Workflow Templates

Stop duplicating your work! This template demonstrates a powerful design pattern to handle multiple triggers (e.g., Form, Webhook, Sub-workflow) within a single, unified workflow. By using a "normalize and consolidate" technique, your core logic becomes independent of the trigger that started it, making your automations cleaner, more scalable, and far easier to maintain. Who is this for? n8n developers & architects:** Build robust, enterprise-grade workflows that are easy to maintain. Automation specialists:** Integrate the same core process with multiple external systems without repeating yourself. Anyone who values clean design:** Apply the DRY (Don't Repeat Yourself) principle to your automations. What problem does this solve? Reduces duplication:** Avoids creating near-identical workflows for each trigger source. Simplifies maintenance:** Update your core logic in one place, not across multiple workflows. Improves scalability:** Easily add new triggers without altering the core processing logic. Enhances readability:** A clear separation of data intake from core logic makes workflows easier to understand. How it works (The "Normalize & Consolidate" Pattern) Trigger: The workflow starts from one of several possible entry points, each with a unique data structure. Normalize: Each trigger path immediately flows into a dedicated Set node. This node acts as an adapter, reformatting the unique data into a standardized schema with consistent key names (e.g., mapping body.feedback to feedback). Consolidate: All "normalize" nodes connect to a single Set node. This node uses the generic {{ $json.key_name }} expression to accept the standardized data from any branch. From here, the workflow is a single, unified path. Setup This template is a blueprint. To adapt it: Replace the triggers with your own. Normalize your data: After each trigger, use a Set node to map its unique output to your common schema. Connect to the consolidator: Link all your "normalize" nodes to the Consolidate trigger data node. Build your core logic after the consolidation point, referencing the unified data. Taking it further Merge any branches:** Use this pattern to merge any parallel branches in a workflow, not just triggers. Create robust error handling:** Unify "success" and "error" paths before a final notification step to report on the outcome.

This n8n template generates a dynamic weekly sales report from Airtable and sends it to Slack. It calculates key sales metrics like total pipeline value, weighted pipeline (based on deal stage), top deal, closed revenue, and win rate.. all formatted in a clean Slack message. How it works A schedule trigger starts the workflow (e.g., every Monday). It fetches deal data from Airtable, splits open vs closed deals, calculates all metrics with JavaScript, and formats the output. The message is then sent to Slack using Markdown for readability. How to use Update the Airtable credentials and select your base and table with fields: Deal Name, Value, Status, etc. Set the Slack channel in the final node to your preferred sales or ops channel. Requirements Airtable base with relevant deal data (see field structure) Slack webhook or token for sending messages Customising this workflow You can adapt the logic to other CRMs like Salesforce or HubSpot, add charts, or tweak stage weights. You can also change the schedule or add filters (e.g., by rep or region).

> ⚠️ Notice: > Community nodes like @custom-js/n8n-nodes-pdf-toolkit can only be installed on self-hosted instances of n8n. This n8n workflow demonstrates how to collect form submissions from a landing page, fill a PDF form automatically, and send it via email. It uses the PDF Form Fill node from customjs.space to populate PDF fields with the submitted data. What this workflow does Serves a landing page with a user-friendly form. Receives form submissions via a Webhook. Uses the HTTP Request node to fetch a PDF template. Fills the PDF form fields with the submitted data using the PDF Form Fill node. Optionally reads PDF form field names using Get PDF Form Fields. Sends the completed PDF as an email attachment. Requirements Self-hosted n8n instance. CustomJS API key for the PDF Toolkit nodes. SMTP account for sending emails. Optional: Access to the PDF template online. Workflow Steps Landingpage Endpoint (Webhook) Serves the landing page HTML to visitors. Set Form Endpoint Dynamically injects the endpoint URL into the HTML form. HTML for Landingpage Provides the form where users enter personal information (name, address, city, country, etc.). Respond to Webhook Returns the landing page HTML to the visitor. FormData Endpoint (Webhook) Receives the submitted form data as JSON. HTTP Request – Get PDF Template Fetches the PDF form template from a URL. PDF Form Fill (Fill PDF Fields) Populates the PDF with the submitted form data. Get PDF Form Fields (Optional) Reads and lists the names of the form fields in the PDF. Send Email Sends the completed PDF as an attachment to a configured recipient. Sticky Notes Provide documentation within the workflow for easier understanding and maintenance. Usage Get API key from CustomJS Sign up on the CustomJS platform. Navigate to your profile page and copy your API key. Set Credentials for CustomJS API in n8n Create a new credential in n8n with your API key. Prepare SMTP Credentials Add your SMTP server credentials to n8n for sending emails. Run or schedule the workflow The workflow will serve the landing page, fill the PDF form with submissions, and send it via email. Customization Tips Modify the landing page form** in the HTML node to add or remove fields. Change PDF template URL** in the HTTP Request node. Add more recipients** or dynamic email addresses in the Send Email node. Track submitted form data** in Google Sheets or a database for long-term storage. Extend workflow logic** with validation or notifications using additional nodes.

Description Automates website downtime detection and notifications using UptimeRobot. Triggers alerts via Slack, WhatsApp, or Email when a website goes down. Creates a task in Notion and tags the responsible engineer for resolution. Essential Information Monitors website status via UptimeRobot webhook. Sends immediate alerts to multiple channels (Slack, WhatsApp, Email). Generates a Notion task to track and assign downtime resolution. System Architecture Downtime Detection Pipeline**: UptimeRobot Webhook Trigger: Detects website status changes (triggers on "down" status). Alert Generation Flow**: Send Slack Alert: Notifies the team via Slack. Send WhatsApp Alert: Sends a message via WhatsApp. Send Email Alert: Emails the team about the downtime. Task Management**: Create Notion Task: Creates a task in Notion and tags the responsible engineer. Implementation Guide Import the workflow JSON into n8n. Configure UptimeRobot webhook with the workflow URL (trigger on "down" status). Set up Slack, WhatsApp, and Email credentials. Configure Notion integration and specify the responsible engineer tag. Test with a simulated downtime event. Monitor alert delivery and task creation accuracy. Technical Dependencies UptimeRobot API for website monitoring and webhook triggers. Slack API for team notifications. WhatsApp API (e.g., Twilio) for messaging. Email service (e.g., SMTP) for email alerts. Notion API for task management. n8n for workflow automation. Customization Possibilities Adjust UptimeRobot trigger to include additional status conditions (e.g., "paused"). Customize alert messages in Slack, WhatsApp, and Email nodes. Modify Notion task template to include more details (e.g., downtime duration). Add escalation logic for unresolved issues. Integrate with additional tools (e.g., PagerDuty) for alerts.

📚 Chat with Internal Documents (RAG AI Agent) ✅ Features Answers should given only within provided text. Chat interface powered by LLM (Ollama) Retrieval-Augmented Generation (RAG) using Supabase Vector DB Multi-format file support (PDF, Excel, Google Docs, text files) Automated file ingestion from Google Drive Real-time document update handling Embedding generation via Ollama for semantic search Memory-enabled agent using PostgreSQL Custom tools for document lookup with context-aware chat ⚙️ How It Works 📥 Document Ingestion & Vectorization Watches a Google Drive folder for new or updated files. Deletes old vector entries for the file. Uses conditional logic to extract content from PDFs, Excel, Docs, or text Summarizes and preprocesses content. (if needed) Splits and embeds the text via Ollama. Stores embeddings in Supabase Vector DB 💬 RAG Chat Agent Chat is initiated via Webhook or built-in chat interface. User input is passed to the RAG Agent. Agent queries the User_documents tool (Supabase vector store) using the Ollama model to fetch relevant content. If context is found, it answers directly. Otherwise, it can call tools or request clarification. Responses are returned to the user, with memory stored in PostgreSQL for continuity. 🛠 Supabase Database Configuration Create a Supabase project at https://supabase.com and go to the SQL editor. Create a documents table with the following schema: id - int8 content - text metadata - jsonb embedding - vector Generate an API Key

🌐 Webpage Audit AI Agent – Automate Your Website Review This workflow contains a virtual digital consultant team to professionally analyze Landing Page, generate Audit Report and sent it via Gmail. At the center is the Editor-in-Chief AI Agent, who acts as the lead strategist. When you submit a website URL, it is scraped and then sent to to a team of specialist AI Agents (each powered by GPT-4o-mini for speed) then after finishing their sub-porcess deliver outcome to the final Editor (Claude Sonnet for premium quality) which is responsible for generating professional analysis. The result: a consulting-style email audit report that combines technical accuracy with business clarity — delivered straight to your inbox. 🟢 Section 1 – Entry & Leadership Nodes: 🌍 Webhook node → Entry point where the website URL, email and language is entered. 📝 Editor-in-Chief Agent → Acts like the consulting team leader. Interprets the request and merges results. 💡 Think Tool → Helps structure the analysis, ensuring that findings are presented in a business-friendly way. 🧠 CRO/SEO/Tech AI Agents → Ensures both efficiency (GPT-4o-mini for scanning large content quickly) and focus on specific task. ✅ Beginner view: Think of this as submitting your website to a digital auditor. They decide what needs to be reviewed, delegate to the right experts, and then craft the final report. 📊 Section 2 – Specialist Audit AI Agents Each specialist focuses on one critical layer of your website: 🔧 Technical SEO Agent → Analyzes code structure, page speed, mobile responsiveness, metadata, and accessibility. 📝 Content SEO Agent → Reviews keyword strategy, text quality, readability, and semantic richness. 🎯 CRO & UX Agent → Checks calls-to-action, user flows, conversion points, and usability. 📈 Analytics Agent → Validates tracking, funnels, and key performance indicators (optional). ✅ Beginner view: This is like hiring a team of experts — SEO, content, UX, and analytics — all working in parallel on your website. 📋 Section 3 – Flow of Execution You submit your website URL. Then it is distributed to the team of AI Agents. Each Agent runs its analysis in parallel. Findings are sent to the Editor-in-Chief. The Editor compiles everything into a consulting-style newsletter report. The final report is emailed to you automatically. ✅ Beginner view: It’s like sending your site to a consulting firm, and within minutes you get a polished audit back in your inbox. 📊 Summary Table | Section | Key Roles | Models | Purpose | Beginner Benefit | |-----------------------|---------------------------------|----------------------------|------------------------------|-------------------------------------------| | 🟢 Entry & Leadership | Editor-in-Chief, Think Tool | Anthropic Claude Sonnet 4| Organize and refine analysis | Works like a consulting team leader | | 📊 Specialists | SEO, Content, CRO, Analytics | GPT-4o-mini | Detailed audits of each area | Each Agent = a specialized consultant | | 📋 Execution Flow | All connected | n8n workflow | Collaboration and reporting | Output = clear, professional audit email | 🌟 Why This Workflow Rocks Full digital consulting team in one workflow** Parallel execution → speed without losing depth** Strategic + tactical insights → both “what” and “how”** Cost-optimized** ($0.40–$0.70 per run) → cheaper than a single human consultant review Action-oriented output** → not just issues, but recommendations and next steps Scalable** → easily extend with more audit dimensions (security, branding, accessibility, etc.) 👉 Example Use Case “Analyze my e-commerce site for SEO, CRO, and technical issues.” Technical SEO Agent → Reports missing alt text, metadata, and slow mobile speed. Content SEO Agent → Flags weak product descriptions, suggests keyword improvements. CRO Agent → Finds unclear CTAs and checkout friction points. Editor-in-Chief Agent → Combines everything into a consulting-style email with prioritized fixes and estimated business impact. ✅ Delivered directly to your inbox in under 5 minutes.

The "WhatsApp Productivity Assistant with Memory and AI Imaging" is a comprehensive n8n workflow that transforms your WhatsApp into a powerful, multi-talented AI assistant. It's designed to handle a wide range of tasks by understanding user messages, analyzing images, and connecting to various external tools and services. The assistant can hold natural conversations, remember past interactions using a MongoDB vector store (RAG), and decide which tool is best suited for a user's request. Whether you need to check your schedule, research a topic, get the latest news, create an image, or even analyze a picture you send, this workflow orchestrates it all seamlessly through a single WhatsApp chat interface. The workflow is structured into several interconnected components: WhatsApp Trigger & Incoming Message Processing:** This is the entry point, starting when a message (text or image) is received via WhatsApp. A Route Message by Type (Image/Text) node then intelligently routes the message based on its content type. A Typing.... node sends a typing indicator to the user for a better experience. If an image is received, it's downloaded, processed via an HTTP Request, and analyzed by the Analyze image node. The Code1 node then standardizes both text and image analysis output into a single, unified input for the main AI agent. Core AI Agent:** This is the brain of the operation. The AI Agent1 node receives the user's input, maintains short-term conversational memory using Simple Memory, and uses a powerful language model (gpt-oss-120b2 or gpt-oss-120b1) to decide which tool or sub-agent to use. It orchestrates all the other agents and tools. Productivity Tools Agent:** This group of nodes connects the assistant to your personal productivity suite. It includes sub-agents and tools for managing Google Calendar, Google Tasks, and Gmail, allowing you to schedule events, manage to-dos, and read emails. It leverages a language model (gpt-4.1-mini or gemini-2.5-flash) for understanding and executing commands within these tools. Research Tool Agent:** This agent handles all research-related queries. It has access to multiple search tools (Brave Web Search, Brave News Search, Wikipedia, Tavily, and a custom perprlexcia search) to find the most accurate and up-to-date information from the web. It uses a language model (gpt-oss-120b or gpt-4.1-nanoChat Model1) for reasoning. Long-Term Memory Webhook:** A dedicated sub-workflow (Webhook2) that processes conversation history, extracts key information using Extract Memory Info, and stores it in a MongoDB Atlas Vector Store for long-term memory. This allows the AI agent to remember past preferences and facts. Image Generation Webhook: ** A specialized sub-workflow (Webhook3) triggered when a user asks to create an image. It uses a dedicated AI Agent with MongoDB Atlas Vector Store1 for contextual image prompt generation, Clean Prompt Text1 to refine the prompt, an HTTP Request to an external image generation API (e.g., Together.xyz), and then converts and sends the generated image back to the user via WhatsApp. Use Cases Personal Assistant:** Schedule appointments, create tasks, read recent emails, and manage your daily agenda directly from WhatsApp. Information Retrieval:** Ask any factual, news, or research-based question and get real-time answers from various web sources. Creative Content Generation:** Request the AI to generate images based on your descriptions for logos, artwork, or social media content. Smart Communication:** Engage in natural, contextual conversations with an AI that remembers past interactions. Image Analysis:** Send an image and ask the AI to describe its contents or answer questions about it. Pre-conditions Before importing and running this template, you will need: Self-hosted n8n Instance:** This template requires a self-hosted n8n instance as it uses webhooks that need public accessibility. WhatsApp Business Account:** A Meta Developer Account configured for WhatsApp Business Platform API access. MongoDB Atlas Account:** A MongoDB Atlas cluster with a database and collection set up for the vector store. Google Cloud Project:** Configured with API access for Google Calendar, Google Tasks, and Gmail. API Keys/Accounts for:** OpenWeatherMap: For weather forecasts. Groq, OpenRouter, or Vercel AI Gateway: For various Language Models (e.g., gpt-oss-120b, gpt-5-nano, gpt-4o-mini). Mistral Cloud: For embedding models (e.g., codestral-embed-2505). Brave Search: For web and news searches. Tavily API: For structured search results. Together.xyz or similar Image Generation API: For creating images. Perplexity API (or self-hosted instance): For the perprlexcia tool (the current URL http://self hoseted perplexcia/api/search implies a self-hosted or custom endpoint). Publicly Accessible URLs:** Your n8n instance and any custom webhook endpoints (like perprlexcia) must be publicly accessible. Requirements (n8n Credentials) You will need to set up the following credentials within your n8n instance: WhatsApp OAuth account:** For the WhatsApp Trigger node. WhatsApp account:** For Send message2, Send message3, Download media, and Typing.... nodes. Google Palm Api account:** For Analyze image, Google Gemini Chat Model, gemini-2.5-flash, and Google Gemini Chat Model5 nodes. OpenWeatherMap account:** For the Get Weather Forecast node. Groq account:** For gpt-oss-120b node. Google Calendar OAuth2Api account:** For the Google Calendar tools. MongoDB account:** For MongoDB Atlas Vector Store nodes. OpenRouter account:** For gpt-5-nano and gpt-4.1-nanoChat Model1 nodes. Gmail account :** For Get many messages and Get a message nodes (ensure correct Gmail OAuth2 setup for each). Google Tasks account:** For the Google Tasks tools. Bearer Auth account:** For HTTP Request5 (used in media download). Brave Search account:** For Brave Web Search and Brave News Search nodes. Vercel Ai Gateway Api account:** For gpt-4.1-mini, gpt-oss-120b, gpt-oss-120b2, and gpt-4.1-nano nodes. HTTP Header Auth account:** For Tavily web search (create a new one named "Tavily API Key" with Authorization: Bearer YOUR_TAVILY_API_KEY) and HTTP Request (for Together.xyz, e.g., "Together.xyz API Key"). Mistral Cloud account:** For codestral-embed-2505, codestral-embed-, and codestral-embed-2506 nodes.

An intelligent automation workflow that processes website demo requests, qualifies leads using AI-powered analysis, and automatically nurtures prospects through personalized follow-up sequences to maximize conversion rates. Overview This workflow transforms raw website leads into qualified prospects through intelligent filtering, enrichment, and personalized nurturing. It combines AI-powered qualification with automated follow-up to ensure high-quality leads receive immediate attention while nurturing those needing additional touchpoints. 🔄 Workflow Process 1. Entry Point - Webhook Website form submission capture Receives demo requests from website forms in real-time Captures lead data including LinkedIn URL, email, use case, and referral source 2. Initial Routing Filter Source-based lead classification Filters out low-quality leads from "lead_capture_box" sources Routes qualified submissions to enrichment process 3. Lead Enrichment Comprehensive data enhancement Enriches LinkedIn profile data via Trigify API Gathers additional company and professional intelligence 4. AI Qualification Engine Intelligent prospect evaluation Uses Claude AI to assess lead quality across multiple criteria: B2B company validation Geographic filtering (US, UK, Europe, Australia) Senior-level job titles or strategic keywords Current employment verification 5. Booking Verification Check Conversion status validation Checks Cal.com API to verify demo scheduling Routes booked leads to completion, non-booked to nurturing 6. AI-Powered Follow-up Research Personalized nurturing preparation Researches prospect's company using AI and web search Generates personalized follow-up messaging based on use case and company context 7. Email Campaign Integration Automated nurturing execution Adds qualified, non-booking leads to Instantly.ai email campaigns Includes personalized research for tailored outreach 🛠️ Technology Stack n8n**: Workflow orchestration Trigify API**: Lead enrichment Claude AI**: Qualification and personalized research Clay**: CRM integration Cal.com API**: Booking verification Instantly.ai**: Email campaign automation ✨ Key Features Real-time lead processing and AI-powered qualification Geographic and demographic filtering for market focus Automated booking verification and conversion tracking Personalized follow-up research and content generation Multi-platform integration for seamless lead management 🎯 Ideal Use Cases Perfect for B2B companies with demo-driven sales processes: SaaS companies requiring product demonstrations B2B service providers needing qualified prospect identification Sales teams managing high-volume inbound lead qualification Organizations with international markets requiring geographic focus 📈 Business Impact Transform website visitors into qualified sales opportunities: Lead Quality Enhancement**: AI filtering ensures only qualified prospects reach sales Conversion Optimization**: Systematic follow-up increases demo booking rates Sales Efficiency**: Automated qualification frees teams for high-value activities Personalized Engagement**: Research-driven follow-up increases response rates 💡 Strategic Advantage This workflow creates a sophisticated qualification funnel that combines automation with personalization. By using AI-powered assessment and research-driven follow-up, it ensures qualified prospects receive appropriate attention while preventing resource waste on unqualified leads. The system maximizes the value extracted from every website visitor by focusing sales efforts on highest-probability opportunities while automatically nurturing prospects who need additional touchpoints to convert.

Unleash the full potential of your website's search engine performance and user experience with this all-in-one n8n automation template. Designed for SEO professionals and webmasters, this suite provides meticulous on-page and technical SEO auditing, deep insights into Core Web Vitals (LCP & INP), and an intelligent AI-powered chatbot for instant insights and troubleshooting. Key Features: Comprehensive On-Page SEO Audit: Automatically checks for **missing or malformed titles, meta descriptions, H1s (including multiple H1s), missing alt text on images, and canonical tag issues. Detailed Technical SEO Scan: Verifies **HTTPS implementation, robots.txt accessibility and content, and sitemap.xml presence. Core Web Vitals Monitoring: Leverages **Google PageSpeed Insights to continuously track and alert on critical performance metrics like Largest Contentful Paint (LCP) and Interaction to Next Paint (INP). AI-Powered Analysis & Recommendations: Integrates advanced AI models (ChatGPT, Claude, or Gemini) to **analyze audit findings, provide actionable recommendations for improvements, and even suggest better alt text for images based on content context. Intelligent SEO Chatbot: A dynamic chatbot triggered by webhooks understands natural language queries, extracts entities (URLs, keywords, SEO topics), and provides **instant, AI-generated answers about SEO best practices, Core Web Vitals explanations, or even specific site data (via Google Search Console integration). Automated Reporting & Alerts: Logs all audit data to **Google Sheets for historical tracking and sends real-time Slack alerts for critical SEO issues or performance degradations. Streamline your SEO workflow, ensure optimal website health, and react swiftly to performance challenges. This template is your ultimate tool for staying ahead in the competitive digital landscape.

📧 What It Does This n8n workflow sends personalized marketing or outreach emails using predefined templates stored in Google Sheets, with SendGrid as the email delivery provider. Instead of relying on dynamic AI content, this setup selects a ready-made template and merges it with business-specific lead data — delivering consistent and fast email personalization at scale. 💡 Why This Workflow? Sometimes, you don’t need the overhead or variability of AI-generated content. Predefined templates give you: ⚡ Faster execution — no calls to AI models 🎯 Total control over tone, formatting, and structure 🛠️ Easy customization using variables like [BusinessName], [Location], etc. 💰 Zero additional cost per email 👤 Who It’s For Freelancers* or *Agencies** running outreach campaigns Startups* or *SMBs** with lead data in Google Sheets Anyone who wants to automate email sending with consistency, control, and low cost. ⚙️ How It Works Manual Trigger starts the workflow. Google Sheets (Leads tab) supplies a list of businesses with fields like name, location, email, category, etc. Loop started to execute each item. Google Sheets (Email Template tab) holds predefined subject and body templates (HTML supported). A random template is selected for each email. Placeholders like [BusinessName] or [Category] are replaced with actual lead info using the Fix Variable (Set) node. The formatted message is sent via SendGrid, using your authenticated sender email. A 1-second wait is added between emails to manage rate limits and avoid spam flags. Loop continues until all leads have been emailed. 🛠 How to Set It Up Import the .json file into your n8n instance. Connect the required credentials: SendGrid API Key (ensure sender domain and identity is verified) Google Sheets OAuth2 Create or duplicate this sample sheet, which contains two tabs and modify to your business interest: Leads Email Template Update the leads and email templates to match your campaign. Click “Execute Workflow” to begin sending emails. 🚀 Want to Scale This? Add additional workflows: 📬 SendGrid Webhook integration to track status & engagements like bounces, opens, and clicks 🔁 Reply tracker via Gmail to update lead status 🤖 AI-based Email Router to label replies as Interested, Not Interested, Others, Forward emails to appropriate department for further engagements. 📆 Follow-up Emails (when there's no email reply) for D+5, D+10 days sequences 📬 Need Help? Feel free to reach out via email: buzanalytics@gmail.com Thanks for using this workflow

Workflow explaination: https://youtu.be/ecafBTFPuvE?si=7csA1yNsaUxUG72F This workflow is designed to automatically handle new freelance project requests from a JotForm, analyze the requirements using AI, create a custom proposal, log the details in a Google Sheet, and send a personalized response to the client. 1. JotForm Trigger Purpose**: This node is the entry point of the entire automation. It waits for a new freelance project submission from your specified JotForm. Action: When a potential client fills out and submits the form, this node **instantly triggers the workflow, passing all submitted data (name, email, project requirements, and budget) to the next node. Key Detail**: Uses a webhook for real-time activation, ensuring immediate processing of every new project request. 2. AI Agent Purpose**: The central brain of your freelance workflow. 🧠 It takes the project submission and turns it into a structured, customized proposal. Action**: The agent follows a prompt sequence to perform these tasks: Calls the My Freelance Document Tool: Fetches your Google Doc containing details about your services, pricing, and project templates — your “source of truth.” Analyzes the Project Request: Reads the client’s requirements and goals from the form. Generates a Custom Proposal: Based on scope, budget, and relevance to your offerings, it prepares a short, tailored proposal or quote that fits the project. Creates a Personalized Email: Builds an HTML email with the proposal embedded, including next steps or a scheduling link for further discussion. Outputs Structured Data: Packages everything (project summary, proposal text, email subject, and body) into a clean JSON object for downstream use. 3. Append or Update Row in Sheet (Google Sheets) Purpose**: Serves as your lightweight CRM for all project inquiries. Action**: Logs data from the AI Agent (proposal details, client info, and project summary) into a Google Sheet. Key Detail: Configured to **Append or Update—if an email already exists, it updates that row instead of duplicating. Keeps your client records clean and organized. 4. If Purpose**: Acts as a control node to decide whether a proposal email should be sent. Action**: Checks the output from the AI Agent to ensure the proposal text is valid (not empty). Key Detail**: If the proposal generation fails or returns “NAN,” the workflow stops here to avoid sending incomplete responses. 5. Send a Message (Gmail) Purpose**: Sends the final personalized proposal email to the client. Action: Pulls the recipient’s email from the sheet and sends the **AI-generated subject and HTML proposal email automatically. Key Detail**: The email is customized per project, giving the client an instant, professional response with no manual effort.

AI-powered Meeting Summaries and Action Items to Slack and ClickUp How it Works Webhook Trigger: The workflow starts when Fireflies notifies that a transcription has finished. Transcript Retrieval: The transcript is pulled from Fireflies based on the meeting ID. Pre-processing: The transcript is split into sentences and then aggregated into a raw text block. AI Summarization: The aggregated transcript is sent to Google Gemini, which generates a short summary and a structured list of action items. Post-processing: The AI response is cleaned and formatted into JSON. Action items are mapped to titles and descriptions. Distribution: The meeting summary is posted to Slack. Action items are created as tasks in ClickUp. Use Case This workflow is designed for teams that want to reduce the manual effort of writing meeting notes and extracting action items. Automatically generate a clear and concise meeting summary Share the summary instantly with your team on Slack Ensure action items are not lost by automatically creating tasks in ClickUp Ideal for distributed teams, project managers, and product teams managing recurring meetings Requirements n8n instance** set up and running Fireflies.ai account** with API access to meeting transcripts Google Gemini API (via PaLM credentials)** for AI-powered summarization Slack account** with OAuth2 credentials connected in n8n ClickUp account** with OAuth2 credentials connected in n8n