Workflow Templates

This n8n template demonstrates how to deploy an AI workflow in production while simultaneously running a robust, data-driven Evaluation Framework to ensure quality and optimize costs. Use Cases Model Comparison: Quickly A/B test different LLM models (e.g., Gemini 3 Pro vs. Flash Lite) for speed and cost efficiency against your specific task. Prompt Regression: Ensure that tweaks to your system prompt do not introduce new errors or lower the accuracy of your lead categorization. Production Safety: Guarantee that test runs never trigger real-world actions like sending emails to a client or sales team. Requirements A configured Gmail Trigger (or equivalent email trigger). A Google Gemini account for the LLM models. An n8n Data Table containing your "Golden Dataset" of test cases and ground truths. How it Works The workflow contains two distinct, parallel execution paths: Production Path: The Gmail Trigger monitors for new emails. The email text is routed through the Sentiment Analysis node, which categorizes the lead as Positive, Neutral, or Negative. Check if Evaluating nodes verify the current execution mode. If it is not an evaluation run (the Fail branch), the lead is routed to the corresponding Send Email node for action. Evaluation Path: The When fetching a dataset row trigger pulls test cases (input text and expected sentiment/ground truth) from an n8n Data Table. Each test case loops through the same Sentiment Analysis node. The Check if Evaluating nodes route this path to the Success branch, skipping the real email actions. The Save Output node writes the model's prediction to the Data Table. The Set Metrics node uses the Categorization metric to compare the prediction against the ground truth, returning a score (0 or 1) to measure accuracy. Key Technical Details Model Switching: Multiple Google Gemini Chat Model nodes are connected via the Model input on the Sentiment Analysis node, allowing you to easily swap and compare models without changing the core logic. Edge Case Handling: The System Prompt Template in the Sentiment Analysis node is customized to handle tricky inputs, such as negative feedback about a competitor that should be classified as a Positive lead. Metrics: The workflow uses the built-in Categorization metric, which is ideal for classification tasks like sentiment analysis, to provide objective evidence of performance.

AI Proposal Workflow Overview This workflow turns your sales calls + intake form into a polished, send-ready proposal. It pulls the latest call transcript from Fireflies, generates structured proposal content with Azure OpenAI, builds a proposal in PandaDoc, routes it for Slack approval, and then handles sending, CRM stage updates (Airtable/HubSpot), and automated follow-ups using the PandaDoc audit trail. This workflow is modular. You can replace each major tool: Fireflies** → Gong, Fathom, Wingman, Avoma (any transcript provider) PandaDoc** → DocuSign, Qwilr, Proposify, Google Docs API Slack Approval** → Gmail Approval, MS Teams Approval, Notion DB Approvals Airtable CRM** → HubSpot, Pipedrive, Salesforce, Zoho, Monday Sales CRM Intake Form** → Typeform, Tally, Jotform, HubSpot forms Azure OpenAI** → OpenAI, Anthropic Claude, Mistral, or any LLM connected through an API The core logic stays the same — you only swap the nodes. Who It’s For Agencies & consultants who send similar proposals after every call B2B SaaS / tech teams that want proposals going out within hours Solo operators who want AI to handle most of the draft but keep final control Teams already working out of Slack, wanting approval flows there How It Works 1. Form Trigger (Client Proposal Intake) Client fills a form with: Name, email, website Industry / business context Problem, solution idea, scope Budget, timeline, deliverables 2. Sales Call Intelligence (Fireflies or Gong) Workflow searches transcripts using the client email Fetches the relevant transcript + summary 3. AI Proposal Generator (Azure OpenAI or any LLM) Sets initial variables (draftText, lastFeedback) Sends transcript + form data into LLM Returns structured JSON: introduction client_problem proposed_solution scope_of_work deliverables timeline_breakdown investment next_steps 4. Proposal Creation (PandaDoc, DocuSign, etc.) Creates the proposal document from a template Fills tokens with AI-generated content Inserts pricing table using Budget 5. Slack Approval Loop Slack message is sent to reviewer with: Approve button Request Changes button Optional comment thread for feedback If Approved: Proposal is sent automatically via PandaDoc/DocuSign Slack message to notify proposal has been sent If Changes Requested: Feedback + draft are stored Passed back into the LLM to regenerate New document is created and the Slack approval request is sent again This loop continues until approval happens 6. CRM Update (Airtable / HubSpot) After proposal is sent, Stage → Proposal Sent 7. Follow-Up System (PandaDoc Audit Trail) After a 48-hour wait: Audit trail is fetched If document is not yet signed: Reminder is sent Stage → Reminder Sent Slack message to notify a reminder has been sent If signed: Stage → Document Signed Ideal use cases Sales teams creating tailored proposals at scale Agencies responding quickly to inbound RFPs Freelancers producing polished proposals in minutes RevOps teams standardizing proposal formats SaaS companies automating repetitive proposal creation Requirements n8n (self-hosted or cloud) Transcript provider (Fireflies, Gong, Fathom, etc.) LLM API (Azure OpenAI, OpenAI, Claude, etc.) Proposal tool (PandaDoc, DocuSign, Qwilr) Slack API app for approval flow CRM (Airtable, HubSpot, Pipedrive) Intake form You can now integrate this into your lead workflow and let AI + automation handle proposal drafting, Slack approvals, sending, CRM updates, and follow-ups.

🧠 AI Lead Enricher & Qualifier using Bright Data MCP and Hubspot This workflow automatically enriches inbound leads, evaluates their business fit, updates HubSpot, and alerts the team only when a lead meets qualification criteria. It eliminates manual research and scoring while keeping CRM data clean and complete. 🏗️ What this automation does | Step | Component | Purpose | |------|----------|---------| | 1 | Form Trigger | Captures a new lead’s Name + Email | | 2 | AI Lead Enricher Agent | Uses Azure OpenAI + Bright Data MCP to search the public web and fill missing contact + company details | | 3 | Structured Output Parser | Ensures AI returns clean JSON in a strict schema | | 4 | Lead Scoring Agent | Calculates a numeric Fit Score (0–100) based on ICP match | | 5 | IF Logic | Routes the lead based on Fit Score threshold (> 70 = qualified) | | 6 | HubSpot Actions | Updates/creates Contact & Company with enriched properties | | 7 | Slack Notification | Sends high-quality leads to the team instantly | 🧩 Data Enriched by AI The enrichment agent populates the following fields only if validated with high confidence: Contact Job title LinkedIn profile Country Company Company name LinkedIn company page Industry Number of employees Annual revenue Description Headquarters (country & city) Funding raised If reliable data is not found → field stays "" (no hallucination, no guessing). 🎯 Lead Qualification Strategy The Fit Score (0–100) evaluates how aligned the lead is with a: > B2B automation / AI / RevOps agency targeting SaaS and tech companies Score increases for: SaaS / tech / B2B service industries Mid-size or high-growth teams High-responsibility job titles (Founder, COO, Head of Ops, RevOps, CTO) Funding raised or traction signals 🔔 Resulting CRM + Team Workflow | Fit Score | CRM Update | Slack Notification | |----------|------------|--------------------| | > (qualified) | Contact + Company updated | YES — sales alert sent | | ≤ 70 (not qualified) | Contact + Company updated | No notification | This ensures: CRM always stays enriched and structured Sales only sees high-potential leads No lead is ever dropped or ignored 🌟 Why this automation is powerful ✔ 0 manual research ✔ 0 manual lead scoring ✔ Real-time alerts for high-value leads ✔ Eliminates poor data quality in HubSpot ✔ Works instantly on every form submission 🔧 Ideal use cases Agencies generating inbound leads SaaS companies with SDR teams RevOps teams improving CRM hygiene Lead qualification before booking calls 📌 Key Integrations Azure OpenAI** Bright Data MCP** HubSpot (Contacts & Companies)** Slack** n8n Form Trigger** This workflow can run fully autonomously or be extended with: Calendly auto-booking for qualified leads Sales sequence automation CRM lifecycle stage updates Forecasting dashboards

This workflow provides a mechanism for using AI transcribed voice notes using Voicenotes AI and then running them into an AI agent as prompts. On the "collection" end of the workflow, we gather the output (with the recorded prompt) and do two things: 1) It is saved into NocoDB as a new row on a database table recording AI outputs and prompts. 2) The prompt gets sent to an AI agent and the output gets returned to the user's email Who Is It For? If you like using voice AI tools to write detailed prompts for AI, then this workflow helps to remove the points of friction in getting from A to B! How Does It Work? Simply tag your voice note in Voicenotes with your preferred tag (I'm using 'prompt'). Then, provide the N8N webhook as the URL for a webhook that will trigger whenever a new note is created with this tag (and this tag only). Now, whenever you wish to use a voice note as a prompt, just add the 'tag.' This will trigger the webhook which, in turn, will trigger this workflow - sending the prompt to an AI agent of your choosing (configure within the workflow) and then saving the output into a database and returning it by email. Note: The AI agent system prompt is written to define a structured output to provide Gmail-safe HTML. This is thin injected into a template. You can use a Google Group to gather together the output runs or just receive them at your main address (if you don't use Gmail, just swap out for any other email node or your preferred delivery channel). How To Set It Up You'll need a Voicenotes account in order to use the service! Once you have one, you'll next want to create the tag and the webhook. In N8N, create your webhook node and then provide that to Voicenotes: Create a note. Then assign it a new tag: "Prompts" (or as you prefer). The webhook is matched to the tag. Requirements Voicenotes AI account Customisation The delivery mechanism can be customized to your preferences. If you're not a Google user, substitute the template and sending mechanism for your preferred delivery provider You could for example collect the outputs to a Slack channel or Telegram bot. You may omit the collector in NocoDB or substitute it for another wiki or knowledge management platform such as Notion or Nuclino.

Who's it for This template is designed for anyone who wants to use WhatsApp as a personal AI assistant hub. If you often juggle tasks, emails, calendars, and expenses across multiple tools, this workflow consolidates everything into one seamless AI-powered agent accessible right from your most-used messaging app. What it does Jarvis listens to your WhatsApp messages (text or audio) and processes them with OpenAI. Based on your request, it can: ✅ Manage tasks (create, complete, or delete) 📅 Handle calendar events (schedule, reschedule, or check availability) 📧 Send, draft, or fetch emails with Gmail 👥 Retrieve Google Contacts 💵 Log and track expenses 🎤 Process voice notes and respond intelligently All responses are returned directly to WhatsApp, giving you a unified command center that works on any device. How to set up Clone this template into your n8n workspace. Set up a WhatsApp Business API account (via Meta Business Suite or providers like Twilio, 360dialog, or MessageBird). Configure the WhatsApp webhook to connect to your n8n instance. Connect your Google accounts (Gmail, Calendar, Contacts, etc.). Add your OpenAI API key in the Credentials section. Test by sending a WhatsApp message like: "Create a meeting tomorrow at 3pm" "Add expense $50 for lunch" "Draft a reply to that email from Steve" "What's on my calendar this week?" Requirements n8n instance** (cloud or self-hosted with public webhook URL) WhatsApp Business API** credentials (not regular WhatsApp) Gmail, Google Calendar, and Google Contacts** credentials (optional based on features) OpenAI API key** ElevenLabs API Key** (optional, for advanced audio note processing) How to customize Swap email providers** by replacing the Gmail MCP node with Outlook, Exchange, or IMAP/SMTP. Add more integrations** like Notion, Slack, Todoist, or your CRM. Adjust AI personality** by modifying the system prompt in the OpenAI node. Control context memory** to determine how much conversation history Jarvis remembers. Add automation rules** like auto-categorizing expenses or auto-scheduling recurring meetings. Multi-language support** by configuring OpenAI to respond in different languages. Key advantages of WhatsApp version 🌍 Universal access - WhatsApp works everywhere, including international numbers 📱 Cross-platform - Seamlessly works on mobile, web, and desktop 🔒 End-to-end encryption for sensitive task and email data 👥 Familiar interface - No need to learn a new app ✅ Read receipts - Know when Jarvis has processed your request With this template, you can transform WhatsApp into your all-in-one AI productivity assistant, simplifying workflows and saving hours every week—all from the app you're already using daily.

Overview Transform competitor Instagram content into optimized scripts for your own channel with this fully automated AI-powered content intelligence system. This workflow monitors Instagram profiles in your niche (AI/automation/tech), downloads their videos, transcribes the content, analyzes it for valuable tools and technologies, enriches it with web research, and rewrites it into polished, engagement-optimized scripts ready for your content team. It's like having a 24/7 content research team that never sleeps, turning competitor content into fresh opportunities for your channel. Key Benefits 🎯 Automated Competitive Intelligence - Monitor unlimited Instagram profiles and automatically capture their latest content the moment they post, ensuring you never miss trending topics in your niche. 🤖 AI-Powered Content Analysis - GPT-4O intelligently filters videos to identify only those discussing relevant tools, technologies, or AI solutions, saving hours of manual review time. ✍️ Professional Script Rewriting - Automatically transforms competitor scripts into unique, high-quality content optimized for your brand voice with engagement-focused CTAs that drive comments and DMs. 🔍 Deep Research Integration - Enriches every script with fresh facts from Perplexity AI's web search, adding unique insights and credibility that sets your content apart from simple reposts. 📊 Comprehensive Data Tracking - Stores all video metadata (views, likes, comments, duration) alongside original and rewritten scripts for performance analysis and content strategy optimization. ⚡ Scalable Batch Processing - Process multiple Instagram profiles in a single execution with built-in error handling, ensuring the workflow continues even if individual videos fail to process. 💰 Revenue-Generating Lead Magnet - Built-in CTA system ("comment [keyword] for the link") creates engagement and captures leads directly into your DMs for monetization opportunities. 🔄 100% Repurposable Output - Every processed video becomes a ready-to-use script with step-by-step guides, tool information, and engagement hooks perfect for reels, shorts, or TikToks. How It Works Phase 1: Content Discovery & Extraction The workflow begins by reading your curated list of Instagram profiles from a Google Sheet. These should be competitors or influencers in your niche (AI, automation, tech tools, etc.). For each profile, the system uses the Scrape Creators API to fetch their most recent post, specifically targeting video content. It extracts multiple video quality URLs and prepares them for download. Phase 2: Video Processing & Transcription Once a video is identified, the workflow downloads it directly from Instagram's servers using the highest quality version available. The video file is then passed to OpenAI's Whisper transcription model, which converts the audio into accurate text transcripts. This happens automatically even for videos with background music, multiple speakers, or accents. Phase 3: Intelligent Content Filtering The raw transcript is analyzed by GPT-4O using a sophisticated prompt that determines if the content is relevant to your niche. The AI identifies: Whether the video discusses tools, technologies, or AI solutions (verdict: true/false) Specific tool names mentioned Step-by-step instructions for using the tools A search query for additional research Suggestions for making the content more engaging for an AI/automation audience If the content isn't relevant, the workflow skips it and moves to the next profile, saving API costs and processing time. Phase 4: Deep Research & Fact-Finding For relevant content, the system automatically queries Perplexity AI using the generated search prompt. Perplexity searches the web in real-time to find three interesting, peculiar, or unique facts about the tool or technology. This adds depth and credibility to your final script that the original content likely didn't have. Phase 5: Professional Script Rewriting The final AI step combines everything: the original transcript, the step-by-step guide, the Perplexity research, and the improvement suggestions. GPT-4O rewrites the entire script in your brand voice (casual, spartan, straightforward) at approximately 100 words. The new script: Opens with a strong hook Presents the tool/technology clearly Includes the researched facts naturally Provides value-driven instructions Ends with a specific CTA (e.g., "Comment 'AI' and I'll send the link") Phase 6: Data Storage & Loop Execution All data is written back to your Google Sheet including video metadata (ID, timestamp, caption, engagement metrics), the original transcript, and the rewritten script. The workflow then loops back to process the next Instagram profile in your list, continuing until all profiles have been processed. Required Setup Google Sheets Database Create a Google Sheet with two tabs: "profiles" tab - Column: "Instagram Handles" (without @ symbol, e.g., "aiautomationhub") "phantom output" tab - Columns: id, timeStamp, caption, commentcount, videoUrl, likesCount, videoViewsCount, Username, Duration, original Script, rewritten Script, style, Updated API Credentials Required Scrape Creators API** - For Instagram data extraction (handles, posts, videos) OpenAI API Key** - For Whisper transcription and GPT-4O script analysis/rewriting Perplexity API Key** - For real-time web research and fact-finding Google Sheets OAuth** - For reading profiles and writing processed data Software Requirements n8n instance (cloud or self-hosted) Internet connection for API calls Sufficient OpenAI credits (approximately $0.05-0.15 per video processed) Business Use Cases Content Creation Agencies - Offer content repurposing services to clients, turning competitor research into ready-to-post scripts at scale. Social Media Managers - Monitor competitor content and generate fresh ideas for your own channels without manual research. Course Creators - Identify trending tools in your niche and create educational content around them before competitors do. Affiliate Marketers - Discover new tools to promote, complete with ready-made scripts and CTAs for lead generation. SaaS Companies - Track how competitors explain similar products and optimize your own messaging based on what works. Newsletter Operators - Find trending topics and tools to feature, with scripts easily adaptable to written content. Revenue Potential Direct Sales: Sell this workflow template for $97-$297 depending on setup complexity and included support. Subscription Service: Offer managed content intelligence as a service at $197-$497/month, processing unlimited profiles for clients. Agency Upsell: Use this as a lead generation tool (the CTA system) to build an email/DM list, then sell content creation services at $500-$2,000 per client/month. Course Integration: Include as a bonus tool in a content creation course priced at $497-$997, increasing perceived value. White-Label Licensing: License to agencies for $997-$2,997 with white-label rights for their client base. Time Savings ROI: If a content team spends 2 hours per video on research and scripting at $50/hour, this workflow saves $100 per video. Processing 20 videos weekly = $104,000 annual savings. Difficulty Level & Build Time Difficulty: Intermediate-Advanced Requires understanding of API authentication Needs basic JSON knowledge for data mapping Involves prompt engineering for optimal AI outputs Build Time: 3-4 hours for experienced n8n users, 6-8 hours for beginners Setup and API credential configuration: 1 hour Node connection and data flow: 1-2 hours Prompt optimization and testing: 1-2 hours Google Sheets schema creation: 30 minutes End-to-end testing with real profiles: 1-2 hours Maintenance: Low - Occasional prompt tweaks as AI models evolve Detailed Setup Steps Create Google Sheets Database Create new Google Sheet named "Instagram Content Intelligence" Add tab "profiles" with column "Instagram Handles" Add tab "phantom output" with all required columns (see schema above) Populate profiles tab with 5-10 Instagram handles in your niche Obtain API Credentials Sign up for Scrape Creators (https://scrapecreators.com) and get API key Create OpenAI account and generate API key with GPT-4O and Whisper access Sign up for Perplexity AI API (https://perplexity.ai) and get API key Connect Google Sheets via OAuth in n8n Import Workflow to n8n Copy the JSON workflow provided In n8n, click "Import from File" or paste JSON All nodes will appear but show credential errors Configure Credentials Click each node with a red error icon Add your respective API credentials (Scrape Creators, OpenAI, Perplexity, Google Sheets) Test each connection to ensure validity Map Google Sheets In "Get row(s) in sheet1" node, select your Google Sheet and "profiles" tab In "Update Entries2" node, select your Google Sheet and "phantom output" tab Verify column mappings match your sheet structure Customize AI Prompts Review "Filter & Generate Suggestions" prompt - adjust for your specific niche Review "Write New Script" prompt - modify tone, length, and CTA format to match your brand Test with sample transcripts to optimize output quality Test with Single Profile Add one Instagram handle to your profiles sheet Click "Execute workflow" manually Monitor each node's output to verify data flow Check that final script appears in Google Sheet Scale to Multiple Profiles Add 10-20 Instagram profiles to your sheet Run full workflow and monitor for errors Review output quality across different content types Adjust batch size if rate limits are hit Set Up Scheduling (Optional) Replace Manual Trigger with Schedule Trigger Set to run daily at optimal times (e.g., 6 AM when fresh posts exist) Enable error notifications to catch failures Implement DM Automation (Advanced) Connect Instagram API or tools like ManyChat Monitor comments for keywords from your CTA Auto-send tool links via DM to engaged users Advanced Customization Options Multi-Language Support: Add language detection node and conditional branches for different script formats per language. Engagement Scoring: Implement scoring algorithm based on likes, comments, views to prioritize which videos to repurpose first. Content Categorization: Add classification layer to tag scripts by category (productivity tools, AI models, automation platforms) for better organization. Thumbnail Analysis: Integrate vision AI to analyze which thumbnail styles perform best and suggest designs for your repurposed content. Sentiment Analysis: Add sentiment detection to understand emotional tone and adjust rewritten scripts to match or improve engagement potential. A/B Script Variants: Generate 2-3 script variations per video with different hooks/CTAs for split testing performance. Competitor Trend Dashboard: Build a connected dashboard showing trending tools, engagement patterns, and content gaps in your niche. Auto-Publishing Integration: Connect to Instagram API or scheduling tools to automatically post rewritten content with approval workflows. Voice Cloning Integration: Add ElevenLabs API to generate audio using your voice profile, making videos fully production-ready. Multi-Platform Expansion: Extend to TikTok, YouTube Shorts, LinkedIn by adjusting script length and platform-specific CTAs.

📌 Overview Description: This powerful workflow automates your sales quotation process by connecting Pipedrive with DottedSign. When a deal is moved to a specific stage in Pipedrive, this template automatically generates a professional PDF quotation, uploads it back to the deal, and sends it out for e-signature via DottedSign service, saving your sales team valuable time and eliminating manual work. What it does When a Pipedrive deal moves to a designated stage (e.g., "Quotation Stage"), this workflow triggers and performs the following actions: Gathers Data: It collects all relevant information, including deal details, client contacts, organization info, and associated products from Pipedrive. Generates PDF Quote: It populates a customizable HTML template with the collected data and uses a PDF generation service (Gotenberg) to create a polished PDF document. Uploads to Pipedrive: The generated PDF quote is automatically uploaded to the "Files" section of the corresponding Pipedrive deal for record-keeping. Sends for E-Signature: It creates a new signing task in DottedSign, sending the quotation to the client for their electronic signature. Requirements A Pipedrive account with admin permissions. A DottedSign developer account to obtain API credentials. A self-hosted instance of Gotenberg for HTML to PDF conversion. How to set up Pipedrive Trigger Stage: In the If node, change the stage ID 7 to the ID of the pipeline stage you want to use as the trigger. PDF Conversion Service: In the Gotenberg to PDF (HTTP Request) node, replace the placeholder URL with the endpoint of your running Gotenberg instance. DottedSign Credentials: In the Get DottedSign Access Token node, enter your client_id and client_secret in the request body. DottedSign Signature Field: In the Create DottedSign Task node, you must adjust the page and coord values under field_settings to match the desired signature location on your PDF template. How to customize the workflow Quotation Template:** Edit the Generate Quotation HTML node to modify the quote's appearance, text, company logo, and terms. The {{ ... }} expressions are placeholders that are filled with Pipedrive data. Trigger:** Replace the Pipedrive Trigger with another trigger, such as a webhook or a form submission, to adapt the workflow to different needs. Notifications:** Add a Slack or email node at the end of the workflow to notify the sales team once the quotation has been sent.

This workflow automates the creation of AI-generated viral selfie images with celebrities using Nano Banana Pro Edit via RunPod, generates engaging social media captions, and publishes the content to Instagram via Postiz. It starts with a form submission where the user provides an image URL, a custom prompt, and an aspect ratio. | START | RESULT | |------|--------| | | | Key Advantages 1. ✅ Full Automation, Zero Manual Effort From image generation to caption writing and publishing, the entire process is automated. This drastically reduces production time and eliminates repetitive manual tasks. 2. ✅ Scalable Content Creation The workflow can handle unlimited submissions, making it ideal for: Creators Agencies Growth teams SaaS products offering AI-generated content 3. ✅ Consistent Viral Quality By using a dedicated AI content agent with strict guidelines, every post is: Optimized for engagement Consistent in tone and quality Designed to maximize comments, shares, and saves 4. ✅ No Technical Skills Required for End Users The form-based entry point allows anyone to generate high-quality, celebrity-style content without understanding AI, APIs, or automation. 5. ✅ Multi-Tool Integration in One Pipeline The workflow seamlessly connects: AI image generation (RunPod) AI content intelligence (Google Gemini) Asset storage (Google Drive) Social media distribution (Postiz) 6. ✅ Brand-Safe and Platform-Native Output The captions are written to feel human and authentic, avoiding: Obvious AI language Overuse of emojis Mentions of AI generation This increases trust and platform compatibility. 7. ✅ Perfect for Growth and Monetization This workflow is ideal for: Viral growth experiments Personal brand scaling Automated influencer-style content AI-powered SaaS or lead magnets How it works The workflow then: Sends the image and prompt to RunPod’s Nano Banana Pro Edit API for AI image generation. Periodically checks the generation status until it is completed. Once the image is ready, it is downloaded and analyzed by Google Gemini to generate a viral-ready Instagram caption and hashtags. The final image is uploaded to Google Drive and to Postiz for social media publishing. The caption and image are combined and scheduled for posting on Instagram through the Postiz integration. The process includes conditional logic, waiting intervals, and error handling to ensure reliable execution from input to publication. Set up steps To use this workflow in n8n: Configure credentials: Add RunPod API credentials under httpBearerAuth named “Runpods”. Set up Google Gemini (PaLM) API credentials for caption generation. Add Postiz API credentials for social media posting. Configure Google Drive OAuth2 credentials for image backup. Prepare nodes: Ensure the Form Trigger node is properly set up with the required fields: IMAGE_URL, PROMPT, and FORMAT. Update the RunPod API endpoints in the “Generate selfie” and “Get status clip” nodes if needed. Verify the Google Drive folder ID in the “Upload file” node. Replace XXX in the “Upload to Social” node with a valid Postiz integration ID. Test the flow: Use the pinned test data in the “On form submission” node to simulate a form entry. Activate the workflow and submit the form to trigger the process. Monitor execution in n8n’s workflow view to ensure all nodes run successfully. 👉 Subscribe to my new YouTube channel. Here I’ll share videos and Shorts with practical tutorials and FREE templates for n8n. Need help customizing? Contact me for consulting and support or add me on Linkedin.

This workflow automates your entire lead follow-up process across email, SMS, and WhatsApp. It starts on a schedule and pulls your latest leads from FollowUpBoss (FUB), checking when the workflow last ran. Each new contact is automatically validated — phone numbers and emails are cleaned, filtered, and checked for duplicates before sending any message. Once validated, the system intelligently decides how to reach each lead: 💬 Email + SMS if all data looks good 📧 Email only if phone is invalid 📱 SMS/WhatsApp only if email is missing Each message is personalized using data from the lead record, and everything is tracked back in your database for future reporting. This template helps agents, marketing teams, and CRM users run consistent follow-ups without missing a single contact. Whether you manage 10 or 10 000 leads, this flow scales effortlessly. Tools used: FollowUpBoss, Gmail, Twilio/WhatsApp, n8n (Tip: Replace your API keys and Gmail credentials before running.)

Description This workflow automates employee retention analytics by combining candidate performance data with trait-level retention statistics. It scores candidates, validates data, and generates a polished Retention Digest HTML email using GPT (Azure OpenAI). Hiring managers receive structured insights weekly, highlighting top/weak traits, candidate scores, and actionable JD refinement tips. What This Template Does (Step-by-Step) ⚡ Manual Trigger – Starts workflow execution on demand. 📑 Candidate Data Fetch (Google Sheets – Hires Tracking) – Pulls candidate-level details like name, role, traits, start date, and retention status. 📑 Trait Summary Fetch (Google Sheets – Retention Summary) – Fetches aggregated trait-level retention statistics, including hires, stayed, left, retention %, and weight adjustments. 🔀 Merge Candidate + Trait Data – Combines both datasets into a unified stream for scoring. 🧮 Candidate Scoring & Data Normalization (Code Node) – Cleans and standardizes data. Builds a trait → weight map. Calculates each candidate’s Candidate_Score. Outputs normalized JSON. ✅ Data Validation (If Node) – Ensures both candidate and trait datasets are present. TRUE → continues to AI digest generation. FALSE → routes to error logging. ⚠️ Error Handling Logic (Google Sheets – Error Log) – Logs any failed or incomplete runs into a dedicated error sheet for auditing. 🧠 AI Processing Backend (Azure OpenAI) – Prepares candidate + trait data for GPT processing. 🤖 Retention Digest Generator (LLM Chain) – Uses GPT (gpt-4o-mini) to create a structured HTML Retention Digest, including: TL;DR summary Top Traits (positive retention) Weak Traits (negative retention) Candidate highlights (scores & retention status) 3 actionable JD refinement tips 📧 Email Delivery (Gmail) – Sends the digest directly to hiring managers as a styled HTML email with subject: Retention Analysis Digest – Weekly Update Prerequisites Google Sheets (Hires Tracking + Retention Summary + Error Log) Gmail API credentials Azure OpenAI access (gpt-4o-mini model) n8n instance (self-hosted or cloud) Key Benefits ✅ Automates retention analytics & reporting ✅ Provides AI-powered insights in structured HTML ✅ Improves hiring strategy with trait-based scoring ✅ Reduces manual effort in weekly retention reviews ✅ Ensures reliability with error handling & validation Perfect For HR & Recruitment teams monitoring post-hire retention Organizations optimizing job descriptions & hiring strategy Talent analytics teams needing automated, AI-driven insights Stakeholders requiring clear weekly digest emails

How it works This workflow automatically creates daily AI-generated videos for any niche. It generates a short script, converts it into a cinematic video prompt, and produces an 8-second video with Veo 3. The workflow waits for the video, downloads it, and sends it via Gmail with a ready-to-post social media description. You can customize the script prompt to match any industry or topic. Step-by-step 1. Trigger the workflow Daily Trigger** – Starts the workflow automatically every day. 2. Generate content Generate Script** – Creates a short, engaging script for your chosen niche. Generate Veo3 Prompt** – Turns the script into a cinematic video prompt for Veo 3. Social Media Description** – Writes an SEO-friendly description for LinkedIn, Instagram, and YouTube. 3. Generate the video Create Video** – Sends the prompt to Veo 3 for video generation. Wait for Video** – Pauses until video processing is complete. Status** – Checks whether the video is ready. If** – Loops until the video is successfully generated. 4. Download and share Download Video** – Fetches the completed video file. Send a message** – Emails the video with the social media description attached. Why use this? Create short, engaging videos in any niche automatically. Combine scriptwriting, video creation, and content delivery in one workflow. Save time by eliminating manual editing and waiting. Ensure consistent, professional social content for multiple platforms. Flexible for marketing, education, news, product updates, and more.

Description This workflow automates Zendesk ticket escalation by creating ClickUp tasks for urgent cases and notifying the support team in Telegram. It ensures that high-priority tickets are instantly visible to the right team members, avoiding delays in resolution. What This Template Does (Step-by-Step) 🟢 Trigger (Manual Test or Later Zendesk Trigger) Currently uses a manual trigger (Execute Workflow) for testing. In production, this would start whenever a pending Zendesk ticket appears. 🎫 Fetch Zendesk Tickets Pulls all pending tickets assigned to a group. Sorts them by status and date. 🧹 Select Latest Ticket Sorts by created_at and keeps only the newest ticket. Outputs: id, subject, description, requester_id, created_at. 📧 Fetch Requester Email Retrieves requester details (name, email, timezone) from Zendesk Users API. 🔀 Merge Ticket & Requester Data Combines both streams: ticket info + requester info. Ensures the ClickUp task payload has everything it needs. 📝 Prepare ClickUp Task Payload Builds a structured task: Task Name: [Escalation] {Subject} (Ticket #ID) Description: Ticket + requester details + escalation message Priority: 3 (default, can be adjusted) Tags: zendesk, escalation 📂 Create ClickUp Task Pushes the structured task into ClickUp under the escalation list. Assigns it to a predefined team member. 📨 Format Telegram Alert Message Generates a concise but urgent message: Ticket subject + ID Requester name + email Direct ClickUp link Adds urgency formatting (🚨 Immediate Attention Required). 📢 Send Telegram Escalation Alert Posts the alert into the chosen Telegram chat/team. Ensures managers/stakeholders know instantly. Prerequisites Zendesk account + API credentials ClickUp account + API credentials Telegram bot token & chat ID n8n instance (cloud or self-hosted) Customization Ideas ⚡ Replace manual trigger with Zendesk “Ticket Created” trigger. 🎯 Add SLA-based conditions (e.g., escalate only if response > 4 hrs). 📊 Auto-assign ClickUp tasks by ticket category. 🔔 Add Slack/Email notification along with Telegram. 📂 Store escalation logs into Notion or Google Sheets. Key Benefits ✅ Zero delay in handling critical tickets ✅ Automatically creates ClickUp task + Telegram alert ✅ Reduces manual handoff between support → escalation team ✅ Keeps everyone aligned in real-time Perfect For 🎯 Support teams needing fast escalations 📈 SaaS companies managing large ticket volumes 🚀 Agencies ensuring VIP clients never wait