HumationHuman + Automation
Back to Catalog

Connect AI to any chats in Kommo

yatolstoyyatolstoy
3338 views
2/3/2026
notificationdata-loggingdiscordairtablehttp
Official Page

Entrust customer service to AI using n8n and Kommo! Using this workflow, you can make the AI agent answer customer questions for your managers. See how it works in the video.

Advantages of integration

  • Works with any message channel that is connected to Kommo (telegram, whatsapp, facebook)
  • Understands voice and text messages
  • You can stop for a specific transaction or contact if you need a person's help.
  • It is possible to supplement the AI agent with additional tools to suit your needs

Where it can be useful

  • In customer support
  • In the qualification of clients
  • When invoicing

How it works

  1. Any incoming message to the Kommo chats is sent by the webhook to n8n
  2. n8n processes the webhook according to the specified logic
  3. n8n sends a reply message to the Kommo chat

Installation Steps

  1. Install workflow
  2. Follow the instructions to connect the kommo to the n8n
  3. Set up Credentials for OpenAI
  4. Fill in the Credentials as shown in the workflow notes
  5. Activate Workflow
  6. Write your first message as client

n8n Workflow: AI-Powered Kommo Chat Assistant

This n8n workflow enables an AI assistant to interact with Kommo chats, providing automated responses and potentially enhancing customer service or internal communication. It acts as a bridge, allowing an AI agent to process incoming messages and send replies back to Kommo.

What it does

This workflow automates the following steps:

  1. Receives Kommo Chat Messages: It listens for incoming chat messages from Kommo via a webhook.
  2. Filters Messages: It checks if the incoming message contains specific keywords or patterns (though the exact condition is not specified in the JSON, it uses an "If" node, implying a conditional check).
  3. Prepares Message for AI: It transforms the incoming message content into a format suitable for the AI agent.
  4. Processes with AI Agent: It sends the prepared message to an AI Agent (powered by LangChain and OpenAI) which uses a chat model and simple memory to generate a response.
  5. Sends AI Response to Kommo: It takes the AI-generated response and sends it back to the Kommo chat via an HTTP Request.

Prerequisites/Requirements

To use this workflow, you will need:

  • n8n Instance: A running n8n instance.
  • Kommo Account: Access to a Kommo account with a configured webhook for incoming messages.
  • OpenAI API Key: An API key for OpenAI to power the AI Chat Model.
  • LangChain Integration: The @n8n/n8n-nodes-langchain package installed in your n8n instance.

Setup/Usage

  1. Import the Workflow: Import the provided JSON into your n8n instance.
  2. Configure Webhook:
    • Activate the "Webhook" node.
    • Copy the webhook URL.
    • In your Kommo account, configure a webhook to send chat messages to this URL.
  3. Configure OpenAI Credentials:
    • In the "OpenAI Chat Model" node, configure your OpenAI API credentials.
    • Ensure the "OpenAI" node (for potential additional OpenAI actions) also has credentials configured if it were to be used in the future.
  4. Configure AI Agent:
    • Review the "AI Agent" node settings. This is where you would define the agent's prompt, tools, and other parameters that dictate its behavior.
    • The "Simple Memory" node provides conversational memory for the AI agent.
  5. Configure HTTP Request (Kommo API):
    • In the "HTTP Request" node, configure the URL, method, headers, and body to send messages back to the Kommo API. You will need your Kommo API endpoint and authentication details.
  6. Activate the Workflow: Once all configurations are complete, activate the workflow.

The workflow will now automatically process incoming Kommo chat messages, generate AI responses, and send them back to the respective chats.

Related Templates

Track meal nutrition from meal photos with LINE, Google Gemini and Google Sheets

AI Meal Nutrition Tracker with LINE and Google Sheets Who's it for This workflow is designed for health-conscious individuals, fitness enthusiasts, and anyone who wants to track their daily food intake without manual calorie counting. It is best suited for users who want a simple, AI-powered meal logging system that analyzes food photos one at a time and provides instant nutritional feedback via LINE. What it does This workflow processes a single meal photo sent via LINE, analyzes it using Google Gemini AI to identify foods and estimate nutritional content, and stores the data in Google Sheets for tracking. The workflow focuses on simplicity and encouragement: it receives a meal image, performs AI-based food recognition, estimates calories and macronutrients, calculates a health score, provides personalized advice, and replies with a detailed nutritional breakdown on LINE. How it works A single meal photo is sent to the LINE bot. The workflow is triggered via a LINE webhook. The image file is downloaded and sent to Google Gemini AI for food analysis. The AI identifies foods and estimates nutritional values (calories, protein, carbs, fat, fiber). A health score (1-10) is calculated with personalized improvement tips. The data is appended to Google Sheets for meal history tracking. The image is uploaded to Google Drive for reference. A formatted nutritional report with advice is sent back as a LINE reply. This workflow is intentionally designed to handle one image per execution. Requirements To use this workflow, you will need: A LINE Messaging API account A Google Gemini API key A Google account with access to Google Sheets and Google Drive A Google Sheets document with the following column names: Date Time Meal Type Food Items Calories Protein (g) Carbs (g) Fat (g) Fiber (g) Health Score Advice Image URL Important limitations This workflow does not support multiple images sent in a single message. Sending images in quick succession may trigger multiple executions and lead to unexpected results. Only the first image in an event payload is processed. Nutritional values are AI estimates based on visual analysis and typical serving sizes. Accuracy depends on image quality, lighting, and food visibility. This tool should not replace professional dietary advice. These limitations are intentional to keep the workflow simple and easy to understand. How to set up Create a LINE Messaging API channel and obtain a Channel Access Token. Generate a Google Gemini API key. Update the Config node with your LINE token, Google Sheets ID, Google Drive folder ID, and daily calorie goal. Configure credentials for LINE, Google Gemini, Google Sheets, and Google Drive. Register the n8n webhook URL in your LINE channel settings. Activate the workflow in n8n and test it with a single meal photo. How to customize Modify the AI prompt in the "Analyze Meal with AI" node to support different languages or dietary frameworks (keto, vegan, etc.). Adjust the daily calorie goal in the Config node to match individual needs. Add additional nutritional fields such as sodium, sugar, or vitamins. Replace Google Sheets with a fitness app API or database. Integrate with other services to send daily/weekly nutrition summaries. --- Note: This workflow was tested using real meal photos sent individually via the LINE Messaging API. Nutritional estimates are approximations and may vary from actual values. For accurate dietary tracking, consult a registered dietitian.

Oka HironobuBy Oka Hironobu
89

Automate LinkedIn requests & icebreaker with Browserflow and Google sheets

Disclaimer: As this workflow uses a Community node, it is available only to self-hosted installation of n8n Who is this for? This n8n template is designed for professionals, recruiters, and marketers who need to automate LinkedIn data population and contact request processes. It is particularly useful for those looking to streamline their outreach efforts and manage LinkedIn connections more efficiently. What problem is this workflow solving? / Use Case The workflow addresses the challenge of manually managing LinkedIn connections and sending contact requests followed by an AI generated ice-breaker. By automating these tasks, users can save time, reduce errors, and ensure consistent follow-ups with potential clients, partners, or candidates. What this workflow does: This template extract LinkedIn adresses from a google sheet, check if they already are connected to you, and send them a contact request if hey are not. Then it sends to them an AI generated Ice breaker messages, which take into account the personal and company posts, and your company description, to find common points of interest. You can contact up to 50 persons for free. Setup Copy this google sheet to your Google account Enter your data in "Set your Data Here": Google sheet URL: Paste here the URL of your google sheet Your activity: Define here what your company is about (used to match your activity with the users activity) Your name: Enter your name (used to sign your mail) Your company: Enter here your company name Your email: Used to send your email Maxitems: The number of maximum posts to download from LinkedIn Set an account on Rapid API, you are allowed for free to 50 credits (5$ for 500) and most of the calls cost 1 credit. Setup an account at Browserflow You will benefit from a 7 days free trial. And then you will have to pay $17.95. With this account you'll be able to send 1920 connection invites and 3204 messages. Install n8n-nodes-browserflow from your n8n Settings > Community Nodes. (it means for now that you'll need a self-hosted installation of n8n). and paste the API key you copied earlier as a credential. Execute it regularly to check if your connections have accepted your connection request. How to customize this workflow to your needs Customize Contact Messages: Personalize the AI agent prompt that generates the icebreaker Integrate with Other Tools: Add additional nodes to integrate with CRM systems or other marketing tools for enhanced functionality. Monitor and Optimize: Regularly review the workflow's performance and make adjustments to improve efficiency and effectiveness. By following this setup and customization guide, users can leverage this n8n template to enhance their LinkedIn outreach and connection management processes.

PollupAIBy PollupAI
650

WhatsApp group chat with your vector database — no Facebook Business required

Enable smart, real-time answers in your WhatsApp groups using a custom webhook, Pinecone vector database, and no Facebook Business setup. > 🟡 Note: This template uses a custom WhatsApp webhook. It does not use the official WhatsApp Business API. --- 👥 Who is this for? This workflow is designed for individuals and teams who want to enable smart WhatsApp group automation — without going through Meta’s official WhatsApp Business API. Ideal for small businesses, internal teams, communities, and personal power users. --- ❓ What problem is this solving? Setting up WhatsApp bots with intelligent responses often requires approval from Meta and a verified business account. This workflow removes those barriers by using a self-hosted webhook to handle incoming messages and respond using a document-trained AI via Pinecone. --- ⚙️ What this workflow does Connects a regular WhatsApp number to a custom webhook Adds the bot to any group chat (it stays silent unless mentioned) Indexes documents from Google Drive into Pinecone Responds with intelligent, context-aware answers from your custom knowledge base Auto-updates its knowledge every minute as the document changes --- 🛠️ Setup Step 1: Connect Google Drive Set up your Google Drive credentials in n8n Step 2: Configure Pinecone Create an index in Pinecone Dimension: 1536 Select this index in both Pinecone nodes Click Test Workflow to ingest your document into Pinecone Step 3: Get Access to the WhatsApp Webhook Fill out this form to request access You’ll receive a WhatsApp confirmation for linking Step 4: Test WhatsApp Integration ✅ One-on-one test: Send a message from another number 👥 Group test: Add the bot to a group; it will only respond when tagged --- 🧩 How to customize this workflow Modify the system prompt inside the AI agent node to control tone and behavior Update the connected Google Doc to match your specific domain (e.g. FAQs, SOPs, product manuals) Adjust the Pinecone sync frequency if you want updates more or less often --- 📚 Use cases Customer Support: Instant, intelligent replies in WhatsApp without live agents Team Knowledge Bot: Tag the bot for quick access to SOPs and internal docs Community Groups: Automate common questions while keeping noise low Personal AI Assistant: A WhatsApp chatbot trained on your notes and files --- 📝 Sticky Note Suggestion 💬 What this template does: > Enables an AI bot in your WhatsApp group that answers questions based on a Google Doc you provide. It uses a custom webhook, Google Drive, and Pinecone. 🔧 Requirements: > Google Drive account > Pinecone account with an index (dimension 1536) > Access to the custom WhatsApp webhook (see setup steps)

Cecilia MukimaBy Cecilia Mukima
1606