Building your first WhatsApp chatbot
This n8n template builds a simple WhatsApp chabot acting as a Sales Agent. The Agent is backed by a product catalog vector store to better answer user's questions. This template is intended to help introduce n8n users interested in building with WhatsApp. How it works This template is in 2 parts: creating the product catalog vector store and building the WhatsApp AI chatbot. A product brochure is imported via HTTP request node and its text contents extracted. The text contents are then uploaded to the in-memory vector store to build a knowledgebase for the chatbot. A WhatsApp trigger is used to capture messages from customers where non-text messages are filtered out. The customer's message is sent to the AI Agent which queries the product catalogue using the vector store tool. The Agent's response is sent back to the user via the WhatsApp node. How to use Once you've setup and configured your WhatsApp account and credentials First, populate the vector store by clicking the "Test Workflow" button. Next, activate the workflow to enable the WhatsApp chatbot. Message your designated WhatsApp number and you should receive a message from the AI sales agent. Tweak datasource and behaviour as required. Requirements WhatsApp Business Account OpenAI for LLM Customising this workflow Upgrade the vector store to Qdrant for persistance and production use-cases. Handle different WhatsApp message types for a more rich and engaging experience for customers.
By JimleukRespond to WhatsApp messages with AI like a pro!
This n8n template demonstrates the beginnings of building your own n8n-powered WhatsApp chatbot! Under the hood, utilise n8n's powerful AI features to handle different message types and use an AI agent to respond to the user. A powerful tool for any use-case! How it works Incoming WhatsApp Trigger provides a way to get messages into the workflow. The message received is extracted and sent through 1 of 4 branches for processing. Each processing branch uses AI to analyse, summarize or transcribe the message so that the AI agent can understand it. The supported types are text, image, audio (voice notes) and video. The AI Agent is used to generate a response generally and uses a wikipedia tool for more complex queries. Finally, the response message is sent back to the WhatsApp user using the WhatsApp node. How to use Once you have setup and configured your WhatsApp account, you'll need to activate your workflow to start processing messages. Good to know: Large media files may negatively impact workflow performance. Requirements WhatsApp Buisness account Google Gemini for LLM. Gemini is used specifically because it can accept audio and video files whereas at time of writing, many other providers like OpenAI's GPT, do not. Customising this workflow For performance reasons, consider detecting large audio and video before sending to the LLM. Pre-processing such files may allow your agent to perform better. Go beyond and create rich and engagement customer experiences by responding using images, audio and video instead of just text!
By JimleukSuggest meeting slots using AI
The purpose of this n8n workflow is to automate the process of identifying incoming Gmail emails that are requesting an appointment, evaluating their content, checking calendar availability, and then composing and sending a response email. Note that to use this template, you need to be on n8n version 1.19.4 or later.
By n8n TeamAI Personal Assistant
Email Personal Assistant - Comprehensive Communication Manager This automation flow is designed to proactively monitor email, calendar, and Slack communications, analyze priorities across all channels, and generate a comprehensive daily briefing with actionable tasks for executive productivity management. ⚙️ How It Works (Step-by-Step): ⏰ Automated Daily Trigger Runs automatically on weekdays: Scheduled execution every weekday at 8:00 AM Manual trigger available for on-demand analysis Comprehensive daily communication audit 📧 Email Assistant Agent Analyzes inbox priorities and context: Scans unread emails across "To Respond" and "FYI" labels Checks email history to determine relationship context Identifies *company-related opportunities and partnerships Categorizes emails by urgency (High, Medium, Low) Cross-references with sent emails for follow-up context 📅 Follow-Up Assistant Agent Monitors meeting follow-up requirements: Reviews last 3 days of calendar meetings Fetches Fireflies transcripts for recorded sessions Identifies meetings without post-meeting communication Flags meetings requiring action items or follow-ups Checks sent emails and Slack for completed follow-ups 💬 Slack Assistant Agent Tracks Slack communication priorities: Monitors direct messages and @mentions Identifies unreplied Slack conversations Cross-references with email and calendar context Prioritizes responses based on sender importance Checks for threaded conversations requiring attention 🎯 Master Orchestrator Agent Synthesizes all communication data: Combines reports from all three assistant agents Cross-references with existing Google Sheets to-do list Prioritizes tasks by urgency and business impact Identifies correlations between different communication channels Creates comprehensive daily action plan 📊 Task Management Integration Automated tracking and delivery: Appends new tasks to Google Sheets to-do tracker Sends personalized daily briefing via Slack DM Maintains conversation memory for context continuity Tracks outstanding vs. completed items 🛠️ Tools Used: n8n: Workflow orchestration and scheduling Claude Sonnet 4 & Opus 4: Multi-agent AI analysis Gmail API: Email monitoring and history checking Google Calendar: Meeting tracking and scheduling Slack API: Message monitoring and user management Fireflies API: Meeting transcript analysis Google Sheets: Task tracking and persistence 📦 Key Features: Multi-channel communication monitoring (Email, Calendar, Slack) AI-powered priority assessment and context analysis Cross-platform relationship tracking and history Automated daily briefing generation and delivery Persistent task tracking with Google Sheets integration Meeting follow-up verification and flagging Conversation memory for continuity across sessions 🚀 Ideal Use Cases: C-level executives managing multiple communication channels Sales leaders tracking prospect interactions and follow-ups Business development professionals managing partnerships Busy professionals needing communication prioritization Teams requiring systematic follow-up management Anyone wanting automated daily productivity briefings
By Max Mitcham🔍🛠️Generate SEO-optimized WordPress content with AI powered perplexity research
Generate SEO-Optimized WordPress Content with Perplexity Research Who is This For? This workflow is ideal for content creators, marketers, and businesses looking to streamline the creation of SEO-optimized blog posts for WordPress. It is particularly suited for professionals in the AI consulting and workflow automation industries. --- What Problem Does This Workflow Solve? Creating high-quality, SEO-friendly blog posts can be time-consuming and challenging, especially when trying to balance research, formatting, and publishing. This workflow automates the process by integrating research capabilities, AI-driven content creation, and seamless WordPress publishing. It reduces manual effort while ensuring professional-grade output. --- What This Workflow Does Research: Gathers detailed insights from Perplexity AI based on user-provided queries. Content Generation: Uses OpenAI models to create structured blog posts, including titles, slugs, meta descriptions, and HTML content optimized for WordPress. Image Handling: Automatically fetches and uploads featured images to WordPress posts. Publishing: Drafts the blog post directly in WordPress with all necessary formatting and metadata. Notification: Sends a success message via Telegram upon completion. --- Setup Guide Prerequisites: A WordPress account with API access. OpenAI API credentials. Perplexity AI API credentials. Telegram bot credentials for notifications. Steps: Import the workflow into your n8n instance. Configure API credentials for WordPress, OpenAI, Perplexity AI, and Telegram. Customize the form trigger to define your research query. Test the workflow using sample queries to ensure smooth execution. --- How to Customize This Workflow to Your Needs Modify the research query prompt in the "Form Trigger" node to suit your industry or niche. Adjust content generation guidelines in the "Copywriter AI Agent" node for specific formatting preferences. Replace the image URL in the "Set Image URL" node with your own source or dynamic image selection logic.
By Joseph LePageScrape any web page into structured JSON data with ScrapeNinja and AI
Disclaimer: This template only works on self-hosted for now, as it uses a community node. Use Case Web scrapers often break due to web page layout changes. This workflow attempts to mitigate this problem by auto-generating web scraping data extractor code via LLM. How It Works This workflow leverages ScrapeNinja n8n community node to: scrape webpage HTML, feed it into LLM (Google Gemini) and ask to write a JS extractor function code, then it executes the written JS extractor against scraped HTML to extract useful data from webpage (the code is safely executed in a sandbox) Installation To install ScrapeNinja n8n node, in your self-hosted instance, go to Settings -> Community nodes, enter "n8n-nodes-scrapeninja", and install. Make sure you are using at least v0.3.0. See this in action: https://www.linkedin.com/feed/update/urn:li:activity:7289659870935490560/
By AnthonyAi prompt generator workflow
🧠 AI Prompt Generator Workflow – n8n Documentation Who is this for? This workflow is for AI builders, prompt engineers, developers, marketers, and no-code creators who want to convert rough user input into structured, high-quality prompts for LLMs. It’s especially useful for tools that rely on precision prompting and want to automate the discovery of intent and constraints. --- What problem is this workflow solving? / Use case Many users struggle to write effective prompts due to vague ideas or unclear formatting needs. This workflow: Collects structured user input. Dynamically generates clarifying questions. Returns a well-formatted AI prompt based on the user's intent and context. This ensures the generated prompt is useful for downstream AI agents without requiring technical understanding from the end user. --- What this workflow does Start with a branded form UI The user is shown a styled form with questions like: What do you want to build? What tools can you access? What input can be expected? What output do you expect? Analyze and generate relevant follow-up questions The workflow sends the user's answers to Google Gemini (via LangChain) which outputs 1–3 clarifying questions. These questions are parsed into a dynamic form. Loop through and collect follow-up answers Each follow-up question is shown in a form one at a time to capture additional context. Merge all inputs The base intent and follow-up responses are merged into a single context block. Generate a final AI-ready prompt The prompt generator node formats everything into a clean, six-section structure: <constraints> <role> <inputs> <tools> <instructions> <conclusions> Display the final result The finished prompt is shown in a clean UI where users can easily copy and reuse it. --- Setup Credentials Required Google Gemini (PaLM) API credentials (already integrated as Google Gemini(PaLM) Api account 2). Form Trigger Ensure the On form submission trigger is exposed via a webhook or public endpoint (e.g. using ngrok or deployed server). Styling Custom CSS is included in all form nodes for a beautiful UI. You can modify this to match your branding. Environment This workflow is compatible with self-hosted n8n or n8n.cloud. Webhooks must be accessible to users who will fill out the form. --- How to customize this workflow to your needs Change the base questions Update the BaseQuestions form node to add or remove fields depending on your use case. Modify Gemini prompts You can edit the system prompt inside PromptGenerator to change tone, output structure, or AI instructions. Change prompt formatting If you use a different AI agent (like GPT, Claude, or Mistral), adjust the section labels and formatting to suit that agent’s expected input. Send results elsewhere Add integration nodes after PromptGenerator, such as: Google Docs / Notion (to log prompts) Gmail / Slack (to notify your team) Zapier / Make (to push to other automation flows) Skip follow-up questions (optional) If your base form collects all needed info, you can bypass the RelevantQuestions form section by modifying conditional logic. --- Example Output Prompt (Structure) <role> You are an AI assistant that converts videos into LinkedIn posts with a witty tone. </role> <inputs> - A short video (max 5 minutes) - Desired tone: witty - Style: both summary and quotes - Audience: general network </inputs> <tools> You do not have access to APIs or web search. </tools> <instructions> 1. Parse transcript. 2. Extract insights and quotes. 3. Write an engaging, witty LinkedIn post under 3000 characters. </instructions> <constraints> Avoid technical jargon. No generic intros. Make it platform-native. </constraints> <conclusions> Return a LinkedIn-ready post that starts with a hook and ends with hashtags.
By Anurag SrivastavaTelegram bot starter template setup & AI agent chatbot
Telegram Bot Starter template workflow + n8n AI Agent Chatbot provides a foundational setup for creating powerful Telegram bots with n8n. It handles incoming messages, photos, files, and voice notes, making it an excellent starting point for developers looking to create bots for customer engagement, support, or interactive services. Sign up to n8n now → and try it! Key Features: Dynamic Message Handling: Respond to text messages, photos, files, and more. Modular Design: Easily integrate additional workflows such as user registration, payment modules, or custom commands. Error Handling: Ensure the bot gracefully manages errors and user inputs. Extensibility: This workflow is the base for building any Telegram bot. Additional modules, such as a user registration module, payment integration, and user profile management, are available for easy connection to expand the bot’s functionality. ✍🏻Use the Telegram user registration workflow → 💵Use the Telegram Payment, Invoicing and Refund Workflow for Stars → Who Can Use This Workflow? Developers looking for a quick way to build and customize Telegram bots. Businesses and service providers who need customer interaction automation. Setup Instructions: Replace Telegram credentials with your own API credentials. Customize responses for different message types (text, photo, file). If integrating with external services (like Google Sheets), update the necessary credentials and links. UPDATES: 🔥 Get the most up-to-date and expanded version → June 25: New! AI Agent + Setup Instructions Simple setup instructions and examples are included inside the workflow as sticky notes. Sep 24: Improved message handler: Updated logic to handle various types of messages using Switch (text, photo, file, voice, and callback). Payment processing: Added new nodes for sending invoices and handling payments via Telegram Aug 24: Changed processing of system events: “new user” and ‘user who blocked bot’ events Please reach out to Victor if you need further assistance with your n8n workflows and automations! Sign up to n8n →, you have to try it!
By Victor GoldLinkedIn job search: auto-match resume with AI + cover letter & Telegram alerts
Overview This n8n templates helps you to authomatically search Linkeding jobs. It uses AI (Gemini or OpenAPI) to match your resume with each job description and write a sample cover letter for each job and update the job google sheet. You can receive daily matched linkedin job alerts by telegram. Prerequisites AI API Key from one model like: Google Gemini OpenAI Telegram Bot Token - Create via @BotFather Google Sheets - OAuth2 credentials Google Drive - OAuth2 credentials Setup Upload your resume Upload your CV in PDF format in google drive and configure google drive node to read your resume from list of google drive files. You need to configure Google Drive OAuth2 and grant access to your drive before that. You can find useful infomration about how to configure Googel OAuth2 API key in n8n documents. Create Google sheet You need to create a google sheet document consist of two sheets, one sheet for define job filter criteria and second sheet to store job search result. You can download this Google Sheet Template and copy in your personal space. Then you can add your job filter in Google sheet. You can search job by keywords, location, remote type, job type and easy apply. You need to configure Google Sheet OAuth2 and grant access to your drive before that. Conifgure Telegram Bot You need to create a new Telegram Bot in @BotFather and insert API Key in Telegram node and you need to TELEGRAMCHATID to your telegram ID.
By Hojjat JashnniloofarBuild custom workflows automatically with GPT-4o, RAG, and web search
🚀 What the “Agent Builder” template does Need to turn a one-line chat request into a fully-wired n8n workflow template—complete with AI agents, RAG, and web-search super-powers—without lifting a finger? That’s exactly what Agent Builder automates: Listens to any incoming chat message (via the Chat Trigger). Spins up an AI architect that analyses the request, searches the web, reads n8n docs from a Pinecone vector store, and designs the smallest possible set of nodes. Auto-generates a ready-to-import JSON template and hands it back as a downloadable file—plus all the supporting assets (embeddings, vector store etc.) so the next prompt is even smarter. Think of it as your personal “workflow chef”: you shout the order, it shops for ingredients, cooks, plates, and serves the meal. All you do is eat. --- 🤗 Who will love this? No-code builders / power users who don’t want to wrestle with AI node wiring. Agencies & consultants delivering lots of bespoke automations. Internal platform teams who need a “workflow self-service portal” for non-technical colleagues. --- 🧩 How it’s wired | Sub-process | What happens inside | Key nodes | | -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------- | | Web Crawler (optional) | Firecrawl scrapes docs.n8n.io (or any URL you drop in) and streams raw markdown back. | Set URL → HTTP Request (Extract) → Wait & Retry | | RAG Trainer | Splits the scraped docs, embeds them with OpenAI, and upserts vectors into Pinecone. | Recursive Text Splitter → Embeddings OpenAI → Train Pinecone | | Agent Builder | The star of the show – orchestrates GPT-4o (via OpenRouter), SerpAPI web-search, your Pinecone index and a Structured Output Parser to produce → validate → prettify the final n8n template. | Chat Trigger → AI Agent → OpenAI (validator) → Code (extract) → Convert to JSON file | Every arrow in the drawn workflow is pre-connected, so the generated template always passes n8n’s import check. --- 🛠️ Getting set up (5 quick creds) | Service | Credential type | | --------------------------------------------------- | ---------------------------------------------------------- | | OpenAI / Azure OpenAI – embeddings & validation | OpenAI API | | Pinecone – vector store | Pinecone API | | OpenRouter – GPT-4o LLM | OpenRouter API Key | | SerpAPI – web search | SerpAPI Key | | Firecrawl (only if you plan to crawl) | Generic Header Auth → Authorization: Bearer YOUR_KEY | Each node already expects those creds; just create them once, select in the dropdown, hit Activate. --- 🏃♀️ What a typical run looks like User says: “Build me a workflow that monitors our support inbox, summarises new tickets with GPT and posts to Slack.” Chat Trigger captures the message. AI Agent: queries Pinecone for relevant n8n docs, fires a SerpAPI search for “n8n gmail trigger example”, sketches an architecture (Gmail Trigger → GPT Model → Slack). The agent returns JSON ➜ OpenAI node double-checks field names, connections, type versions. A tiny JS Code node slices the JSON out of the chat blob and saves it as template.json ready for download. You download, import, and… done. --- ✏️ Customising Switch the LLM – plug in Claude 3, Gemini 1.5, or a local model; just swap the OpenRouter Chat Model* node. Point the RAG at your own docs – change the crawl URL or feed PDFs via the Default Data Loader*. Hard-code preferred nodes – edit the “User node preferences” in the system message so the agent always chooses Notion* for databases, etc. --- 🥡 Take-away notes It's a prototype feel free to experiment with it to improve its capabilities. Have fun building!
By FranzDeep Research - Sales Lead Magnet Agent
Want to check out all my flows, follow me on: https://maxmitcham.substack.com/ https://www.linkedin.com/in/max-mitcham/ This automation flow is designed to generate comprehensive, research-backed lead magnet articles based on a user-submitted topic, conduct deep research across multiple sources, and automatically create a professional Google Doc ready for LinkedIn sharing. ⚙️ How It Works (Step-by-Step): 📝 Chat Input (Entry Point) A user submits a topic through the chat interface: Topic for lead magnet content Target audience (automatically detected) Company context (when relevant) 🔍 Query Builder Agent An AI agent refines the input by: Converting the topic into 5 targeted research queries Determining if topic relates to *company for specialized research Using structured output parsing for consistent results 📚 Research Leader Agent Conducts comprehensive research that: Uses Perplexity API for real-time web research Integrates *company knowledge base when relevant Creates detailed table of contents with research insights Identifies key trends, expert opinions, and case studies 📋 Project Planner Agent Structures the content by: Generating professional title and subtitle Creating 8-10 logical chapter outlines Developing detailed writing prompts for each section Ensuring step-by-step actionable guidance ✍️ Research Assistant Team Multiple AI agents write simultaneously: Each agent writes one chapter with proper citations Maintains consistent voice across all sections Includes real-world examples and implementation steps Uses both web research and *company knowledge 📝 Editor Agent Professional content polishing: Refines tone for authenticity and engagement Adds image placeholders where appropriate Ensures proper flow between chapters Optimizes for LinkedIn lead magnet format 📄 Google Docs Creation Automated document generation: Creates new Google Doc with formatted content Sets proper sharing permissions (public link) Organizes in designated company folder Returns shareable URL for immediate use 🛠️ Tools Used: n8n: Workflow orchestration platform Anthropic Claude: Primary AI model for content generation OpenRouter: Backup AI model options Perplexity API: Real-time research capabilities *Company Knowledge Hub: Internal documentation access Google Docs API: Document creation and formatting Google Drive API: File management and sharing 📦 Key Features: End-to-end automation from topic to published document Multi-agent approach ensures comprehensive coverage Real-time research with proper citations Company-specific knowledge integration Professional editing and formatting Automatic Google Docs creation with sharing Scalable content generation (3-5 minutes per article) 🚀 Ideal Use Cases: B2B companies building thought leadership content Sales teams creating industry-specific lead magnets Marketing departments scaling content production Consultants developing expertise-demonstrating resources SaaS companies creating feature-focused educational content Startups establishing market presence without content teams
By Max MitchamAdvanced AI demo (presented at AI Developers #14 meetup)
This workflow was presented at the AI Developers meet up in San Fransico on 24 July, 2024. AI workflows Categorize incoming Gmail emails and assign custom Gmail labels. This example uses the Text Classifier node, simplifying this usecase. Ingest a PDF into a Pinecone vector store and chat with it (RAG example) AI Agent example showcasing the HTTP Request tool. We teach the agent how to check availability on a Google Calendar and book an appointment.
By Max Tkacz