HumationHuman + Automation
Back to Catalog

Create an automated customer support assistant with GPT-4o and GoHighLevel SMS

Cyril Nicko GasparCyril Nicko Gaspar
3449 views
2/3/2026
data extractionrest apiwordpresscsvexport
Official Page

📌 AI Agent via GoHighLevel SMS with Website-Based Knowledgebase

This n8n workflow enables an AI agent to interact with users through GoHighLevel SMS, leveraging a knowledgebase dynamically built by scraping the company's website.

❓ Problem It Solves

Traditional customer support systems often require manual data entry and lack real-time updates from the company's website. This workflow automates the process by:

  • Scraping the company's website at set intervals to update the knowledgebase.
  • Integrating with GoHighLevel SMS to provide users with timely and accurate information.
  • Utilizing AI to interpret user queries and fetch relevant information from the updated knowledgebase.

🧰 Pre-requisites

Before deploying this workflow, ensure you have:

  • An active n8n instance (self-hosted or cloud).
  • A valid OpenAI API key (or any compatible AI model).
  • A Bright Data account with Web Unlocker setup.
  • A GoHighLevel SMS LeadConnector account.
  • A GoHighLevel Marketplace App configured with the necessary scopes.
  • Installed n8n-nodes-brightdata community node for Bright Data integration (if self-hosted).

⚙️ Setup Instructions

1. Install the Bright Data Community Node in n8n

For self-hosted n8n instances:

  • Navigate to Settings → Community Nodes.
  • Click on Install.
  • In the search bar, enter n8n-nodes-brightdata.
  • Select the node from the list and click Install.

Docs: https://docs.n8n.io/integrations/community-nodes/installation/gui-install

2. Configure Bright Data Credentials

  • Obtain your API key from Bright Data.
  • In n8n, go to Credentials → New, select HTTP Request.
    • Set authentication to Header Auth.
    • In Name, enter Authorization.
    • In Value, enter Bearer <your_api_key_from_Bright_Data>.
    • Save the credentials.

3. Configure OpenAI Credentials

  • Add your OpenAI API key to the relevant nodes.
  • If you want to use a different model, replace all OpenAI nodes accordingly.

4. Set Up GoHighLevel Integration

a. Create a GoHighLevel Marketplace App
locations.readonly contacts.readonly contacts.write opportunities.readonly opportunities.write users.readonly conversations/message.readonly conversations/message.write
  • Add your n8n OAuth Redirect URL as a redirect URI in the app settings.
  • Save and copy the Client ID and Client Secret.
b. Configure GoHighLevel Credentials in n8n
  • Go to Credentials → New
  • Choose OAuth2 API
  • Input:
    • Client ID
    • Client Secret
    • Authorization URL: https://auth.gohighlevel.com/oauth/authorize
    • Access Token URL: https://auth.gohighlevel.com/oauth/token
    • Scopes: 
      locations.readonly contacts.readonly contacts.write opportunities.readonly opportunities.write users.readonly conversations/message.readonly conversations/message.write
  • Save and authenticate to complete setup.

Docs: https://docs.n8n.io/integrations/builtin/credentials/highlevel

🔄 Workflow Functionality (Summary)

  • Scheduled Scraping: Scrapes website at user-defined intervals.
  • Edit Fields node: User defines the homepage or site to scrape.
  • Bright Data Node (self-hosted) OR HTTP Node (cloud users) used to perform scraping.
  • Knowledgebase Update: The scraped content is stored or indexed.
  • GoHighLevel SMS: Incoming user queries are received through SMS.
  • AI Processing: AI matches queries to relevant content.
  • Response Delivery: AI-generated answers are sent back via SMS.

🧩 Use Cases

  • Customer Support Automation: Provide instant, accurate responses.
  • Lead Qualification: Automatically answer potential customer inquiries.
  • Internal Knowledge Distribution: Keep staff updated via SMS based on website info.

🛠️ Customization

  • Scraping URLs: Adjust targets in the Edit Fields node.
  • Model Swap: Replace OpenAI nodes to use a different LLM.
  • Format Response: Customize output to match your tone or brand.
  • Other Channels: Expand to include chat apps or email responses.
  • Vector Databases: It is advisable to store the data into a third-party vector database services like Pinecone, Supabase, etc.
  • Chat Memory Node: This workflow is using Redis as a chat memory but you can use N8N built-in chat memory.

✅ Summary

This n8n workflow combines Bright Data’s scraping tools and GoHighLevel’s SMS interface with AI query handling to deliver a real-time, conversational support experience. Ideal for businesses that want to turn their website into a live knowledge source via SMS, this agent keeps itself updated, smart, and customer-ready.

Automated Customer Support Assistant with GPT-4o and GoHighLevel SMS

This n8n workflow creates an automated customer support assistant that leverages GPT-4o for intelligent responses and integrates with GoHighLevel for SMS communication. It's designed to handle incoming SMS messages, process them using an AI agent, and respond appropriately, while also managing conversation history.

What it does

This workflow automates the following steps:

  1. Receives Incoming SMS: Listens for incoming SMS messages via a webhook, likely from a platform like GoHighLevel.
  2. Initial Data Transformation: Processes the incoming SMS data, extracting relevant information like the sender's phone number and the message content.
  3. Manages Conversation History (Redis): Stores and retrieves conversation history using a Redis Chat Memory, ensuring the AI agent has context for ongoing dialogues.
  4. Loads Knowledge Base (Optional/Implicit): Although not explicitly shown with a dedicated "load knowledge base" node, the workflow structure suggests that the AI agent is configured with a knowledge base (likely ingested during setup or implicitly handled by the "Default Data Loader" and "Simple Vector Store").
  5. Splits Text for Processing: If a knowledge base is loaded, it splits the text into smaller, manageable chunks for efficient processing by the AI.
  6. Embeds Text: Generates numerical representations (embeddings) of the text using OpenAI's embedding model, which are then stored in a vector store.
  7. Stores Embeddings (Vector Store): Saves the text embeddings in a Simple Vector Store for quick retrieval of relevant information during AI processing.
  8. Processes with AI Agent (GPT-4o): Utilizes an AI Agent (configured with an OpenAI Chat Model, likely GPT-4o) to understand the incoming message in context of the conversation history and knowledge base, and formulate a response.
  9. Filters Responses: Checks if the AI agent generated a valid response.
  10. Sends SMS Response (GoHighLevel): If a valid response is generated, it sends the AI-generated message back to the customer via GoHighLevel SMS.
  11. Handles No Response: If the AI agent does not generate a response, the workflow can be extended to handle this scenario (e.g., escalate to human support, send a default message).
  12. Waits for Next Interaction: Includes a Wait node, potentially to manage rate limits or allow for asynchronous processing before the next interaction.

Prerequisites/Requirements

To use this workflow, you will need:

  • n8n Instance: A running n8n instance.
  • GoHighLevel Account: For sending and receiving SMS messages. You'll need GoHighLevel credentials configured in n8n.
  • OpenAI API Key: For the OpenAI Chat Model (GPT-4o) and Embeddings OpenAI.
  • Redis Instance: For the Redis Chat Memory to store conversation history. You'll need Redis credentials configured in n8n.
  • Knowledge Base Data: Any documents or information you want your AI assistant to reference (e.g., FAQs, product manuals). This data will be processed and stored in the vector store.

Setup/Usage

  1. Import the Workflow: Download the JSON provided and import it into your n8n instance.
  2. Configure Credentials:
    • GoHighLevel: Set up your GoHighLevel API credentials in n8n.
    • OpenAI: Set up your OpenAI API key in n8n.
    • Redis: Configure your Redis connection details in n8n.
  3. Configure Webhook:
    • Activate the Webhook node and copy its URL.
    • In your GoHighLevel account, configure an incoming SMS webhook to point to this n8n webhook URL.
  4. Configure AI Agent:
    • Review the AI Agent node settings. Ensure the OpenAI Chat Model is set to gpt-4o (or your preferred model).
    • Adjust the agent's instructions and tools as needed for your specific use case.
  5. Load Knowledge Base (if applicable):
    • The Default Data Loader, Recursive Character Text Splitter, Embeddings OpenAI, and Simple Vector Store nodes are set up to process and store your knowledge base.
    • You will need to manually trigger this part of the workflow or configure a separate workflow to ingest your knowledge base documents into the Simple Vector Store.
  6. Activate the Workflow: Once all configurations are complete, activate the workflow in n8n.

Your automated customer support assistant will now be live and ready to respond to SMS messages via GoHighLevel!

Related Templates

Daily Magento 2 customer sync to Google Contacts & Sheets without duplicates

Automatically sync newly registered Magento 2 customers to Google Contacts and Google Sheets every 24 hours — with full duplication control and seamless automation. This workflow is a plug-and-play customer contact automation system designed for Magento 2 store owners, marketers, and CRM teams. It fetches customer records registered within the last 24 hours (from 00:00:00 to 23:59:59), checks against an existing Google Sheet to avoid reprocessing, and syncs only the new ones into Google Contacts. This ensures your contact list is always fresh and up to date — without clutter or duplicates. ✅ What This Workflow Does: Automates Customer Syncing Every day, it fetches newly registered Magento 2 customers via API based on the exact date range (midnight to midnight). Deduplicates Using Google Sheets A master Google Sheet tracks already-synced emails. Before adding a customer, the workflow checks this list and skips if already present. Creates Google Contacts Automatically For each unique customer, it creates a new contact in your Google Contacts, saving fields like first name, last name, and email. Logs New Entries to Google Sheets In Google Sheets, it even records magento 2 customer group, createdat, websiteid & store_id After syncing, it adds each new email to the tracking sheet, building a cumulative record of synced contacts. Fully Scheduled & Automated Can be scheduled with the Cron node to run daily (e.g., 12:05 AM) with no manual intervention required. 🔧 Modules Used: HTTP Request (Magento 2 API) Date & Time (for filtering registrations) Google Sheets (for reading/writing synced emails) Google Contacts (for contact creation) Set, IF, and Merge nodes (for control logic) Cron (for scheduling the automation) 💼 Use Cases: Keep your email marketing tools synced with Magento 2 customer data. Build a CRM-friendly contact base in Google Contacts without duplicates. Share customer data with sales or support teams through synced Google Sheets. Reduce manual work and human error in data transfer processes. 🔒 Credentials Required Magento 2 Bearer Auth: Set up as a credential in n8n using your Magento 2 API access token. Google API 📂 Category E-commerce → Magento 2 (Adobe Commerce) 💬 Need Help? 💡 Having trouble setting it up or want to customize this workflow further? Feel free to reach out — I’m happy to help with setup, customization, or Magento 2 API integration issues. Contact: Author 👤 Author Kanaka Kishore Kandregula Certified Magento 2 Developer https://gravatar.com/kmyprojects https://www.linkedin.com/in/kanakakishore

Kanaka Kishore KandregulaBy Kanaka Kishore Kandregula
163

Send RSS feed data to webhook

Filters articles based on keywords, checks against MongoDB for unique links, then sends results to different webhooks

daveBy dave
3968

Run bulk RAG queries from CSV with Lookio

This template processes a CSV of questions and returns an enriched CSV with RAG-based answers produced by your Lookio assistant. Upload a CSV that contains a column named Query, and the workflow will loop through every row, call the Lookio API, and append a Response column containing the assistant's answer. It's ideal for batch tasks like drafting RFP responses, pre-filling support replies, generating knowledge-checked summaries, or validating large lists of product/customer questions against your internal documentation. Who is this for? Knowledge managers & technical writers: Produce draft answers to large question sets using your company docs. Sales & proposal teams: Auto-generate RFP answer drafts informed by internal docs. Support & operations teams: Bulk-enrich FAQs or support ticket templates with authoritative responses. Automation builders: Integrate Lookio-powered retrieval into bulk data pipelines. What it does / What problem does this solve? Automates bulk queries: Eliminates the manual process of running many individual lookups. Ensures answers are grounded: Responses come from your uploaded documents via Lookio, reducing hallucinations. Produces ready-to-use output: Delivers an enriched CSV with a new Response column for downstream use. Simple UX: Users only need to upload a CSV with a Query column and download the resulting file. How it works Form submission: User uploads a CSV via the Form Trigger. Extract & validate: Extract all rows reads the CSV and Aggregate rows checks for a Query column. Per-row loop: Split Out and Loop Over Queries iterate rows; Isolate the Query column normalizes data. Call Lookio: Lookio API call posts each query to your assistant and returns the answer. Build output: Prepare output appends Response values and Generate enriched CSV creates the downloadable file delivered by Form ending and file download. Why use Lookio for high quality RAG? While building a native RAG pipeline in n8n offers granular control, achieving consistently high-quality and reliable results requires significant effort in data processing, chunking strategy, and retrieval logic optimization. Lookio is designed to address these challenges by providing a managed RAG service accessible via a simple API. It handles the entire backend pipeline—from processing various document formats to employing advanced retrieval techniques—allowing you to integrate a production-ready knowledge source into your workflows. This approach lets you focus on building your automation in n8n, rather than managing the complexities of a RAG infrastructure. How to set up Create a Lookio assistant: Sign up at https://www.lookio.app/, upload documents, and create an assistant. Get credentials: Copy your Lookio API Key and Assistant ID. Configure the workflow nodes: In the Lookio API call HTTP Request node, replace the apikey header value with your Lookio API Key and update assistantid with your Assistant ID (replace placeholders like <your-lookio-api-key> and <your-assistant-id>). Ensure the Form Trigger is enabled and accepts a .csv file. CSV format: Ensure the input CSV has a column named Query (case-sensitive as configured). Activate the workflow: Run a test upload and download the enriched CSV. Requirements An n8n instance with the ability to host Forms and run workflows A Lookio account (API Key) and an Assistant ID How to take it further Add rate limiting / retries: Insert error handling and delay nodes to respect API limits for large batches. Improve the speed: You could drastically reduce the processing time by parallelizing the queries instead of doing them one after the other in the loop. For that, you could use HTTP request nodes that would trigger your sort of sub-workflow. Store results: Add an Airtable or Google Sheets node to archive questions and responses for audit and reuse. Post-process answers: Add an LLM node to summarize or standardize responses, or to add confidence flags. Trigger variations: Replace the Form Trigger with a Google Drive or Airtable trigger to process CSVs automatically from a folder or table.

Guillaume DuvernayBy Guillaume Duvernay
293