Workflow Templates

Summary Engage multiple, uniquely configured AI agents (using different models via OpenRouter) in a single conversation. Trigger specific agents with @mentions or let them all respond. Easily scalable by editing simple JSON settings. Overview This workflow is for users who want to experiment with or utilize multiple AI agents with distinct personalities, instructions, and underlying models within a single chat interface, without complex setup. It solves the problem of managing and interacting with diverse AI assistants simultaneously for tasks like brainstorming, comparative analysis, or role-playing scenarios. It enables dynamic conversations with multiple AI assistants simultaneously within a single chat interface. You can: Define multiple unique AI agents. Configure each agent with its own name, system instructions, and LLM model (via OpenRouter). Interact with specific agents using @AgentName mentions. Have all agents respond (in random order) if no specific agents are mentioned. Maintain conversation history across multiple turns. It's designed for flexibility and scalability, allowing you to easily add or modify agents without complex workflow restructuring. Key Features Multi-Agent Interaction:** Chat with several distinct AI personalities at once. Individual Agent Configuration:** Customize name, system prompt, and LLM for each agent. OpenRouter Integration:** Access a wide variety of LLMs compatible with OpenRouter. Mention-Based Triggering:** Direct messages to specific agents using @AgentName. All-Agent Fallback:** Engages all defined agents randomly if no mentions are used. Scalable Setup:** Agent configuration is centralized in a single Code node (as JSON). Conversation Memory:** Remembers previous interactions within the session. How to Set Up Configure Settings (Code Nodes): Open the Define Global Settings Code node: Edit the JSON to set user details (name, location, notes) and add any system message instructions that all agents should follow. Open the Define Agent Settings Code node: Edit the JSON to define your agents. Add or remove agent objects as needed. For each agent, specify: "name": The unique name for the agent (used for @mentions). "model": The OpenRouter model identifier (e.g., "openai/gpt-4o", "anthropic/claude-3.7-sonnet"). "systemMessage": Specific instructions or persona for this agent. Add OpenRouter Credentials: Locate the AI Agent node. Click the OpenRouter Chat Model node connected below it via the Language Model input. In the 'Credential for OpenRouter API' field, select or create your OpenRouter API credentials. How to Use Start a conversation using the Chat Trigger input. To address specific agents, include @AgentName in your message. Agents will respond sequentially in the order they are mentioned. Example: "@Gemma @Claude, please continue the count: 1" will trigger Gemma first, followed by Claude. If your message contains no @mentions, all agents defined in Define Agent Settings will respond in a randomized order. Example: "What are your thoughts on the future of AI?" will trigger Chad, Claude, and Gemma (based on your default settings) in a random sequence. The workflow will collect responses from all triggered agents and return them as a single, formatted message. How It Works (Technical Details) Settings Nodes: Define Global Settings and Define Agent Settings load your configurations. Mention Extraction: The Extract mentions Code node parses the user's input (chatInput) from the When chat message received trigger. It looks for @AgentName patterns matching the names defined in Define Agent Settings. Agent Selection: If mentions are found, it creates a list of the corresponding agent configurations in the order they were mentioned. If no mentions are found, it creates a list of all defined agent configurations and shuffles them randomly. Looping: The Loop Over Items node iterates through the selected agent list. Dynamic Agent Execution: Inside the loop: An If node (First loop?) checks if it's the first agent responding. If yes (true path -> Set user message as input), it passes the original user message to the Agent. If no (false path -> Set last Assistant message as input), it passes the previous agent's formatted output (lastAssistantMessage) to the next agent, creating a sequential chain. The AI Agent node receives the input message. Its System Message and the Model in the connected OpenRouter Chat Model node are dynamically populated using expressions referencing the current agent's data from the loop ({{ $('Loop Over Items').item.json.* }}). The Simple Memory node provides conversation history to the AI Agent. The agent's response is formatted (e.g., AgentName:\n\nResponse) in the Set lastAssistantMessage node. Response Aggregation: After the loop finishes, the Combine and format responses Code node gathers all the lastAssistantMessage outputs and joins them into a single text block, separated by horizontal rules (---), ready to be sent back to the user. Benefits Scalability & Flexibility:** Instead of complex branching logic, adding, removing, or modifying agents only requires editing simple JSON in the Define Agent Settings node, making setup and maintenance significantly easier, especially for those managing multiple assistants. Model Choice:** Use the best model for each agent's specific task or persona via OpenRouter. Centralized Configuration:** Keeps agent setup tidy and manageable. Limitations Sequential Responses:** Agents respond one after another based on mention order (or randomly), not in parallel. No Direct Agent-to-Agent Interaction (within a turn):* Agents cannot directly call or reply to each other *during the processing of a single user message. Agent B sees Agent A's response only because the workflow passes it as input in the next loop iteration. Delayed Output:* The user receives the combined response only *after all triggered agents have completed their generation.

Daily Economic News Brief for Israel (Hebrew, RTL, GPT-4o) Overview Stay ahead of the curve with this AI-powered workflow that delivers a daily economic summary tailored for professionals tracking the Israeli economy. At 8:00 PM Israel Time, this workflow: Retrieves the latest articles from Calcalist and Mako via RSS Filters duplicates and irrelevant stories Uses OpenAI’s GPT-4o to identify the 5 most important stories of the day Summarizes each article in concise, readable Hebrew Generates a fully styled, responsive HTML email (with proper RTL layout) Sends it to your inbox using your preferred SMTP email provider Perfect for economists, analysts, investors, or policymakers who want an actionable and personalized news digest -- no distractions, no fluff. Setup Instructions Estimated setup time: 10 minutes Required credentials: OpenAI API Key SMTP credentials (for email delivery) Steps: Import this template into your n8n instance. Add your OpenAI API Key under credentials. Configure the SMTP Email node with: Host (e.g. smtp.gmail.com) Port (465 or 587) Username (your email) Password (app-specific password or login) Set your target email address in the last node. (Optional) Customize the GPT prompt to adjust tone or audience (e.g. general public, policy makers). Activate the workflow and receive daily updates straight to your inbox. Customization Tips Change the RSS sources to pull from other Hebrew or international news websites Modify the summarization prompt to fit different sectors (e.g. tech, health, politics) Add integrations like Notion, Airtable, or Telegram for logging or distribution Apply your branding to the HTML output (logos, footer, colors) Why Use This? This is more than a news digest. It’s an intelligent economic assistant that filters noise, highlights what matters, and keeps you informed-automatically. You can set it up in 10 minutes and benefit every single day.

Automatically deploy n8n workflows by simply dropping JSON files into a Google Drive folder—this template watches for new exports, cleans and imports them into your n8n instance, applies a tag, and then archives the processed files. Who is this template for? This workflow template is designed for n8n power users, and automation specialists who need a simple, reliable way to bulk‑deploy or version‑control n8n workflows via Google Drive. It’s perfect if you: Manage multiple n8n instances (staging, production, etc.) Want an easy “drop‑in” approach to publish new or updated workflows Prefer storing/exporting JSON in Drive rather than editing in the UI Use case Manually importing .json exports into n8n is slow and error‑prone. With this template you can: Keep your workflows in a shared Drive folder (version control friendly) Automatically sanitize each file so only supported settings go through Tag deployed workflows consistently for easy filtering Move processed files to a “Deployed” folder for clear change tracking How it works Watch “ToDeploy” folder in Google Drive for new .json files Download & parse each file into a JSON object Clean payload: strip out everything except the allowed executionOrder (and timezone if you choose) POST the cleaned workflow to your n8n instance via /api/v1/workflows PUT a predefined tag onto the newly created workflow Move file to your “Deployed” folder when import succeeds, or capture the workflow name & error if it fails Setup instructions 1. In Google Drive create a ToDeploy folder and a Deployed folder Update "Google Drive Trigger -ToDeploy folder" to your ToDeploy folder Update "Move JSON file to Deployed folder" to you Deployed folder 2. Create a n8n API key: +Go to Settings > n8n API +Select Create an API key +Copy API Key 3. In "Get Existing Workflow Tags" node: Create n8n API Authentication Authentication: Predefined Credential Type Credential Type: n8n API Create new credential: +Paste in API key +Baseurl: https://SUBDOMAIN.YOURDOMAINNAME.com/api/v1/ 4. Add n8n API authentication to: "Create n8n Workflow" node "Set Workflow Tag" node 5. Add your N8N instance URL to the N8N_Instance_URL variable in "Set n8n URL variable" node. 6. Run "1. Get Workflow Tags" flow and copy the ID of your chosen tag. 7. In "Set n8n API URL & Tag ID variables" node: Add the Workflow Tag ID to the N8N_Instance_Tag variable Add your N8N instance URL to the N8N_Instance_URL variable 8. Set workflow to Active How to adjust it to your needs Use different tags: run Get Existing Workflow Tags on start‑up to refresh available tags, or hard‑code multiple tags in the Set Workflow Tag node. Add notifications**: connect the error branch to Slack or Email nodes so you get alerted if an import fails. Swap Drive for another storage**: replace Google Drive nodes with Dropbox, S3, or GitHub triggers if you prefer a different source for your JSON files.

Detailed Description The ToDo App workflow is designed to streamline task management through Telegram and Google Tasks integration. This workflow allows users to create, update, and manage tasks via Telegram messages, leveraging AI capabilities to enhance user interaction. The expected outcome is a seamless experience where users can manage their tasks efficiently without needing to switch between applications. Who is this for? This workflow is intended for: Individuals** looking for an efficient way to manage their tasks directly from Telegram. Teams** that require a collaborative task management solution integrated with Google Tasks. Developers** interested in automating task management processes using n8n and Telegram. What problem does this workflow solve? Managing tasks can often be cumbersome, especially when switching between different applications. This workflow addresses the following problems: Fragmented Task Management**: Users can manage tasks directly from Telegram, reducing the need to switch to Google Tasks. Inefficient Communication**: By integrating AI, users can interact with the task management system in a conversational manner, making it more intuitive. Task Updates**: Users can easily update task statuses and details through simple messages, enhancing productivity. What this workflow does The ToDo App workflow performs the following functions: Incoming Message Handling: Listens for messages sent to a Telegram bot. Task Creation: Allows users to create new tasks based on their messages. Task Updates: Users can update existing tasks by sending specific commands. Task Retrieval: Retrieves today's and upcoming tasks from Google Tasks. Voice Note Transcription: Supports voice messages, converting them into text for task management. AI Assistance: Utilizes an AI agent to assist users in managing their tasks effectively. Setup Prerequisites Before setting up the workflow, ensure you have the following: n8n Account**: Sign up for an n8n account if you don't have one. Telegram Bot**: Create a Telegram bot and obtain the API token. Google Tasks API**: Set up Google Tasks API and obtain OAuth2 credentials. OpenAI API Key**: Sign up for OpenAI and obtain an API key for AI functionalities. Setup Process Upload the JSON for this workflow and setup the authentication for the different tools. How to customize this workflow To adapt the ToDo App workflow to different needs, consider the following customizations: Change Task Management Platform**: If you prefer a different task management tool, replace the Google Tasks nodes with your preferred service's API. Modify AI Responses**: Adjust the AI agent's system message to change how it interacts with users. Add Additional Commands**: Expand the workflow by adding more commands for different task management functionalities (e.g., deleting tasks). Integrate Other Messaging Platforms**: If you want to use a different messaging service, replace the Telegram nodes with the appropriate nodes for that service. Conclusion The ToDo App workflow provides a powerful solution for managing tasks through Telegram, enhancing productivity and user experience. By following the setup instructions and customization options, users can tailor the workflow to meet their specific needs, making task management more efficient and accessible.

This workflow sends a message to a Discord channel when a new row is added or a row is updated in a Google Sheet. The message will send all data rows in the Google Sheet. Prerequisites Discord account and Discord credentials. Google account and Google credentials. How it works Using a code node, we can use the obtained Google Sheet data to create a custom message that will be sent to Discord. The message will be sent to the Discord channel specified in the Discord node. Setup This workflow requires that you set up a Discord webhook and have an existing Google Sheet with data. See how to set up a Discord webhook here.

Tags: EU Legislation, Sustainability, Automation, Web Scraping, OpenAI, Google Sheets, Policy Monitoring, Climate Context Hey! I’m Samir, a Supply Chain Engineer and Data Scientist from Paris, and the founder of LogiGreen Consulting. We use AI, automation, and data to support sustainable business practices for small, medium and large companies. This workflow is part of our broader initiative to monitor and act on sustainability legislation in Europe. > How do you know if new EU laws will impact your business's sustainability goals? This n8n workflow automatically scrapes the EU Parliament’s legislative portal to find and flag procedures related to environmental sustainability. 📬 For business inquiries, feel free to connect with me on LinkedIn Who is this template for? This workflow is useful for: Sustainability consultants** monitoring legal frameworks NGOs and researchers** tracking environmental regulations Companies* aligning with *CSRD* or *EU Green Deal** objectives Policy analysts** looking for automation tools What does it do? This n8n workflow: 🌐 Scrapes the EU Parliament legislative portal for yesterday’s entries 🧠 Uses OpenAI to classify if each procedure is related to sustainability 🗂️ Filters out irrelevant items 📊 Saves the results in a Google Sheet ✅ Creates a Google Task for each relevant file to review the legislation How it works Trigger manually or on schedule Scrape HTML blocks for scheduled debates Parse each procedure to extract Title, Committee, Rapporteur, PDF link Call GPT-4-turbo to check if the topic matches sustainability criteria Filter responses based on “yes” or “no” Store valid items into Google Sheets Generate tasks in Google Tasks The AI only flags procedures that directly impact the environment, circular economy, or pollution control. What do I need to get started? You’ll need: A Google Sheet connected to your n8n instance An OpenAI account with GPT-4 access A Google Task List Follow the Guide! Follow the sticky notes in the workflow or check my tutorial to configure each node and start using AI to monitor sustainability regulations in Europe. 🎥 Watch My Tutorial Notes AI filters are strict — you can customise the system prompt to match your needs This is ideal for tracking legislative risk for climate regulations This workflow was built using n8n version 1.85.4 Submitted: April 21, 2025

Disclaimer This template is only available on n8n self-hosted as it's making use of the community node for MCP Client. Who this is for? The Scrape Web Data with Bright Data and MCP Automated AI Agent workflow is built for professionals who need to automate large-scale, intelligent data extraction by utilizing the Bright Data MCP Server and Google Gemini. This solution is ideal for: Data Analysts - Who require structured, enriched datasets for analysis and reporting. Marketing Researchers - Seeking fresh market intelligence from dynamic web sources. Product Managers - Who want competitive product and feature insights from various websites. AI Developers - Aiming to feed web data into downstream machine learning models. Growth Hackers - Looking for high-quality data to fuel campaigns, research, or strategic targeting. What problem is this workflow solving? Manually scraping websites, cleaning raw HTML data, and generating useful insights from it can be slow, error-prone, and non-scalable. This workflow solves these problems by: Automating complex web data extraction through Bright Data’s MCP Server. Reducing the human effort needed for cleaning, parsing, and analyzing unstructured web content. Allowing seamless integration into further automation processes. What this workflow does? This n8n workflow performs the following steps: Trigger: Start manually. Input URL(s): Specify the URL to perform the web scrapping. Web Scraping (Bright Data): Use Bright Data’s MCP Server tools to accomplish the web data scrapping with markdown and html format. Store / Output: Save results into disk and also performs a Webhook notification. Setup Please make sure to setup n8n locally with MCP Servers by navigating to n8n-nodes-mcp Please make sure to install the Bright Data MCP Server @brightdata/mcp on your local machine. Sign up at Bright Data. Create a Web Unlocker proxy zone called mcp_unlocker on Bright Data control panel. Navigate to Proxies & Scraping and create a new Web Unlocker zone by selecting Web Unlocker API under Scraping Solutions. In n8n, configure the Google Gemini(PaLM) Api account with the Google Gemini API key (or access through Vertex AI or proxy). In n8n, configure the credentials to connect with MCP Client (STDIO) account with the Bright Data MCP Server as shown below. Make sure to copy the Bright Data API_TOKEN within the Environments textbox above as API_TOKEN=<your-token>. Update the LinkedIn URL person and company workflow. Update the Webhook HTTP Request node with the Webhook endpoint of your choice. Update the file name and path to persist on disk. How to customize this workflow to your needs Different Inputs: Instead of static URLs, accept URLs dynamically via webhook or form submissions. Outputs: Update the Webhook endpoints to send the response to Slack channels, Airtable, Notion, CRM systems, etc.

Amazon Product Price Tracker This workflow automatically monitors Amazon product prices, tracks price changes, and sends alerts when significant price fluctuations occur. Built with ScrapeOps' structured data API, it provides a reliable, maintenance-free solution for price tracking without worrying about anti-bot measures or complex selectors. What This Workflow Does Monitors multiple Amazon products simultaneously using their ASINs Calculates both absolute and percentage price changes Sends customizable email alerts when prices cross defined thresholds Maintains a historical record of all price data for trend analysis Updates a Google Sheets with the latest price information Prerequisites A ScrapeOps API key (register at https://scrapeops.io) Google account for Google Sheets integration SMTP email configuration for alerts Setup Instructions Spreadsheet Setup Make a copy of the template spreadsheet: https://docs.google.com/spreadsheets/d/1hRv-TBXrpN6rkIU65WorttNHt-IPWas_An0sF4Of39U Add your Amazon product ASINs in the "Products to Monitor" sheet Set your desired alert thresholds for price increases/decreases Workflow Configuration Add your ScrapeOps API key to the "Setup" node Update the spreadsheet URL in the "Setup" node with YOUR copy Configure your email settings for notifications Adjust the schedule frequency as needed (default: hourly) How It Works The workflow reads product ASINs from your Google Sheet, fetches current pricing data via ScrapeOps' Amazon Product API, calculates price changes, updates your spreadsheet, and sends alerts when price movements exceed your defined thresholds. Unlike traditional web scrapers that break when websites change, this solution uses ScrapeOps' reliable API that handles all the complexity of Amazon data extraction, ensuring consistent results without maintenance. Additional Notes This workflow is ideal for deal hunters, price comparison services, and e-commerce analytics The alerting system can be extended to additional channels like Slack or Telegram ScrapeOps handles all anti-bot measures, proxy management, and parsing complexities

This workflow creates a documentation system for n8n instances using Docsify.js. It serves a dynamic documentation website that allows users to: View an overview of all workflows in a tabular format Filter workflows by tags Access automatically generated documentation for each workflow Edit documentation with a live Markdown preview Visualize workflow structures using Mermaid.js diagrams > 📺 Check out the short 2-min demonstration on LinkedIn. Don't forget to connect! 🔧 Key Components Main Documentation Portal Serves a Docsify-powered website Provides a navigation sidebar with workflow tags Displays workflow status, creation date, and documentation links Documentation Generator Uses GPT model to auto-generate workflow descriptions Creates Mermaid.js diagrams of workflow structures Maintains consistent documentation format Live Editor Split-screen Markdown editor with preview Real-time Mermaid diagram rendering Save/Cancel functionality ⚙️ Technical Details Environment Setup Requires write access to the specified project directory Uses environment variables for n8n instance URL configuration Implements webhook endpoints for serving documentation ⚠️ Security Considerations > Note: The current implementation doesn't include authentication for editing. Consider adding authentication for production use. Dependencies Docsify.js for documentation rendering Mermaid.js for workflow visualization OpenAI GPT for documentation generation 🔍 Part of the n8n Observability Series This workflow is part of a broader series focused on n8n instance observability. Check out these related workflows: Workflow Dashboard - Get comprehensive analytics of your n8n instance Visualize Your n8n Workflows with Mermaid.js - Create beautiful workflow visualizations Each workflow in this series helps you better understand and manage your n8n automation ecosystem!

Who this is for? The Structured Data Extract & Data Mining workflow is crafted for researchers, content analysts, SEO strategists, and AI developers who need to transform semi-structured web data (like markdown content or scraped HTML) into actionable structured datasets. It is ideal for: Content Analysts** - Organizing and mining large volumes of markdown or HTML content. SEO & Trend Researchers** - Exploring topics by location and category. AI Engineers & NLP Developers** - Looking to automate insight extraction from unstructured inputs. Growth Marketers** - Tracking topic-level trends for strategic campaigns. Automation Specialists** - Streamlining workflows from scrape to storage. What problem is this workflow solving? Extracting insights from markdown or HTML documents typically requires manual review, formatting, and parsing. This becomes unscalable when dealing with large datasets or when real-time response is needed. Additionally, trend and topic extraction usually involves external tools, custom scripts, and inconsistent formatting. This workflow solves: Automatic text extraction from markdown or structured content. Location and category-based trend mining with semantic grouping. AI-driven topic extraction and summarization Real-time notification via webhook with rich structured payloads. Persistent storage of mined data to disk for audits or further processing. What this workflow does Receives input: Sets the URL for the data extraction and analysis. Uses Bright Data's Web Unlocker to extract content from relevant sites. A Markdown/Text Extractor node parses the content into clean plaintext The cleaned data is passed to Google Gemini to: Identify trends by location and category Extract key topics and themes Format the response into structured JSON The structured insights are sent via Webhook Notification to external systems (e.g., Slack, Web apps, Zapier) The final output is saved to disk Setup Sign up at Bright Data. Navigate to Proxies & Scraping and create a new Web Unlocker zone by selecting Web Unlocker API under Scraping Solutions. In n8n, configure the Header Auth account under Credentials (Generic Auth Type: Header Authentication). The Value field should be set with the Bearer XXXXXXXXXXXXXX. The XXXXXXXXXXXXXX should be replaced by the Web Unlocker Token. A Google Gemini API key (or access through Vertex AI or proxy). Update the Set URL and Bright Data Zone for setting the brand content URL and the Bright Data Zone name. Update the Webhook HTTP Request node with the Webhook endpoint of your choice. How to customize this workflow to your needs Update Source** : Update the workflow input to read from Google Sheet or Airbase for dynamically tracking multiple brands or topics. Gemini Prompt Customization** : Extract trends within a custom category (e.g., E-commerce design patterns in the US) Output topics with popularity metrics Structure the output as per your database schema (e.g., [{ topic, trend_score, location }]) Webhook Output** : Send notifications to - Slack – with AI summaries in rich blocks Internal APIs – for use in dashboards Zapier/Make – for multi-step automation Persistence** Save output to: Remote FTP or SFTP storage Amazon S3, Google Cloud Storage etc.

This Template gives the ability to monitor all uplinks for your Meraki Dashboard and then alert your team in a method you prefer. This example is a Teams notification to our Dispatch Channel Setup will probably take around 30 minutes to 1h provided with the Template. Most time intensive steps are getting a Meraki API key which I go over and setting up the Teams node which n8n has good documentation for. Tutorial & explanation https://www.youtube.com/watch?v=JvaN0dNwRNU

👉 Build a Phone Agent to qualify outbound leads and schedule inbound calls Who is this for? This workflow is designed for sales teams, call centers, and businesses handling both outbound and inbound lead calls who want to automate their qualification, follow-up, and call documentation process without manual intervention. It’s ideal for teams using Google Sheets, RetellAI, OpenAI, and Gmail as part of their tech stack. Real-World Use Cases 🛍 E-commerce – Instantly handle product FAQs and order status checks, 24/7. 🏬 Retail Stores – Share store hours, directions, and return policies without lifting a finger. 🍽 Restaurants – Take reservations or answer menu questions automatically. 💼 Service Providers – Book appointments or consultations while you focus on your craft. 📞 Any Local Business – Deliver friendly, consistent phone support — no live agent required. What problem is this workflow solving? Managing lead calls at scale can be chaotic—between scheduling outbound qualification calls, handling inbound appointment requests, and making sure every call is documented and followed up. This workflow automates the entire process, reducing human error and saving time by: ✅ Sending reminders to reps for outbound calls ✅ Automatically placing calls with RetellAI ✅ Handling inbound calls and checking caller details ✅ Generating and emailing call summaries automatically What this workflow does This n8n template connects Google Sheets, RetellAI, OpenAI, and Gmail into a seamless workflow: Outbound Lead Qualification Workflow Triggers when a new lead is added to Google Sheets Sends an SMS notification to remind the rep to call in 5 minutes (Optional) Waits 5 minutes Initiates an automated call to the lead via RetellAI Inbound Call Appointment Scheduler Receives inbound calls from RetellAI (via webhook) Checks if the caller’s number exists in Google Sheets Responds to RetellAI with a success or error message Post-Call Workflow Receives post-call data from RetellAI Filters only analyzed calls Updates the lead’s record in Google Sheets Uses OpenAI to generate a call summary Emails the summary to a team inbox or rep Setup ✅ You need an active RetellAI API key Sign up for RetellAI, create an agent, and set the webhook URLs (n8n_call for call events). Purchase a Twilio phone number and link it to the agent. ✅ Your Google Sheet must have a column for phone numbers (e.g., "Phone") ✅ Gmail account connected and authorized in n8n ✅ OpenAI API key added to your environment variables or credentials Configure your Google Sheets node with the correct spreadsheet ID and range Add your RetellAI API key to the HTTP request nodes Connect your Gmail account in the Gmail node Add your OpenAI key in the OpenAI node 👉 See full setup guide here: Notion Documentation How to customize this workflow to your needs Change SMS content**: Edit the text in the “Send SMS reminder” node to match your team’s tone Modify call wait time**: Enable and adjust the “Wait 5 minutes” node to any delay you prefer Add CRM integration**: Replace or extend the Google Sheets node to update your CRM instead of a spreadsheet Customize call summary prompts**: Edit the prompt sent to OpenAI to change the summary style or add extra insights Send email to different recipients**: Change the recipient address in the Gmail node or make it dynamic from the lead record Need help customizing? Contact me for consulting and support : Linkedin