Google Gemini Chat Model and HighLevel integration

Youtube Video For Workflow Explanation: https://youtu.be/3VTYQU7N6uU This workflow operates as an automated WhatsApp customer service and booking chatbot for an HVAC company (Blankarray HVAC Solutions). It connects WhatsApp, GoHighLevel (for CRM and calendar), and a Gemini AI model to handle customer inquiries, capture contact details, and schedule service appointments. Core Flow (The Main Logic) WhatsApp Trigger** Purpose:** This is the starting point of the workflow. It actively listens for incoming WhatsApp messages and triggers the sequence whenever a new message is received. If Valid Sender Exists** Purpose:** A conditional check to ensure the incoming message has a valid sender phone number (messages[0].from is not empty). This prevents the workflow from failing on empty or malformed requests. Fetch GHL Contacts** Purpose:** Connects to GoHighLevel to search for an existing contact record using the sender's WhatsApp phone number. It always outputs data, which tells the AI later if this is a known customer or a new lead. Customer Service AI Agent1** Purpose:** The central "brain" of the operation. This node orchestrates the conversational logic based on a detailed system prompt. It adopts the persona of "Alex," an HVAC service coordinator. Functionality:** It decides whether to ask for missing user information (Name and Email), when to look up calendar slots, when to book the appointment, and how to format the responses (using WhatsApp-friendly styling). Send WhatsApp Response** Purpose:** The final step in the main execution path. It takes the text output generated by the AI Agent and sends it back to the customer's WhatsApp number. AI Sub-Nodes (The Agent's Toolkit & Brain) These nodes are connected directly to the Customer Service AI Agent1 to give it memory, intelligence, and the ability to take actions. The Brain & Memory Gemini Chat Model** Purpose:** The Large Language Model (LLM) powering the AI Agent. It processes the user's text, understands the context based on your prompt, and generates the natural language response. Redis Chat History Memory** Purpose:** Maintains the context of the conversation. It uses the user's phone number as a unique session key, allowing the AI to remember what was said earlier in the chat rather than treating every message as a brand new interaction. The Action Tools (GoHighLevel Integrations) The AI Agent intelligently decides when to trigger these tools based on the conversation flow. Save user issue in notes** Purpose:** When a customer describes their HVAC problem, the AI uses this tool to immediately log a summary of the issue directly into the customer's GoHighLevel contact profile notes. Create or update a contact in HighLevel** Purpose:** If the "Fetch GHL Contacts" node found no existing record, the AI asks the user for their name and email. Once provided, the AI uses this tool to create a brand new contact profile in GoHighLevel before proceeding to book an appointment. Fetch Available Calendar Slots** Purpose:** When the user wants to book a service, the AI uses this tool to query the GoHighLevel calendar for available 30-minute time slots on the requested date. Book Calendar Appointment** Purpose:** Once the customer agrees to a specific time, the AI uses this tool to officially book the appointment in the GoHighLevel calendar using the Contact ID and the agreed-upon timestamp.

Project Overview: Automated Climate-Driven HVAC Upsell & AI Concierge This project is specifically built for an HVAC business to automatically upsell to old customers when their locality has a heatwave or snow wave forecast in the upcoming five days. Prerequisites & Setup GoHighLevel (GHL) Create Custom Fields:** stop_whatsapp: Used when a user replies "STOP" to remove them from the marketing list. opp_type: To track the campaign type (e.g., heatwave or snowwave). Create Two Pipelines:** Pipeline A: HEATWAVE Pipeline B: SNOWWAVE Note: Both pipelines require 4 stages: New Lead, Contacted, Scheduled, and Closed. Grab the Calendar ID:** Keep your GHL Calendar ID handy, as the workflow will need it to search for free slots and book appointments. WhatsApp (Meta Business Suite) Create and approve two marketing templates for proactive outreach: A. Heatwave Template > Hello {{1}}, > With temperatures expected to rise soon, we wanted to share a few tips to keep your home comfortable and your AC running efficiently. > Maintenance Tips: > • Keep blinds closed during peak sun hours. > • Check your air filters; a clean filter prevents overworking. > • If you leave the house, raise the thermostat a few degrees rather than turning it off. > Need help? > If your system is struggling to keep up, we are here to assist. > Stay cool and safe! B. Snow Wave Template > Hello {{1}}, > With a cold front and freezing temperatures expected soon, we wanted to share a few tips to keep your home warm and your heating system running efficiently. > Winter Comfort Tips: > • Keep curtains and blinds open during the day to let sunlight naturally warm your home, then close them at night to trap the heat. > • Check your air filters; a clogged filter makes your heater work much harder in freezing weather. > • Ensure your outdoor vents and heat pump units are clear of snow or debris to maintain proper airflow. > Need help? > If your heating system is struggling to stay warm or making unusual noises, we are here to assist. > Stay warm and safe! API Integrations Nominatim OpenStreetMap API:** Review the documentation. This open-source tool will be used to extract exact cities from customer street addresses. WeatherAPI:** Obtain a free API key. Add this to your workflow's generic credentials (Type: Query Auth > Name: key > Value: your-api-key). Gemini API:** Obtain your API key to power the AI Service Concierge. Part 1: The Climate-Driven Lead Generation Engine (Proactive Outreach) This sub-workflow acts as a proactive scraper. It monitors your CRM contacts, cross-references their locations with live weather data, and triggers targeted upsell campaigns. Schedule Trigger & Fetch Contacts Schedule Trigger:** Kicks off the workflow every morning at 7:00 AM. Fetch Contacts (HighLevel):** Pulls your entire list of previous customers and leads from GoHighLevel. Geocoding & Data Cleaning If Node (City Set):** Checks if the CRM contact already has a city populated. Nominatim API (Loop & Fetch):** If a city is missing, the workflow runs the address through the Nominatim OpenStreetMap API to extract the exact city. Update Contact (HighLevel):** Saves the extracted city back to the GHL contact profile to prevent redundant geocoding in the future. Weather Data Aggregation Code Node (Group by City):** A vital step to optimize API usage. Instead of making 1,000 separate calls for 1,000 contacts, custom JavaScript groups all contacts by their respective cities. HTTP Request (Fetch Forecast):** Pings WeatherAPI.com to grab the 5-day forecast for each unique city. Hazard Detection & Routing Code Node (Detect Weather Hazards):** A script evaluates the 5-day forecast against dynamic, seasonal temperature thresholds (e.g., a "heatwave" threshold in May might be >85°F, but >95°F in August). It tags the grouped contacts with a campaign type (HEATWAVE or SNOWWAVE). If Node (Check Campaign Type):** Routes the qualified leads into the appropriate pipeline logic. CRM Execution & WhatsApp Outreach Create Opportunity (HighLevel):** Drops the qualified lead into the "New Lead" stage of the respective GHL pipeline. Send Template (WhatsApp):** Dispatches the pre-approved Meta marketing template to the customer. Update & Upsert (HighLevel):** Moves the Opportunity to the "Contacted" stage and updates the opp_type custom field so the system tracks the reason for outreach. Part 2: The AI-Powered Service Concierge (Inbound Handling) When a customer replies to the proactive blast (e.g., "My AC is making a weird noise, can someone come out?"), this sub-workflow seamlessly takes over to assist the customer and autonomously book an appointment. Trigger & Validation Trigger (WhatsApp Message Received):** Listens for inbound replies from customers. Fetch & Validate (HighLevel):** Looks up the sender's phone number in GHL. If the number does not exist in the CRM, the workflow ignores the message to prevent spam handling. The Opt-Out Filter If Node (Stop Command):** Scans the inbound message for the keyword "STOP". Upsert Contact (HighLevel):** If "STOP" is detected, the workflow immediately updates the user's stop_whatsapp custom field to TRUE, excluding them from all future blasts, and terminates the flow. The Agentic Core Customer Service AI Agent (LangChain + Gemini):** If the user is requesting assistance, the message is routed to an AI Agent powered by the Gemini Chat Model. Redis Chat History Memory:** Connects to a Redis instance so the AI retains conversation context, which is crucial for natural, back-and-forth scheduling. Agent Tools (HighLevel Integration):** The Gemini agent is equipped with specific tools it can trigger autonomously: Fetch Available Calendar Slots: The AI is strictly instructed to check live GHL availability before suggesting times to the user. Book Calendar Appointment: Automatically secures the timeslot in GHL if the user agrees. Close Deal: If the user declines service ("I'm good, no thanks"), the AI triggers this tool to mark the GHL opportunity as "Closed/Lost". Update Pipeline Stage: If an appointment is successfully booked, the AI moves the pipeline stage to "Scheduled" without any manual human intervention. Final Response Send Response (WhatsApp):** The AI formulates a conversational, friendly reply—utilizing WhatsApp's native formatting like bolding and bullet points—and sends it back to the customer to confirm the action taken.

Workflow explanation: Watch on YouTube Automated Missed Call Recovery with Gohighlevel + Twilio + Gemini Prerequisites for the HVAC n8n Workflow Before setting up the workflow in n8n, ensure you have completed the following foundational steps: Twilio Call Status Webhook:** Set the webhook of Sub-workflow 1 in the Twilio Voice section for "Call Status Changes". GoHighLevel Custom Fields:** Create two custom fields in GoHighLevel (GHL): called phone number call sid Twilio API Integration:** Ensure your Twilio API credentials are ready and configured in n8n. GoHighLevel Developer App:** Create a free GoHighLevel Developer App with the following scopes: contacts.readonly, contacts.write, opportunities.readonly, opportunities.write, locations.readonly. Generate the Client ID and Secret within the Developer App. Enter these into the n8n GHL OAuth credentials. Copy the OAuth Redirect URL from n8n to the App OAuth redirection settings and complete the authentication process. GoHighLevel Automation Workflow:** Create a workflow inside GHL that triggers when a "New Appointment is Created" and fires a POST webhook to the URL generated by Sub-workflow 3 in n8n. GoHighLevel Pipeline Setup:** Create a pipeline in GHL named "Missed call to appointment" with the following 3 stages: SMS sent No Reply Engaged | Appointment Link Sent BOOKED Scheduling Link:** Note down your GoHighLevel scheduling link and keep it handy to insert into the Twilio SMS node. Workflow Breakdown This n8n architecture is divided into three distinct sub-workflows. Here is the node-by-node explanation. Sub-Workflow 1: Automated Missed Call Follow-Up Goal: Detect a missed call, log it in GoHighLevel, and immediately text the prospect. When Webhook Received (n8n-nodes-base.webhook):** Acts as the entry point. It receives incoming POST call data from your telephony provider (Twilio) whenever a call status changes. Filter Valid Call Statuses (n8n-nodes-base.if):** Evaluates the incoming webhook payload. It only allows the workflow to continue if the CallStatus contains busy, no-answer, or canceled. Prepare Lead Data (n8n-nodes-base.set):** Cleans and maps the incoming JSON data. It extracts the caller's phone number, removes the + sign for clean formatting, grabs the called number and CallSid, and attaches specific tags like missed-call-lead. Create Lead in HighLevel (n8n-nodes-base.highLevel):** Pushes the cleaned data into GHL to create a new Contact. It maps the custom fields you created (called phone number and call sid) and assigns the hvac-inbound-missed tag. Create Opportunity in HighLevel (n8n-nodes-base.highLevel):** Creates a pipeline opportunity for the newly generated lead. It names the opportunity dynamically (e.g., "Missed Call.... [Phone].... [Date/Time]"). Send SMS via Twilio (n8n-nodes-base.twilio):** Sends the initial outreach text message to the caller (e.g., "Hi, I believe you missed a call with us... Please state your issue directly here"). Update Opportunity Status (n8n-nodes-base.highLevel):** Updates the GHL opportunity stage to the first stage in your pipeline ("SMS sent No Reply") to track that the initial outreach has occurred. Sub-Workflow 2: AI-Powered SMS Lead Qualification & Booking Goal: Process replies to the initial SMS, use AI to determine if it's a valid HVAC opportunity, and send a booking link. When SMS Received (n8n-nodes-base.twilioTrigger):** Listens for incoming SMS messages on your Twilio number. Check If Lead (n8n-nodes-base.highLevel):** Searches GHL to see if the sender's phone number already exists as a contact. Check Pipeline State (n8n-nodes-base.highLevel):** Looks up the specific opportunity associated with this contact in the "Missed call to appointment" pipeline. Lead Analyzer Agent (@n8n/n8n-nodes-langchain.agent):** The core AI brain of this sub-workflow. It consists of three integrated parts: The Agent: Prompted to act as an HVAC Opportunity Finder. It evaluates the user's SMS context to determine if they need HVAC services and if it's appropriate to send a booking link. Gemini Chat Model: Uses Google's gemini-3.1-flash-lite-preview model to process the prompt and context. Parse Structured Output: Forces the AI to return a clean JSON response (e.g., {"HVAC_oppurtunity?": "yes"}). If HVAC Opportunity Found (n8n-nodes-base.if):** Checks the parsed JSON output from the AI. If the AI determined the answer is "yes" or "yeah", the workflow proceeds. Send Response SMS (n8n-nodes-base.twilio):** Sends a text message containing your GHL scheduling link to prompt the prospect to book a visit. Update Lead Opportunity (n8n-nodes-base.highLevel):** Moves the GHL opportunity stage forward to "Engaged | Appointment Link Sent". Sub-Workflow 3: GoHighLevel Appointment Sync & Pipeline Advancement Goal: Finalize the pipeline sequence once the prospect actually books an appointment through your scheduling link. When Appointment Booked (n8n-nodes-base.webhook):** Receives the payload triggered by the GHL automation workflow you created in the prerequisites (fired when an appointment is booked). Check Lead SMS Origin (n8n-nodes-base.highLevel):** Queries GHL using the phone number from the appointment payload to ensure it matches up with the correct existing contact record. Check Pipeline State1 (n8n-nodes-base.highLevel):** Retrieves the current opportunity linked to this phone number that is currently sitting in the "Engaged" stage. Update Contact in HighLevel (n8n-nodes-base.highLevel):** Fills in the missing data gaps. Since the initial missed call only gave you a phone number, this node uses the data submitted in the booking form to update the contact's First Name, Last Name, and Email address. Update Opportunity in HighLevel (n8n-nodes-base.highLevel):** Moves the opportunity to its final stage: "BOOKED".

⏺ 🚀 How it works Fully automates your inbound and outbound voice sales pipeline — from live call qualification to CRM pipeline management — with multi-agent AI and automatic lead nurturing if a prospect doesn't book. 📞 Receives end-of-call reports from Vapi or Retell AI via webhook — works with both providers out of the box 🧠 Qualifies every inbound lead using BANT scoring (Budget · Authority · Need · Timeline) powered by Claude Haiku 📅 Detects appointment intent and preferred meeting time using GPT-4o before touching your CRM 🗂️ Upserts the contact and creates a pipeline opportunity in GoHighLevel automatically — no duplicates 💬 Analyses objections and generates a rebuttal script using Claude Sonnet (feel-felt-found + Challenger Sale) 📝 Writes a professional CRM note from the call summary using Gemini 2.0 Flash — ready to sync 🔁 Enrols unqualified leads into a GoHighLevel nurture workflow automatically for long-term follow-up 📤 Fires prioritised outbound calls every morning at 9 AM via Vapi — GPT-4o Mini ranks leads by conversion probability 📊 Logs every call (inbound + outbound) to Supabase and Google Sheets for full pipeline reporting 🛠️ Set up steps Estimated setup time: ~45 minutes Webhook — copy the webhook URL and paste it into your Vapi or Retell dashboard as the end-of-call report URL GoHighLevel — connect your HighLevel OAuth2 credential; set your Pipeline ID, Hot Stage ID, and Nurturing Stage ID in the opportunity nodes (Opportunities → Settings → Pipelines) Anthropic — connect your Anthropic API credential; used for Claude Haiku (BANT qualification) and Claude Sonnet (objection handling) OpenAI — connect your OpenAI API credential; used for GPT-4o (booking intent detection) and GPT-4o Mini (outbound lead ranking) Google Gemini — connect your Google Gemini API credential; used for CRM note writing with gemini-2.0-flash Vapi — add your Vapi API key to the HTTP Request node header; set your Phone Number ID and Assistant ID in the outbound call node (Vapi Dashboard → Phone Numbers / Assistants) Supabase — connect your Supabase API credential; create the voice_call_logs table using the SQL in the setup sticky note inside the workflow Google Sheets — connect Google Sheets OAuth2; set your Spreadsheet ID and ensure a sheet named Voice Call Log exists with the columns listed in the setup sticky note Follow the sticky notes inside the workflow — each section has a one-liner setup guide 📋 Prerequisites Vapi or Retell AI account with an active phone number and assistant configured Anthropic API key (Claude API access) OpenAI API key (GPT-4o and GPT-4o Mini access) Google Gemini API key GoHighLevel account with at least one pipeline and automation workflow set up Supabase project with the voice_call_logs table created Google Sheets spreadsheet set up as your call log --- Custom Workflow Request with Personal Dashboard [email protected] https://www.smartflowcraft.com/contact More free templates https://www.smartflowcraft.com/n8n-templates