Workflow Templates

Who’s it for This template is perfect for TikTok creators, content marketers, and social media teams who want to turn viral comments into engaging short-form videos without manually scripting, recording, or editing. If you want to keep up with trends and consistently publish high-quality avatar videos, this workflow automates the entire process from comment selection to enhanced final video. What it does The workflow takes TikTok video URLs and their top comments from a Data Table, extracts the transcript using Dumpling AI, and uses GPT-4 to write a natural and engaging TikTok script inspired by the comment. It then generates a full AI avatar video through Captions.ai, enhances it with subtitles and B-roll using Submagic, and finally saves all video details into Airtable for tracking. Here’s what happens step by step: Pulls TikTok videos and their top comments from a Data Table Sends video URLs to Dumpling AI to retrieve transcripts Feeds both transcript and comment into GPT-4 to generate a conversational TikTok script Cleans and formats the script using JavaScript Sends the script to Captions.ai to produce an AI avatar video Checks video status and retries if needed Enhances the final video with Submagic for captions and effects Receives the enhanced video via webhook and logs details into Airtable How it works Schedule Trigger: Runs automatically at set intervals to start the workflow Data Table: Retrieves TikTok video URLs and associated comments Dumpling AI: Extracts transcripts from the video URLs GPT-4: Generates a compelling TikTok script based on the comment JavaScript Node: Cleans up script formatting for a smooth avatar generation Captions.ai: Creates an AI avatar video from the cleaned script Wait & Check: Monitors video creation status and retries if necessary Submagic: Enhances the video with captions, zooms, and B-roll effects Webhook & Airtable: Receives final video data and saves URL and ID for future use Requirements ✅ Dumpling AI API key stored as HTTP header credentials ✅ OpenAI GPT-4 credentials ✅ Captions.ai API credentials ✅ Submagic API credentials ✅ Airtable base with fields for Video URL and Caption Video ID ✅ A properly structured Data Table containing TikTok Keywords or video URLs How to customize Adjust the GPT-4 system prompt to shape the tone, style, or format of the TikTok script Change the avatar or creator settings in Captions.ai to match your brand personality Modify Submagic settings to control subtitle styling or B-roll effects Integrate approval steps before final video generation if needed Extend the workflow to auto-publish videos to TikTok or store them in cloud drives > This workflow lets you transform TikTok comments into engaging AI avatar videos with captions and edits, completely on autopilot. It’s a powerful way to scale content output and stay ahead of trends without manual scripting or filming.

Stop manually searching for songs and let an AI DJ do the work for you. This template provides a complete, end-to-end system that transforms any text prompt into a ready-to-play Spotify playlist. It combines the creative understanding of a powerful AI Agent with the real-time web knowledge of Linkup to curate perfect, up-to-the-minute playlists for any occasion. The experience is seamless: simply describe the vibe you're looking for in a web form, and the workflow will automatically create the playlist in your Spotify account and redirect you straight to it. Whether you need "upbeat funk for a sunny afternoon" or "moody electronic tracks for late-night coding," your personal AI DJ is ready to deliver. Who is this for? Music lovers:** Create hyper-specific playlists for any mood, activity, or niche genre without the hassle of manual searching. DJs & event planners:** Quickly generate themed playlists for parties, weddings, or corporate events based on a simple brief. Content creators:** Easily create companion playlists for your podcasts, videos, or articles to share with your audience. n8n developers:** A powerful example of how to build an AI agent that uses an external web-search tool to accomplish a creative task. What problem does this solve? Creates up-to-date playlists:** A standard AI doesn't know about music released yesterday. By using Linkup's live web search, this workflow can find and include the very latest tracks. Automates the entire creation process:** It handles everything from understanding a vague prompt (like "songs that feel like a summer road trip") to creating a fully populated Spotify playlist. Saves time and effort:** It completely eliminates the tedious task of searching for individual tracks, checking for relevance, and manually adding them to a playlist one by one. Provides a seamless user experience:** The workflow begins with a simple form and ends by automatically opening the finished playlist in your browser. There are no intermediate steps for you to manage. How it works Submit your playlist idea: You describe the playlist you want and the desired number of tracks in a simple, Spotify-themed web form. The AI DJ plans the search: An AI Agent (acting as your personal DJ) analyzes your request. It then intelligently formulates a specific query to find the best music. Web research with Linkup: The agent uses its Linkup web-search tool to find artists and tracks from across the web that perfectly match your request, returning a list of high-quality suggestions. The AI DJ curates the list: The agent reviews the search results and finalizes the tracklist and a creative name for your playlist. Build the playlist in Spotify: The workflow takes the agent's final list, creates a new public playlist in your Spotify account, then searches for each individual track to get its ID and adds them all. Instant redirection: As soon as the last track is added, the workflow automatically redirects your browser to the newly created playlist on Spotify, ready to be played. Setup Connect your accounts: You will need to add your credentials for: Spotify: In the Spotify nodes. Linkup: In the Web query to find tracks (HTTP Request Tool) node. Linkup's free plan is very generous! Your AI provider (e.g., OpenAI): In the OpenAI Chat Model node. Activate the workflow: Toggle the workflow to "Active." Use the form: Open the URL from the On form submission trigger and start creating playlists! Taking it further Change the trigger:* Instead of a form, trigger the playlist creation from a *Telegram* message, a *Discord** bot command, or even a webhook from another application. Create collaborative playlists:** Set up a workflow where multiple people can submit song ideas. You could then have a final AI step consolidate all the requests into a single, cohesive prompt to generate the ultimate group playlist. Optimize for speed:* The *Web query to find tracks** node is set to deep search mode for the highest quality results. You can change this to standard mode for faster and cheaper (but potentially less thorough) playlist creation.

How it works A complete AI-powered study assistant system that lets you chat naturally with your documents stored in Google Drive: The system has two connected workflows: 1. Document Indexing Pipeline (Sub-workflow): • Accepts Google Drive folder URLs • Automatically fetches all files from the folder • Converts documents to plain text • Generates 768-dimensional embeddings using Google Gemini • Stores everything in Supabase vector database for semantic search 2. Study Chat Agent (Main workflow): • Provides a conversational chat interface • Automatically detects and processes Google Drive links shared in chat • Searches your indexed documents using semantic similarity • Maintains conversation history across sessions • Includes calculator for math problems • Responds naturally using Google Gemini 2.5 Pro Use Cases: Students studying for exams, researchers managing papers, professionals building knowledge bases, anyone needing to query large document collections conversationally. Set up steps Prerequisites: • Google Drive OAuth2 credentials • Google Gemini API key (free tier available) • Supabase account with Postgres connection • ~15 minutes setup time Complete Setup: Part 1: Document Indexing Workflow Add Google Drive OAuth2 credentials to the Drive nodes Configure Supabase Postgres credentials in the SQL node Add Supabase API credentials to the Vector Store node Add Google Gemini API key to the Embeddings node Part 2: Study Agent Workflow Import the Study Agent workflow Verify the "Folder all file to vector" tool links to the indexing workflow Add Google Gemini API credentials to both Gemini nodes Configure Supabase API credentials in the Vector Store node Add Postgres credentials for Chat Memory Deploy and access the chat via webhook URL How to Use: Open the chat interface (webhook URL) Paste a Google Drive folder link in the chat Wait for indexing to complete (~1-2 minutes) Start asking questions about your documents The AI will search and answer from your materials Note: The indexing workflow runs automatically when you share Drive links in chat, or you can run it manually to pre-load documents. System Components: Main Agent:** Gemini 2.5 Pro with conversational AI Vector Search:** Supabase with pgvector (768-dim embeddings) Memory:** Postgres chat history (10-message context window) Tools:** Document retrieval, Drive indexing, calculator Embedding Model:** Google Gemini text-embedding-004

This n8n template demonstrates a multi-modal AI recipe assistant that suggests delicious recipes based on user input, delivered via Telegram. The workflow can uniquely handle two types of input: a photo of your ingredients or a simple text list. Use cases are many: Get instant dinner ideas by taking a photo of your fridge contents, reduce food waste by finding recipes for leftover ingredients, or create a fun and interactive service for a cooking community or food delivery app! Good to know This workflow uses two different AI models (one for vision, one for text generation), so costs will be incurred for each execution. See OpenRouter Pricing or your chosen model provider's pricing page for updated info. The AI prompts are in English, but the final recipe output is configured to be in Japanese. You can easily change the language by editing the prompt in the Recipe Generator node. How it works The workflow starts when a user sends a message or an image to your bot on Telegram via the Telegram Trigger. An IF node intelligently checks if the input is text or an image. If an image is sent, the AI Vision Agent analyzes it to identify ingredients. A Structured Output Parser then forces this data into a clean JSON list. If text is sent, a Set node directly prepares the user's text as the ingredient list. Both paths converge, providing a standardized ingredient list to the Recipe Generator agent. This AI acts as a professional chef to create three detailed recipes. Crucially, a second Structured Output Parser takes the AI's creative text and formats it into a reliable JSON structure (with name, difficulty, instructions, etc.). This ensures the output is always predictable and easy to work with. A final Set node uses a JavaScript expression to transform the structured recipe data into a beautiful, emoji-rich, and easy-to-read message. The formatted recipe suggestions are sent back to the user on Telegram. How to use Configure the Telegram Trigger with your own bot's API credentials. Add your AI provider credentials in the OpenAI Vision Model and OpenAI Recipe Model nodes (this template uses OpenRouter, but it can be swapped for a direct OpenAI connection). Requirements A Telegram account and a bot token. An AI provider account that supports vision and text models, such as OpenRouter or OpenAI. Customising this workflow Modify the prompt in the Recipe Generator to include dietary restrictions (e.g., "vegan," "gluten-free") or to change the number of recipes suggested. Swap the Telegram nodes for Discord, Slack, or a Webhook to integrate this recipe bot into a different platform or your own application. Connect to a recipe database API to supplement the AI's suggestions with existing recipes.

✔ Short Description Automate your lead qualification pipeline — capture Typeform Webhook leads, enrich with APIs, score intelligently, and route to HubSpot, Slack, and Sheets in real-time. 🧩 Description Automate your lead management pipeline from form submission to CRM enrichment and routing. This workflow intelligently processes Typeform Webhook submissions, enriches leads using Hunter.io and Abstract API, scores them with dynamic logic, and routes them into HubSpot while keeping your sales team and tracking sheets up to date. It’s a full-stack automation designed to turn raw form submissions into prioritized, qualified CRM-ready leads — without manual intervention. 💡 Who’s it for Marketing teams managing inbound leads from web forms Sales operations teams that qualify and route leads CRM administrators automating lead data entry and scoring Automation professionals building data enrichment systems ⚙️ How it works / What it does Trigger: Receives new Typeform Webhook submissions via Webhook. Data Extraction: Parses name, email, and company info. Email Verification: Validates email deliverability with Hunter.io. Company Enrichment: Fetches company data (industry, size, country) using Abstract API. Lead Scoring Logic: Calculates a lead score and assigns a tier (Hot / Warm / Cold). Conditional Routing: Hot Leads (≥70) → Sent to HubSpot as Qualified. Warm/Cold Leads (<70) → Sent to HubSpot as Nurture stage. Revalidation Loop: Waits (e.g., 3 days) → Rechecks Nurture leads in HubSpot. Logs them to Google Sheets and alerts your Slack channel. 🧰 How to set up Connect accounts: Typeform Webhook (for inbound lead capture) Hunter.io (API key for email verification) Abstract API (for company enrichment) HubSpot (via OAuth2 credentials) Slack (for notifications) Google Sheets (for logging) Customize the Webhook URL inside your Typeform Webhook integration. Replace API keys with your own (Hunter.io, Abstract). Adjust scoring logic inside the Lead Scoring & Routing Logic node to fit your business. Set Wait duration (default: 10 seconds for testing → change to 3 days for production). Activate the workflow and test it with a sample form submission. 🔧 Requirements Typeform account with webhook capability Hunter.io account + API key Abstract API account + API key HubSpot account with OAuth2 credentials Slack workspace & channel Google Sheets integration 🎨 How to customize the workflow Scoring rules:** Modify the “Lead Scoring & Routing Logic” node to adjust how points are calculated (e.g., country, industry, employee size). CRM target:** Replace HubSpot nodes with another CRM (e.g., Pipedrive, Salesforce). Notification channel:** Swap Slack for Email, Discord, or MS Teams. Data source:** Replace Typeform Webhook with another trigger like Webflow Forms, Airtable, or custom API input. Tracking:** Add Google Analytics or Notion API for additional reporting. 🧭 Summary End-to-end lead automation workflow that combines form data, enrichment APIs, CRM updates, and Slack alerts into one intelligent system. Ideal for any team looking to centralize and qualify leads automatically — from submission to sales. 🧑‍💻 Creator Information Developed by: Adem Tasin 🌐 Website: ademtasin 💼 LinkedIn: Adem Tasin

How it works This workflow automates the classification and routing of incoming Intercom conversations. When a new customer message arrives, it is analyzed by AI to determine category, sentiment, urgency, and tags. Based on this classification, the workflow creates tasks in ClickUp for Support or Product requests, or sends real-time alerts to Slack for Sales inquiries. Step-by-step Webhook Intake Triggered when Intercom sends a new conversation payload. Captures customer details, message content, and metadata. AI Classification Sends the conversation JSON to OpenAI (gpt-4o-mini) with a structured prompt. AI returns a JSON object with category (Support, Product, Sales, Other), sentiment, urgency, reasoning, and tags. Processing & Structuring A Code node parses the AI output and merges it with conversation details. Prepares formatted task fields such as title, description, customer info, and priority. Conditional Routing Support requests → Task created in ClickUp with urgency and tags. Product requests → Task created in ClickUp with structured details. Sales inquiries → Slack alert sent to the Sales channel with context and AI reasoning. Other → No task/action triggered. Benefits Automates Intercom ticket triage and routing in real time. Ensures consistent, AI-driven classification of all customer conversations. Reduces manual review time for Support, Product, and Sales teams. Creates structured tasks with enriched metadata for faster resolution. Keeps Sales teams instantly informed with Slack alerts for urgent leads.

Introduction Automates AI-driven assignment grading with HTML and CSV output. Designed for educators evaluating submissions with consistent criteria and exportable results. How It Works Webhook receives papers, extracts text, prepares data, loads answers, AI grades submissions, generates results table, converts to HTML/CSV, returns response. Workflow Template Webhook → Extract Text → Prepare Data → Load Answer Script → AI Grade (OpenAI + Output Parser) → Generate Results Table → Convert to HTML + CSV → Format Response → Respond to Webhook Workflow Steps Input & Preparation: Webhook receives paper, extracts text, prepares data, loads answer script. AI Grading: OpenAI evaluates against answer key, Output Parser formats scores and feedback. Output & Response: Generates results table, converts to HTML/CSV, returns multi-format response. Setup Instructions Trigger & Processing: Configure webhook URL, set text extraction parameters. AI Configuration: Add OpenAI API key, customize grading prompts, define Output Parser JSON schema. Prerequisites OpenAI API key Webhook platform n8n instance Use Cases University exam grading Corporate training assessments Customization Modify rubrics and criteria Add PDF output Integrate LMS (Canvas, Blackboard) Benefits Consistent AI grading Multi-format exports Reduces grading time by 90%

How it works This workflow creates an intelligent document assistant called "Mookie" that can answer questions based on your uploaded documents. Here's how it operates: Document Ingestion:** The system can automatically load PDF files from Google Drive or accept PDFs uploaded directly through Telegram, then processes and stores them in a PostgreSQL vector database using Mistral embeddings Smart Retrieval:** When users ask questions via Telegram or a web chat interface, the AI agent searches through the stored documents to find relevant information using vector similarity matching Contextual Responses:** Using GPT-4 and the retrieved document context, Mookie provides accurate answers based solely on the ingested documents, avoiding hallucination by refusing to answer questions not covered in the stored materials Memory & Conversation:** The system maintains conversation history for each user, allowing for natural follow-up questions and contextual discussions Set up steps Estimated setup time: 30-45 minutes You'll need to configure several external services and credentials: Set up a PostgreSQL database with PGVector extension for document storage Create accounts and API keys for Azure OpenAI (GPT-4), Mistral Cloud (embeddings), and Google Drive access Connect your own LLM's if you don't have these credentials. Configure a Telegram bot and obtain API credentials for chat functionality Update webhook URLs throughout the workflow to match your n8n instance Test the document ingestion pipeline with sample PDFs Verify the chat interfaces (both Telegram and web) are responding correctly >The workflow includes approval mechanisms for PDF ingestion and handles both automated bulk processing from Google Drive and real-time document uploads through Telegram. Read the sticky notes provided in the template code for clear instructions.

📝 Auto-Generate Meeting Notes & Summaries (Zoom → Google Docs + Slack) This workflow automatically captures Zoom meeting data when a meeting ends, generates AI-powered notes, saves them to Google Docs, and instantly posts a summary with a link in Slack. ⚙️ How It Works Zoom Webhook → Triggers on meeting.ended or recording.completed. Normalize Data → Extracts meeting details (topic, host, duration, transcript). AI Notes (GPT-4) → Summarizes transcript into key decisions, action items, and next steps. Google Docs → Saves formatted meeting notes + transcript archive. Slack Post → Shares summary + link to notes in #team-meetings. 🛠️ Setup Steps 1. Zoom App Go to Zoom Developer Console → create App. Enable event meeting.ended. Paste workflow webhook URL. 2. Google Docs Connect Google OAuth in n8n. Docs auto-saved in your Google Drive. 3. Slack Connect Slack OAuth. Replace channel #team-meetings. 4. OpenAI Add your OpenAI API key. Uses GPT-4 for accurate summaries. 📊 Example Output Slack Message: 📝 Auto-Generate Meeting Notes & Summaries (Zoom → Google Docs + Slack) This workflow automatically captures Zoom meeting data when a meeting ends, generates AI-powered notes, saves them to Google Docs, and instantly posts a summary with a link in Slack. ⚙️ How It Works Zoom Webhook → Triggers on meeting.ended or recording.completed. Normalize Data → Extracts meeting details (topic, host, duration, transcript). AI Notes (GPT-4) → Summarizes transcript into key decisions, action items, and next steps. Google Docs → Saves formatted meeting notes + transcript archive. Slack Post → Shares summary + link to notes in #team-meetings. 🛠️ Setup Steps 1. Zoom App Go to Zoom Developer Console → create App. Enable event meeting.ended. Paste workflow webhook URL. 2. Google Docs Connect Google OAuth in n8n. Docs auto-saved in your Google Drive. 3. Slack Connect Slack OAuth. Replace channel #team-meetings. 4. OpenAI Add your OpenAI API key. Uses GPT-4 for accurate summaries. 📊 Example Output Slack Message: 📝 New Meeting Notes Available Topic: Marketing Sync Host: david@company.com Duration: 45 mins 👉 Read full notes here: https://docs.google.com/document/d/xxxx Google Doc: Executive Summary Key Decisions Action Items w/ Owners Next Steps Full Transcript ⚡ With this workflow, your team never scrambles for meeting notes again.

Who is this for? This n8n workflow template is designed for customer support, CX, and ops teams that manage customer messages through HubSpot and use Jira for internal task management. It is especially useful for SaaS companies aiming to automate ticket triage, sentiment detection, and team assignment using AI agents. 🧩 What problem is this workflow solving? Customer service teams often struggle with manual message classification, delayed reactions to churn signals, and inefficiencies in routing support issues to the right internal teams. This workflow uses LLMs and automated profiling to: Detect churn risk or intent in customer messages Summarize issues Classify tickets into categories (e.g. fulfillment, technical, invoicing) Automatically create Jira tickets based on enriched insights 🤖 What this workflow does This AI-powered workflow processes HubSpot support tickets and routes them to Jira based on sentiment and topic. Here’s the full breakdown: Triggers: Either manually or on a schedule (via cron). Fetch HubSpot tickets: Retrieves new messages and their metadata. Run Orchestration Agent: Uses Sentinel Agent to detect emotional tone, churn risk, and purchase intent. Calls Profiler Agent to enrich customer profiles from HubSpot. Summarizes the message using OpenAI. Classifies the ticket using a custom classifier (technical, fulfillment, etc.). Generate a Jira ticket: Title and description are generated using GPT. The assignee and project are predefined. AI agents can be expanded (e.g. add Guide or Facilitator agents). ⚙️ Setup To use this template, you’ll need: HubSpot account** with OAuth2 credentials in n8n Jira Software Cloud account** and project ID OpenAI credentials** for GPT-based nodes Optional: Create sub-workflows for additional AI agents Steps: Clone the workflow in your n8n instance. Replace placeholder credentials for HubSpot, OpenAI, and Jira. Adjust Jira project/issue type IDs to match your setup. Test the workflow using the manual trigger or scheduled trigger node. 🛠️ How to customize this workflow to your needs 1. Edit category logic In the “Category Classifier” node, modify categories and prompt structure to match your internal team structures (e.g., billing, account management, tech support). 2. Refine AI prompts Customize the agent prompt definitions in: Sentinel_agent Profiler_agent Orchestrator to better align with your brand tone or service goals. 3. Update Jira integration You can route tickets to different projects or team leads by adjusting the “Create an issue in Jira” node based on classification output. 4. Add escalation paths Insert Slack, email, or webhook notifications for specific risk levels or customer segments. This workflow empowers your team with real-time message triage, automated decision-making, and AI-enhanced customer insight, turning every inbound ticket into a data-driven action item.

In this tutorial, I’ll show how to create UGC (User Generated Content) videos automatically using n8n and Sora 2. This workflow uses OpenAI to generate detailed prompts and Sora 2 to produce realistic UGC-style videos that look natural and engaging. Who is this for? Marketers and social media managers scaling short-form video content Agencies producing branded or influencer-style content Content creators and freelancers automating their video workflows Anyone exploring AI-driven video generation and automation What problem is this workflow solving? Creating authentic, human-like UGC videos manually takes time and effort. This workflow automates the entire process by: Generating engaging scripts or prompts via OpenAI Sending those prompts to Sora 2 for automatic video generation Managing rendering and delivery inside n8n Eliminating manual editing and production steps What this workflow does This workflow connects n8n, OpenAI, and Sora 2 to fully automate the creation of short-form UGC videos. The steps include: Taking user input (topic, tone, niche). Using OpenAI to create a detailed video prompt. Sending the prompt to Sora 2 via HTTP Request to generate the video. Handling video rendering and storing or sending results automatically. By the end, you’ll have a complete UGC video pipeline running on autopilot — producing content for under $1.50 per video. Setup Create Accounts: Sign up for n8n.io (cloud or self-hosted). Get access to OpenAI API and Sora 2. Generate API Keys: Retrieve API keys from OpenAI and Sora 2. Store them securely in n8n credentials. Create Workflow: Add a Form Trigger or Webhook Trigger for input (topic, target audience). Add an OpenAI Node to generate script prompts. Connect an HTTP Request Node to send the prompt to Sora 2. Use a Wait Node or delay logic for video rendering completion. Store or send the output video file via Gmail, Telegram, or Google Drive. Test the Workflow: Run a test topic. Confirm that Sora 2 generates and returns a video automatically. How to customize this workflow to your needs Adjust OpenAI prompts for specific video styles (tutorials, product demos, testimonials). Integrate video output with social media platforms via n8n nodes. Add text-to-speech layers for voiceover automation. Schedule automatic content creation using Cron triggers. Connect with Notion or Airtable to manage content ideas. Notes You’ll need valid API keys for both OpenAI and Sora 2. Sora 2 may charge per render (approx. $1–$1.50 per video). Ensure your workflow includes sufficient delay/wait handling for video rendering. Works seamlessly on n8n Cloud or self-hosted setups. Want a Video Tutorial on How to Set Up This Automation? 👉 Watch on YouTube

Overview This workflow is an AI-powered Salon Booking Assistant that automates hair, beauty, and spa appointment scheduling through a Webhook trigger. It interacts with the user in natural conversation, collects booking details (service type, stylist preference, date/time, and any special requests), finalizes the draft, and confirms the appointment by storing it in Google Calendar and sending an email confirmation — fully automated end-to-end. How It Works 1. User Interaction The workflow starts when a user submits a request via the Webhook. The AI agent asks step-by-step questions: Type of service (haircut, facial, manicure, etc.) Preferred stylist (optional) Preferred date & time Any additional notes (special treatments, products, etc.) Once details are gathered, it generates a draft appointment summary. 2. Confirmation & Personal Details The user reviews the draft and confirms. The assistant then asks for personal details (name, email, phone number). 3. Booking & Notifications After confirmation, the details are sent to Google Calendar to create an appointment. A confirmation email is sent to the user with all booking information. A final webhook response confirms that the appointment is successfully booked. How to Use Triggered directly via a Webhook URL (can be embedded in your salon website or mobile app). Simply fill in the details, and the assistant will guide the user step by step until the booking is finalized. Once completed, the user receives both an email confirmation and an on-screen success message. Requirements To use this workflow, you’ll need: n8n account** (self-hosted or cloud) Webhook node** (for booking trigger) OpenAI or OpenRouter API Key** (for AI-driven conversation) Google Calendar API access** (to create appointments) Gmail / SMTP credentials** (to send confirmation emails)