Workflow Templates

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. This workflow automates the process of scraping product data from e-commerce websites and using it to fine-tune a custom OpenAI GPT model for generating high-quality marketing copy and product descriptions. Main Use Cases Fine-tune OpenAI models with real product data from hundreds of supported e-commerce websites for marketing content generation. Create custom AI models specialized in writing compelling product descriptions across different industries and platforms. Automate the entire pipeline from data collection to model training using Bright Data's extensive scraper library. Generate marketing copy using your custom-trained model via an interactive chat interface. How it works The workflow operates in two main phases: model training and model usage, organized into these stages: Data Collection & Processing Manually triggered to start the fine-tuning process. Uses Bright Data's web scraper to extract product information from any supported e-commerce platform (Amazon, eBay, Shopify stores, Walmart, Target, and hundreds of other websites). Collects product titles, brands, features, descriptions, ratings, and availability status from your chosen platform. Easily customizable to scrape from different websites by simply changing the dataset configuration and product URLs. Training Data Preparation A Code node processes the scraped product data to create training examples in OpenAI's required JSONL format. For each product, generates a complete training example with: System message defining the AI's role as a marketing assistant. User prompt containing specific product details (title, brand, features, original description snippet). Assistant response providing an ideal marketing description template. Compiles all training examples into a single JSONL file ready for OpenAI fine-tuning. Model Fine-Tuning Uploads the training file to OpenAI using the OpenAI File Upload node. Initiates a fine-tuning job via HTTP Request to OpenAI's fine-tuning API using the GPT-4o-mini model as the base. The fine-tuning process runs on OpenAI's servers to create your custom model. Interactive Chat Interface Provides a chat trigger that allows real-time interaction with your fine-tuned model. An AI Agent node connects to your custom-trained OpenAI model. Users can chat with the model to generate product descriptions, marketing copy, or other content based on the training. Custom Model Integration The OpenAI Chat Model node is configured to use your specific fine-tuned model ID. Delivers responses trained on your product data for consistent, high-quality marketing content. Summary Flow: Manual Trigger → Scrape E-commerce Products (Bright Data) → Process & Format Training Data (Code) → Upload Training File (OpenAI) → Start Fine-Tuning Job (HTTP Request) | Parallel: Chat Trigger → AI Agent → Custom Fine-Tuned Model Response Benefits: Fully automated pipeline from raw product data to trained AI model. Works with hundreds of different e-commerce websites through Bright Data's extensive scraper library. Creates specialized models trained on real e-commerce data for authentic marketing copy across various industries. Scalable solution that can be adapted to different product categories, niches, or websites. Interactive chat interface for immediate access to your custom-trained model. Cost-effective fine-tuning using OpenAI's most efficient model (GPT-4o-mini). Easily customizable with different websites, product URLs, training prompts, and model configurations. Setup Requirements: Bright Data API credentials for web scraping (supports hundreds of e-commerce websites). OpenAI API key with fine-tuning access. Replace placeholder credential IDs and model IDs with your actual values. Customize the product URLs list and Bright Data dataset for your specific website and use case. The workflow can be adapted for any e-commerce platform supported by Bright Data's scraping infrastructure.

🤖🥗 Telegram Nutrition AI Assistant (Alternative to Cal AI App) > AI-powered nutrition assistant for Telegram — log meals, set goals, and get personalized daily reports with Google Sheets integration. 📋 Description This n8n template creates a Telegram-based Nutrition AI Assistant 🥑🔥 designed as an open-source alternative to the Cal AI mobile app. It allows users to interact with an AI agent via text, voice, or images to track meals, calculate macros, and monitor nutrition goals directly from Telegram. The system integrates Google Sheets as the database, handling both user profiles and meal logs, while leveraging Gemini AI for natural conversation, food recognition, and daily progress reports. ✨ Key Features 💬 Multi-input support: Text, voice messages (transcribed), and food images (AI analysis). 📊 Macro calculation: Automatic estimation of calories, proteins, carbs, and fats. 📝 User-friendly registration: Simple onboarding without storing personal health data (no weight/height required). 🎯 Goal tracking: Users can set and update calorie and protein targets. 📈 Daily reports: Personalized progress messages with visual progress bars. 🗂 Google Sheets integration: Profile table for user targets. Meals table for food logs. 🔄 Advanced n8n nodes: Includes use of Merge, Subworkflow, and Code nodes for data processing and report generation. 💡 Acknowledgment Inspired by the Cal AI concept 💡 — this template demonstrates how to reproduce its main functionality with n8n, Telegram, and AI agents as a flexible, open-source automation workflow. 🏷 Tags telegram ai-assistant nutrition meal-tracking google-sheets food-logging voice-transcription image-analysis daily-reports n8n-template merge-node subworkflow-node code-node telegram-trigger google-gemini 💼 Use Case Use this template if you want to: 🥗 Log meals using text, images, or voice messages. 📊 Track nutrition goals (calories, proteins) with daily progress updates. 🤖 Provide a chat-based nutrition assistant without building a full app. 🗂 Store structured nutrition data in Google Sheets for easy access and analysis. 💬 Example User Interactions 📸 User sends a photo of a meal → AI analyzes the food and logs calories/macros. 🎤 User sends a voice message → AI transcribes and logs the meal. ⌨️ User types “report” → AI returns a daily nutrition summary with progress bars. 🥅 User says “update my protein goal” → AI updates profile in Google Sheets. 🔑 Required Credentials Telegram Bot API (Bot Token) Google Sheets API credentials AI Provider API (Google Gemini or compatible LLM) ⚙️ Setup Instructions 🗂 Create two Google Sheets tables: Profile: User_ID, Name, Calories_target, Protein_target Meals: User_ID, Date, Meal_description, Calories, Proteins, Carbs, Fats 🔌 Configure the Telegram Trigger with your bot token. 🤖 Connect your AI provider credentials (Gemini recommended). 📑 Connect Google Sheets with your credentials. ▶️ Deploy the workflow in n8n. 🎯 Start interacting with your nutrition assistant via Telegram. 📌 Extra Notes 🟩 Green section: Handles Telegram trigger and user check. 🟥 Red section: Registers new users and sets goals. 🟦 Blue section: Processes text, voice, and images. 🟨 Yellow section: Generates nutrition reports. 🟪 Purple section: Main AI agent controlling tools and logic. 💡 Need Assistance? If you’d like help customizing or extending this workflow, feel free to reach out: 📧 Email: johnsilva11031@gmail.com 🔗 LinkedIn: John Alejandro Silva Rodríguez

This n8n template demonstrates how to use AI as a comprehensive personal assistant with multiple specialized agents. Use cases include email management, scheduling, web search, calculations, and more - all automated through AI coordination. Good to know This template integrates multiple AI services through OpenRouter Each agent specializes in different tasks (Gmail, Calendar, Search, etc.) Memory persistence maintains context across interactions How it works The workflow is triggered by Telegram messages (can be replaced with other triggers) A router node directs requests to the appropriate specialized agent Agents include: Gmail for email management Calculator for math operations Google Search for information retrieval Calendar for scheduling Contacts for CRM functions The OpenRouter Chat Model coordinates responses Final responses are sent back through Telegram How to use Connect your Telegram bot credentials Configure each service with appropriate API keys The system will automatically route requests to the right agent Requirements OpenRouter account for AI services Telegram bot token Google API credentials for relevant services Customising this workflow Add more specialized agents as needed Replace Telegram with other communication channels Adjust routing logic for different use cases

Description This n8n workflow enables users to send an image to a Telegram bot and receive the extracted text using Tesseract OCR (via the n8n-nodes-tesseractjs Community Node). It's a quick and straightforward way to convert images into readable text directly through chat. How it Works The workflow listens for new image messages coming in via the Telegram bot. Once an image is received, it downloads the image file from Telegram (which initially arrives as application/octet-stream). The image data, now properly identified, is then sent to the Tesseract OCR node to extract the text. Finally, the recognized text is sent back as a reply to the Telegram user. Setup Steps Install Community Node: Ensure you have installed n8n-nodes-tesseractjs in your n8n instance. Connect Telegram Bot: Configure the Telegram Trigger node with your Telegram bot. Bot Token: Add your Telegram bot token to the Send Message node to send replies. Deploy & Test: Activate (deploy) the workflow and send an image to your Telegram bot to test.

This workflow automates web scraping of Amazon search result pages by retrieving raw HTML, cleaning it to retain only the relevant product elements, and then using an LLM to extract structured product data (name, description, rating, reviews, and price), before saving the results back to Google Sheets. It integrates Google Sheets to supply and collect URLs, BrightData to fetch page HTML, a custom n8n Function node to sanitize the HTML, LangChain (OpenRouter GPT-4) to parse product details, and Google Sheets again to store the output. URL to scape . Result Who Needs Amazon Search Result Scraping? This scraping workflow is ideal for teams and businesses that need to monitor Amazon product listings at scale: E-commerce Analysts** – Track competitor pricing, ratings, and inventory trends. Market Researchers** – Collect data on product popularity and reviews for market analysis. Data Teams** – Automate ingestion of product metadata into BI pipelines or data lakes. Affiliate Marketers** – Keep affiliate catalogs up to date with latest product details and prices. If you need reliable, structured data from Amazon search results delivered directly into your spreadsheets, this workflow saves you hours of manual copy-and-paste. Why Use This Workflow? End-to-End Automation** – From URL list to clean JSON output in Sheets. Robust HTML Cleaning** – Strips scripts, styles, unwanted tags, and noise. Accurate Structured Parsing** – Leverages GPT-4 via LangChain for reliable extraction. Scalable & Repeatable** – Processes thousands of URLs in batches. Step-by-Step: How This Workflow Scrapes Amazon Get URLs from Google Sheets – Reads a list of search result URLs. Loop Over Items – Iterates through each URL in controlled batches. Fetch Raw HTML – Uses BrightData’s Web Unlocker proxy to retrieve the page. Clean HTML – A Function node removes doctype, scripts, styles, head, comments, classes, and non-whitelisted tags, collapsing extra whitespace. Extract with LLM – Passes cleaned HTML into LangChain → GPT-4 to output JSON for each product: name, description, rating, reviews, price Save Results – Appends the JSON fields as columns back into a “results” sheet in Google Sheets. Customization: Tailor to Your Needs Adaptable Sites** – This workflow can be adapted to any e-commerce or other website, for example Walmart or eBay. Whitelist Tags** – Modify the allowedTags array in the Code node to keep additional HTML elements. Schema Changes** – Update the Structured Output Parser schema to include more fields (e.g., availability, SKU). Alternate Data Sink** – Instead of Sheets, route output to a database, CSV file, or webhook. 🔑 Prerequisites Google Sheets Credentials** – OAuth credentials configured in n8n. BrightData API token** – Stored in n8n credentials as BRIGHTDATA_TOKEN. OpenRouter API Key** – Configured for the LangChain node to call GPT-4. n8n Instance** – Self-hosted or cloud with sufficient quota for HTTP requests and LLM calls. 🚀 Installation & Setup Configure Credentials** In n8n, set up Google Sheets OAuth under “Credentials.” Add BrightData token as a new HTTP Request credential. Create an OpenRouter API key credential for the LangChain node. Import the Workflow** Copy the JSON workflow into n8n’s “Import” dialog. Map your Google Sheet IDs and GIDs to the {{WEB_SHEET_ID}}, {{TRACK_SHEET_GID}}, and {{RESULTS_SHEET_GID}} placeholders. Ensure the BRIGHTDATA_TOKEN credential is selected on the HTTP Request node. Test & Run** Add a few Amazon search URLs to your “track” sheet. Execute the workflow and verify product data appears in your “results” sheet. Tweak batch size or parser schema as needed. ⚠ Important API Rate Limits** – Monitor your BrightData and OpenRouter usage to avoid throttling. Amazon’s Terms** – Ensure your scraping complies with Amazon’s policies and legal requirements. Summary This workflow delivers a fully automated, scalable solution to extract structured product data from Amazon search pages directly into Google Sheets—streamlining your competitive analysis and data collection. 🚀 Phil | Inforeole

This workflow auto-fetches top financial headlines, cleans the content, and uses AI to summarize it into a short investor-friendly email. Good to know The workflow runs daily and relies on stable webpage access; check the URL (e.g., https://www.ft.com/) for availability. AI costs may apply depending on the LLM model used (e.g., GPT-4 or Gemini); refer to provider pricing. How it works Trigger the workflow daily with the Schedule Daily Trigger node. Fetch financial news from a webpage using the Fetch Webpage News node. Add a Delay to Ensure Page Load node to ensure content is fully loaded. Extract and clean headlines with the Extract News Headlines & Clean Extracted Data node. Process the data with the LLM Chat Model node to generate a summary. Send the summarized report via email using the Email Daily Financial Summary node. How to use Import the workflow into n8n and configure the nodes with your webpage URL and email credentials. Test the workflow to verify content fetching and email delivery. Requirements Webpage access (e.g., financial news site API or RSS) Email service (e.g., SMTP or API) LLM model credentials (e.g., GPT-4 or Gemini) Customising this workflow Adjust the Fetch Webpage News node to target different news sources or modify the LLM Chat Model prompt for a different summary style.

Purpose The purpose of this automation is to help context switch from office to some side projects or passion gigs so you can be free of distracting thoughts and re-set your perspective. Benefits Anyone who works full time and also does something on the side (perhaps a side gig/being a mom/just follow your passion project) What you need N8N (lol) Any LLM API Key (I used OpenAI 4.1) IPhone (automations and shortcuts) Template Setup Setup LLM API key. Import template file to new workflow. On Iphone create a new shortcut as per video. Create automation steps. Resources Youtube

Google Sheets Company Enrichment with Explorium MCP Template Download the following json file and import it to a new n8n workflow: google\_sheets\_enrichment.json Overview This n8n workflow template enables automatic enrichment of company information in your Google Sheets. When you add a new company or update existing company details (name or website), the workflow automatically fetches additional business intelligence data using Explorium MCP and updates your sheet with: Business ID NAICS industry code Number of employees (range) Annual revenue (range) Key Features Automatic Triggering**: Monitors your Google Sheet for new rows or updates to company name/website fields Smart Processing**: Only processes new or modified rows, not the entire sheet Data Validation**: Ensures both company name and website are present before processing Error Handling**: Processes each row individually to prevent one failure from affecting others Powered by AI**: Uses Claude Sonnet 4 with Explorium MCP for intelligent data enrichment Prerequisites Before setting up this workflow, ensure you have: n8n instance (self-hosted or cloud) Google account with access to Google Sheets Anthropic API key for Claude Explorium MCP API key Installation & Setup Step 1: Import the Workflow Create a new workflow. Download the workflow JSON from above. In your n8n instance, go to Workflows → Add Workflow → Import from File Select the JSON file and click Import Step 2: Create Google Sheet Create a new google sheet (or make a copy of this template) Your Google Sheet must have the following columns (exact names): name - Company name website - Company website URL business_id - Will be populated by the workflow naics - Will be populated by the workflow number_of_employees_range - Will be populated by the workflow yearly_revenue_range - Will be populated by the workflow Step 3: Configure Google Sheets Credentials You'll need to set up two Google credentials: Google Sheets Trigger Credentials: Click on the Google Sheets Trigger node Under Credentials, click Create New If working on n8n Cloud, Click the 'Sign in with Google' button Grant permissions to read and monitor your Google Sheets If working on n8n Instance, Follow the OAuth2 authentication process here Fill the Client ID and Client Secret fields Google Sheets Update Credentials: Click on the Update Company Row node Under Credentials, select the same credentials or create new ones (The same you did above) Ensure permissions include write access to your sheets Step 4: Configure Anthropic Credentials Click on the Anthropic Chat Model node Under Credentials, click Create New Enter your Anthropic API key Save the credentials Step 5: Configure Explorium MCP Credentials Click on the MCP Client node Under Credentials, click Create New (Header Auth) Fill the Name field with api_key Fill the Value field with your Explorium API Key Save the credentials Step 6: Link Your Google Sheet In the Google Sheets Trigger node: Select your Google Sheet from the dropdown Select the worksheet (usually "Sheet1") In the Update Company Row node: Select the same Google Sheet and worksheet Ensure the matching column is set to row_number Step 7: Activate the Workflow Click the Active toggle in the top right to activate the workflow The workflow will now monitor your sheet every minute for changes How It Works Workflow Process Flow Google Sheets Trigger: Polls your sheet every minute for new rows or changes to name/website fields Filter Valid Rows: Validates that both company name and website are present Loop Over Items: Processes each company individually AI Agent: Uses Explorium MCP to: Find the company's business ID Retrieve firmographic data (revenue, employees, NAICS code) Format Output: Structures the data for Google Sheets Update Company Row: Writes the enriched data back to the original row Trigger Behavior First Activation**: May process all existing rows to establish a baseline Ongoing Operation**: Only processes new rows or rows where name/website fields change Polling Frequency**: Checks for changes every minute Usage Adding New Companies Add a new row to your Google Sheet Fill in the name and website columns Within 1 minute, the workflow will automatically: Detect the new row Enrich the company data Update the remaining columns Updating Existing Companies Modify the name or website field of an existing row The workflow will re-process that row with the updated information All enrichment data will be refreshed Monitoring Executions In n8n, go to Executions to see workflow runs Each execution shows: Which rows were processed Success/failure status Detailed logs for troubleshooting Troubleshooting Common Issues All rows are processed instead of just new/updated ones Ensure the workflow is activated, not just run manually Manual test runs will process all rows First activation may process all rows once No data is returned for a company Verify the company name and website are correct Check if the company exists in Explorium's database Some smaller or newer companies may not have data available Workflow isn't triggering Confirm the workflow is activated (Active toggle is ON) Check that changes are made to the name or website columns Verify Google Sheets credentials have proper permissions Authentication errors Re-authenticate Google Sheets credentials Verify Anthropic API key is valid and has credits Check Explorium Bearer token is correct and active Error Handling The workflow processes each row individually, so if one company fails to enrich: Other rows will still be processed The failed row will retain its original data Check the execution logs for specific error details Best Practices Data Quality: Ensure company names and websites are accurate for best results Website Format: Include full URLs (https://example.com) rather than just domain names Batch Processing: The workflow handles multiple updates efficiently, so you can add several companies at once Regular Monitoring: Periodically check execution logs to ensure smooth operation API Limits & Considerations Google Sheets API**: Subject to Google's API quotas Anthropic API**: Each enrichment uses Claude Sonnet 4 tokens Explorium MCP**: Rate limits may apply based on your subscription Support For issues specific to: n8n platform**: Consult n8n documentation or community Google Sheets integration**: Check n8n's Google Sheets node documentation Explorium MCP**: Contact Explorium support for API-related issues Anthropic/Claude**: Refer to Anthropic's documentation for API issues Example Use Cases Sales Prospecting: Automatically enrich lead lists with company size and revenue data Market Research: Build comprehensive databases of companies in specific industries Competitive Analysis: Track and monitor competitor information Investment Research: Gather firmographic data for potential investment targets

This workflow contains community nodes that are only compatible with the self-hosted version of n8n. Overview This workflow automates the process of transcribing audio files and summarizing them using OpenAI models, with the final output stored neatly in Notion. Whether you're a researcher, content creator, student, or professional, this automation saves time by converting voice recordings into actionable summaries with zero manual effort. Created by: Abdullah Dilshad Contact: iamabdullahdilshad@gmail.com Who It’s For This template is ideal for: Researchers**: Transcribe and summarize interviews, lectures, or research recordings. Content Creators**: Convert podcasts or videos into transcripts and social captions/show notes. Students**: Automatically turn lectures or study group audio into summarized notes. Professionals**: Log meeting notes and summaries directly into your Notion workspace. How It Works This four-step workflow performs the following: Step 1:* *Trigger: New Audio in Google Drive** Automatically triggers when a new audio file (MP3/WAV) is uploaded to a specified Google Drive folder.The file is then downloaded for processing. Step 2: Transcribe Audio with Whisper** The audio file is sent to OpenAI’s Whisper model for high-accuracy transcription. Step 3: Summarize Transcript with GPT-4** The transcript is passed to GPT-4, which generates a clean, concise summary. Step 4: Store Summary in Notion** A new Notion page is created with the generated summary and optional metadata (file name, upload time, etc.). Setup Instructions Step 1: Google Drive Trigger** Connect your Google Drive account. Select the folder you want to monitor. This node detects new file uploads and passes the file for download. Step 2: Download File** Downloads the new audio file for transcription. Step 3: Transcribe Recording (OpenAI Whisper) Connect your OpenAI API Key. Ensure this node receives the binary audio file. It will return the transcription as plain text. Step 3: Transcribe Recording (OpenAI Whisper)** Connect your OpenAI API Key. Ensure this node receives the binary audio file. It will return the transcription as plain text. Step 4: Summarize Transcript (GPT-4 via AI Agent)** Use your OpenAI API Key. Configure a summarization prompt like: "Summarize the following transcript in a clear and concise manner:" Connect the output from Whisper into this GPT-4 prompt. Step 5: Notion Integration** Connect your Notion account. Choose or create a database to store summaries. Map the GPT output (summary) to a "Text" or "Rich Text" property. Optionally include metadata like filename, file upload date, etc.

✨ What It Does Mello is a Claude-powered Slack assistant that helps you stay on top of unread messages across all your channels. It: Summarizes conversations contextually using Claude AI. Generates reply suggestions and sends them as private (ephemeral) Slack messages. Lets you respond instantly with one-click AI-suggested replies. Perfect for busy teams, founders, and anyone looking to reduce Slack noise and save hours each week. 🔧 Setup Instructions Create a Slack App Go to Slack API → Your Apps Click Create New App and set it up for your workspace Under OAuth & Permissions, add: Bot Token Scopes: commands, chat:write, channels:history, users:read User Token Scopes: channels:history, chat:write Enable Interactivity, and point the Request URL to your n8n webhook (e.g. /slash-summarize) Add Claude API Get an API key from Claude (Anthropic) In n8n, set up the Claude API credential (or switch to OpenAI) Import This Workflow Go to your n8n instance, click Import, and paste this template Update any placeholders (Slack app, Claude key, webhook URLs) Follow the inline sticky notes for guidance Test It Type /summarize in any Slack channel Mello will fetch unread messages, summarize them, and show reply buttons in a private message ⏱ Setup time: ~10 minutes 🛠 Workflow Highlights Slash command trigger (/summarize) Slack API integration to fetch messages Claude AI for contextual summaries Reply suggestions with smart buttons Private Slack delivery (ephemeral messages) Designed to be easily extended (e.g. add support for OpenAI, custom storage) 🔒 Note This is a lite preview of the full Mello workflow. ✅ The full version includes: Slack reply buttons with thread context Full OAuth flow with token storage MongoDB integration Custom Claude/OpenAI configuration Hosted version with onboarding, branding & support 💡 Want access to the complete version? 📩 Email nina@baloon.dev

This n8n workflow demonstrates multiple ways to harness DeepSeek's AI models in your automation pipeline! 🌟 Core Features Multiple Integration Methods 🔌 Local deployment using Ollama for DeepSeek-R1 Direct API integration with DeepSeek Chat V3 Conversational agent with memory buffer HTTP request implementation with both raw and JSON formats Model Options 🧠 DeepSeek Chat V3 for general conversation DeepSeek-R1 for advanced reasoning Memory-enabled agent for persistent context Quick Setup 🛠️ API Configuration Base URL: https://api.deepseek.com Get your API key from platform.deepseek.com/api_keys Local Setup 💻 Install Ollama for local deployment Set up DeepSeek-R1 via Ollama Configure local credentials in n8n Implementation Details 🔧 Conversational Agent Window Buffer Memory for context Customizable system messages Built-in error handling with retries API Endpoints 🌐 Chat completions for V3 and R1 models OpenAI API format compatibles

Overview This release introduces a Voice-Enabled Tour Recommendation System that leverages n8n, ElevenLabs Voice Agent, OpenAI GPT-4o, and Pinecone Vector DB to deliver personalized travel itineraries based on spoken input. Users speak their preferences to the ElevenLabs voice agent, which then triggers an n8n workflow that returns a tailored tour plan. Features Voice interaction with AI-powered travel agent via ElevenLabs Uses ChatGPT-4o for contextual understanding and generation Dynamic query handling with vector-based search using Pinecone Fast response generation using n8n webhook Modular agent memory and role design for scalable enhancement Pre-requisites n8n account with workflow creation access ElevenLabs account with agent and webhook setup OpenAI API key (GPT-4o access) Pinecone account for vector database A list of vectorized tour packages using this n8n embedder (https://creators.n8n.io/workflows/5085) Setup Instructions Step 1: Configure the Voice Agent Webhook in ElevenLabs Use POST method Webhook URL: https://... Breakdown voice input into: Destination Type of tour Number of days Number of passengers Step 2: Set Up the AI Agent Prompt in ElevenLabs Use a conversational style with summaries, clarifying questions, and affirmations. Example Prompt: “You use a natural speech style and periodically summarize... Your goal is to help callers create a personalized tour plan.” Step 3: Select LLM LLM: GPT-4o Mini Memory window: Up to 5 contexts Step 4: Integrate Tools Use Custom Tool: n8n ID: tool_xxxxxx Tool Description: “Generates travel plan once the details are collected” Step 5: Build n8n Workflow Trigger: Webhook (POST) Process user input: Tour Recommendation AI Agent Use OpenAI Chat Model (GPT-4o) for reasoning Query Pinecone Vector Store using Tour Builder Q&A node Respond with structured Itinerary Plan via webhook response How to use: Execute the n8n workflow (the webhook waits for the voice trigger from elevenlabs) Start the Elevenlabs Voice Agent Request for a tour plan to any destination giving the details of your tour preferences. Wait for the Voice Agent to respond back with tour package suggestions after fetching the tour details from the n8n workflow. Close the conversation. | Area | Improvement | | ------------------ | ----------------------------------------------------- | | 🔉 Voice UX | Natural-sounding travel agent using ElevenLabs | | 💡 Personalization | ChatGPT-4o adapts based on travel style & preferences | | 📚 Knowledge Base | Pinecone-powered vector retrieval of real tour data | | 🔁 Reusability | Modular workflow with reusable embedding tools | | ⚙️ System Design | Separation of memory, logic, and data layers | Who is this for? Travel Agencies & DMCs Offer ultra-personalized packages based on customer queries. Let AI do the matching. Tour Package Aggregators Auto-curate and send matching packages from your catalog — no manual searching needed. Content & Marketing Teams Craft customized tour recommendations for email campaigns and newsletters. Tech-enabled Travel Startups Embed this intelligence in your workflows, CRMs, or chatbots to delight customers.