-4.1-mini analyzes each email and classifies it as one of: High_Priority Customer_Support Promotions Finance/Billing Routing node moves emails to matching Outlook folders. AI-generated replies and Telegram notifications keep the right team informed instantly. (Optional) Use Google Sheets + Manual Trigger to test with sample data before going live. --- 🛠️ Requirements Outlook account connected via Microsoft Outlook OAuth2. OpenAI API key (set up in n8n credentials). (Optional) Telegram bot token for team alerts. (Optional) Google Sheets for test emails. --- 🔧 How to Set Up Import the workflow into your n8n instance. Add credentials for: Microsoft Outlook OpenAI Telegram (optional) Deploy and activate the workflow. Start sending or receiving emails — watch them get auto-classified and organized! --- 🧩 How to Customize Update the system prompt in the EmailClassifierAgent to add more categories (like HR, Legal, etc.). Change Telegram recipients for alerts. Extend the workflow to post classified data into Notion, Slack, or CRM. --- 📘 Example Use Case An AI agent monitors your Outlook inbox, classifies incoming emails in real time, moves them to their respective folders, creates response drafts, and alerts your team instantly through Telegram. --- 💬 Connect with the Creator 👋 Created by Sandeep Patharkar 💼 Connect on LinkedIn 🌐 Join my Skool community for n8n + AI automation tutorials, live Q&As, and exclusive workflow templates. --- Category: Email Automation / AI Productivity Difficulty: Intermediate Estimated Setup Time: ⏱️ 10–15 minutes
By Sandeep Patharkar | www.FastTrackAiMastery.comCreate Deepfake Videos by Swapping Faces with Fal.ai Wan 2.2 and AWS S3
Animate Any Face into a Video with Fal.ai Create stunning deepfake-style videos automatically by swapping a face from an image onto a source video. This workflow provides a powerful, automated pipeline to perform video face-swapping using the Fal.ai API. It's designed to handle the entire asynchronous process: accepting a source video and a target face image, uploading them to cloud storage, initiating the AI job, polling for completion, and retrieving the final, rendered video. | Services Used | Features | | :--- | :--- | | 🤖 Fal.ai | Leverages the powerful Wan 2.2 model for high-quality face animation. | | ☁️ AWS S3 | Uses enterprise-grade cloud storage for reliable public file hosting. | | 🔄 Polling Loop | Intelligently waits for the asynchronous AI job to complete before proceeding. | | 📥 n8n Form Trigger | Provides a simple UI to upload your source image and video. | --- How It Works ⚙️ 📥 Get User Input: The workflow starts when you upload a source video and a face image via the n8n Form Trigger. ☁️ Upload to Cloud: Both files are automatically uploaded to a specified AWS S3 bucket to generate the publicly accessible URLs required by the AI model. 🚀 Start AI Job: The public URLs for the video and image are sent in an HTTP Request to the Fal.ai API, which starts the asynchronous face animation process and returns a request_id. ⏳ Wait & Check: The workflow enters a polling loop. It Waits for one minute, then makes another HTTP Request to the Fal.ai status endpoint using the request_id. ✅ Check for Completion: An IF node checks if the job status is COMPLETED. If not, the workflow loops back to the Wait node. 🎬 Retrieve Final Video: Once the job is complete, the workflow makes a final HTTP Request to fetch the finished animated video. --- 🛠️ How to Set Up 🔑 Set Up Fal.ai Credentials: Get your API Key from Fal.ai. In n8n, go to Credentials, add a new Header Auth credential, and save your key. Connect this credential to all three HTTP Request nodes in the workflow. ☁️ Configure AWS S3: Add your AWS credentials in n8n. In the two AWS S3 nodes (Upload Video1 and Upload Image1), update the Bucket Name parameter to your own S3 bucket. Ensure your bucket permissions allow for public reads. ▶️ Activate and Run: Activate the workflow. Open the Form Trigger URL from the n8n editor, upload your files, and submit. The final video will be available in the execution log of the Get Final Video node. --- Requirements An active Fal.ai account and API key. An AWS account with an S3 bucket configured for public access. Alternative Storage: For a personal setup, you can replace the AWS S3 nodes with Cloudinary nodes. Just ensure the output is a public URL. --- 💬 Need Help or Want to Learn More? Join my Skool community for n8n + AI automation tutorials, live Q&A sessions, and exclusive workflows: 👉 https://www.skool.com/n8n-ai-automation-champions --- Template Author: Sandeep Patharkar Category: Content Generation / Content Marketing Difficulty: Intermediate Estimated Setup Time: ⏱️ 20 minutes
By Sandeep Patharkar | www.FastTrackAiMastery.comBuild enterprise RAG system with Google Gemini file search & retell AI voice
🧠 Enterprise RAG System with Google Gemini File Search + Retell AI Voice Agent Build a complete enterprise-grade RAG pipeline using Google Gemini’s brand-new File Search API, combined with a powerful Retell AI voice agent (JARVIS) as the conversational front end. This workflow is designed for AI automation agencies, SMBs, enterprise teams, and internal AI copilots. --- 📌 Who Is This For? Enterprise teams building internal search copilots AI automation agencies delivering RAG products to clients SMBs wanting automated knowledge lookup Anyone needing a production-ready, zero-Pinecone RAG workflow --- 🚧 Problem This Solves Traditional RAG requires: Vector DB setup Embedding jobs Chunking pipelines Custom search APIs Gemini File Search eliminates all of this — you simply create a store and upload files. Indexing, chunking, embeddings = fully automated. This workflow turns that into a plug-and-play enterprise template. --- 🧩 What This Workflow Does (High-Level) 1️⃣ Create a Gemini File Search Store Calls fileSearchStores API Creates a persistent embedding store Automatically saved to Google Sheets for future retrieval 2️⃣ Auto-Upload Documents from Google Drive When a new file is added: Download → Start resumable upload → Upload actual bytes Gemini auto-indexes the document for retrieval 3️⃣ Chat-Based Retrieval (Chat Trigger) User question → Gemini File Search → Short, precise answer returned. 4️⃣ Voice Search (Retell AI Agent) Your Gemini RAG can now be searched by voice. --- 🎙️ Retell AI (JARVIS) Voice Agent – Integration Steps 🔧 Step 1 — Paste This Prompt Into Retell AI You are JARVIS, an advanced AI assistant designed to help user with their daily tasks. Always call the user “Sir”. You remember the user's name and important details to improve the experience. Whenever the user asks for information that requires external lookup: Make a short, witty remark related to their request. Immediately call the n8n tool — do NOT repeat the question back. Be concise, professional, and efficient. n8n tool call: Use this tool for all knowledge-based or RAG lookups. It sends the user’s query to the n8n workflow. JSON Schema: { "type": "object", "properties": { "query": { "type": "string", "description": "The user’s full request for JARVIS to process." } }, "required": ["query"] } --- 🔧 Step 2 — Add This URL to Retell (YOUR WEBHOOK) Paste the webhook URL from your Respond to Webhook node: https://YOUR-N8N-URL/webhook/Gemini ← replace with your actual webhook ID This is the endpoint Retell calls every time the user speaks. --- 🔧 Step 3 — End-to-End Flow User speaks to JARVIS Retell sends query → n8n n8n forwards query to Gemini using File Search Gemini returns answer Retell speaks the response out loud You now have a voice-powered enterprise RAG agent. --- 📦 Requirements Google Gemini File Search API access Google Drive folder for document uploads Retell AI agent n8n instance (Optional) Google Sheets for storing store IDs --- 📝 Estimated Setup Time ⏱️ 25–30 minutes (end-to-end) --- 👨💻 Template Author Sandeep Patharkar Founder – FastTrackAI AI Automation Architect | Enterprise Workflow Designer 🔗 Website: https://fasttrackaimastery.com 🔗 LinkedIn: https://www.linkedin.com/in/sandeeppatharkar/ 🔗 Skool Community: https://www.skool.com/aic-plus 🔗 YouTube: https://www.youtube.com/@FastTrackAIMastery --- 🏁 Summary This template gives you a full enterprise RAG infrastructure: Automatic document indexing Gemini File Search retrieval Chat + Voice interfaces Zero-vector-database setup Seamless Retell AI integration Fully production-ready Perfect for creating internal AI copilots, employee knowledge assistants, client-facing search apps, and enterprise RAG systems.
By Sandeep Patharkar | www.FastTrackAiMastery.comn8n enterprise AI security firewall — guardrails for secure agents
🛡️ n8n Guardrails: Risk Ranking This workflow provides a complete testing rig for evaluating text against seven essential AI guardrails used in production systems. It helps you detect jailbreak attempts, PII exposure, NSFW content, secret key leaks, malicious URLs, topical misalignment, and keyword violations. Use the included Google Sheet or CSV to batch-test multiple inputs instantly. --- How It Works (Internal Workflow Overview) Load Input Rows The workflow reads each test entry (GuardrailType + InputText) from a Google Sheet or CSV. Route to the Correct Guardrail A Switch node sends the text to the appropriate guardrail: Jailbreak PII Secret Keys NSFW URLs Topical Alignment Keywords AI Guardrail Evaluation Each guardrail uses Google Gemini to return: Pass / Fail Confidence score Reasoning Extracted PII, URLs, or entities (when relevant) Optional Sanitization Layer Three sanitizers demonstrate how to clean unsafe text: PII Sanitization Secret Key Sanitization URL Sanitization Review Results Each guardrail node outputs clean JSON, making debugging fast and transparent. --- How to Set Up Load the Test Dataset Use either: The included CSV file The linked Google Sheet Update only: Document ID Sheet name --- Add Google Sheets Credentials Create an OAuth2 credential → paste the Google JSON → connect your account. --- Add Google Gemini Credential Go to Credentials → Google Gemini (PaLM API) → Paste your API key → attach it to all Guardrail nodes. --- Review Sticky Notes They visually explain: What each guardrail checks Why the check is important Risk scoring and impact --- Run the Workflow Click Execute Workflow and inspect: Each guardrail node’s output The full execution data --- Requirements n8n (latest version recommended) Google Gemini API key Google Sheets API access Test dataset: n8n Guardrails test data.csv --- Test Data Included The included dataset allows instant testing: Jailbreak prompts PII samples API key leaks NSFW text Malicious URL examples Off-topic content Keyword triggers --- Template Metadata Template Author: Sandeep Patharkar Category: AI Safety / Agent Security Difficulty: Intermediate Estimated Setup Time: 10–15 minutes Tags: Guardrails, AI Agents, Safety, Enterprise --- Connect With Me Author: Sandeep Patharkar 🔗 LinkedIn: https://www.linkedin.com/in/sandeeppatharkar 🏠 Skool AIC+: https://www.skool.com/aic-plus
By Sandeep Patharkar | www.FastTrackAiMastery.com