Google Gemini workflows
1,419 results — 128 downloadable workflow files, 1,291 source-linked n8n references
Draft personalized cold emails from Google Sheets using Gemini and HubSpot
Quick overview This workflow batch-processes leads from Google Sheets, researches each person and company using Tavily plus Google Gemini, drafts a personalized cold email, then creates/updates the contact in HubSpot with a research note and a saved email draft before marking the lead as Done in the sheet. How it works Runs manually and sets a batch size that controls how many leads to process per run. Reads leads from Google Sheets, skips rows already marked as Done, and normalizes the selected batch into clean lead fields. Processes the batch one lead at a time and uses Tavily search (last 60 days) with Google Gemini to extract the most recent public activity, pain points, and a personalization hook. Cleans and parses the research JSON so it can be reused reliably downstream. Uses Google Gemini to draft a 90–120 word cold outreach email (subject and body) that incorporates the research and offers a free “Automated LinkedIn Post Creator” n8n workflow. Creates or reuses the HubSpot contact, logs a HubSpot note with the research and drafted email, and saves the email as a HubSpot engagement in DRAFT status. Updates the matching row in Google Sheets (by Email) to set Status to “Done
Send and track Slack invoice requests with Gemini, Google Sheets and Gmail
Quick overview Youtube Video: https://youtu.be/42-oHh9w9Eo This workflow listens for Slack @mentions, uses Google Gemini to classify the request and extract invoice details, then reads and updates Google Sheets, generates invoice PDFs with PdfBro, sends invoices or reminders via Gmail, and posts confirmations or errors back to Slack. How it works Triggers when the workflow’s Slack app is mentioned in a specified Slack channel. Uses Google Gemini to classify the message intent (send invoice, remind invoice, or check status) and extract the recipient email and invoice due date. Routes the request based on the extracted intent and stops if the intent cannot be determined. For SEND_INVOICE, looks up the client in a Google Sheets “Client Bill” spreadsheet and posts a Slack error if no matching email is found. If a client is found, generates an invoice PDF with PdfBro, emails it to the client via Gmail, appends/updates the invoice record in a Google Sheets “Client Invoices” spreadsheet, and posts a Slack confirmation. For REMIND_INVOICE, finds an UNPAID invoice for the email in the “Client Invoices” Google Sheet, regenerates the invoice PDF with PdfBro, emails a reminder via Gmail, and p
WRun LinkedIn outreach with Google Gemini, Apify, Google Sheets, and PhantomBuster
Quick overview This workflow collects a plain-English LinkedIn audience description via an n8n form, uses Google Gemini to generate a search URL, pulls matching leads from Apify, writes five personalized icebreakers to Google Sheets, and drip-launches a PhantomBuster agent every 15 minutes. How it works Receives a form submission with a plain-English description of your target LinkedIn audience. Uses Google Gemini to turn the audience description into a JSON response containing an Apollo-style search URL, then parses and extracts the searchUrl value. Calls the Apify API to run an actor and return up to 100 lead records matching the configured filters. Limits processing to the first five leads to control outreach volume. Uses Google Gemini to generate a short, unique connection-message icebreaker for each lead based on their profile fields. Appends or updates each lead in Google Sheets with contact details, LinkedIn URLs, and the generated icebreaker. Waits 15 minutes per lead and then triggers a PhantomBuster agent via HTTP request to start the outreach action. Setup Create and add credentials for Google Gemini (PaLM API) and update the model selection if needed. Add an Apify API t
Handle WhatsApp customer service chats with Google Gemini and Google Sheets
Quick Overview This workflow handles WhatsApp customer service via OpenWA, using Google Gemini and a Google Sheets knowledge base to answer personal chats, while routing conversations to a human queue in Google Sheets when escalation is needed. How it works Triggers on OpenWA WhatsApp events and ignores message reactions except for specific ✅/☑ reactions used to re-enable AI handling. Normalizes incoming event fields and processes only personal chats (IDs ending with @c.us) that are not sent by your own WhatsApp account. Checks a Google Sheets “Session Chat” list to decide whether the conversation is currently handled by a human, and only continues to AI when no active human session is found. Uses a Google Gemini chat model with short-term memory and a Google Sheets “Database Company” tool to draft a friendly Indonesian response based only on the sheet data. If the AI response does not contain the #admin escalation token, it sends the reply back to the customer via OpenWA. If the AI response contains #admin, it appends the chat to the Google Sheets “Session Chat” sheet to flag it for human follow-up. When a ✅/☑ reaction is received for a chat, it finds and deletes the corresponding
Tailor ATS-ready resumes and cover letters with Gemini, Google Drive, Notion, and Gmail
Quick overview Transform any resume into a professional, ATS-compliant document with AI. Supports Global ATS, German, and Japanese resume formats, generates personalized cover letters, and automates PDF creation and delivery for every job application. How it works Receives an n8n form submission with the company name, job description, selected ATS type, and an optional request to generate a cover letter. Lists resume PDF files from a specified Google Drive folder, downloads each file, extracts the PDF text, and cleans it into a single plain-text resume input. Uses Google Gemini to rewrite the resume into pure-HTML output tailored to the job description, choosing Global ATS, German Lebenslauf, or Japanese Rirekisho formatting based on the selected ATS type. Converts the generated HTML resume into a PDF using the PDF.co HTML-to-PDF API and retrieves the resulting PDF from the returned URL. Uploads the generated resume PDF to a Google Drive output folder, then reads the existing Notion database entries to compute the next serial number and creates a new Notion database page linking to the uploaded file. If cover letter generation is requested, uses Google Gemini to write a localized c
Score Salesforce playbook compliance with Google Sheets, Gemini, and Slack
Quick overview This workflow manually runs to review Salesforce opportunities listed in Google Sheets, evaluates each deal against sales playbook rules using Google Gemini, updates compliance fields in Salesforce, alerts in Slack for low scores, and logs results back to Google Sheets. How it works Starts manually and loads a list of opportunities from Google Sheets. Processes each row in batches and fetches the latest matching Opportunity record from Salesforce. Adds predefined playbook rules (including a passing score) and combines them with the opportunity data. Checks whether at least two meetings are completed, and if not, auto-generates a non-compliant evaluation without using AI. For opportunities that pass the meeting minimum, sends the opportunity details and rules to Google Gemini to produce a compliance decision, missing steps, score, reason, and risk level, then normalizes the response into structured fields. Updates the Opportunity in Salesforce with compliance status, risk, score, and timestamp, and sends a Slack alert when the compliance score is below 70. For compliant opportunities, writes the final status and compliance metrics back to a Google Sheets results tab (
Create a Gmail morning audio briefing with Google Gemini and Google Drive
Quick Overview This workflow runs every weekday at 7 AM to fetch up to 10 unread Gmail messages from the last day, summarize them into a narrated script with Google Gemini, convert the script to an MP3 using Smallest.ai, upload it to Google Drive, and email you a public listening link. How it works Runs on a schedule every weekday at 7:00 AM. Pulls up to 10 unread Gmail emails from the last 24 hours. Cleans and categorizes the emails into URGENT, NEWSLETTERS, and OTHER sections while skipping common job-alert style messages. Uses a LangChain AI Agent powered by Google Gemini to turn the digest into a plain-text morning briefing script. Truncates the script to a safe character limit and converts it to speech as an MP3 with Smallest.ai. Uploads the MP3 to Google Drive, makes the file publicly readable, and sends a Gmail message with the listening link and the script text. Setup Connect your Gmail credentials for both reading unread emails and sending the briefing email, and update the recipient address in the outgoing email step. Add Google Gemini credentials in the Google Gemini Chat Model used by the AI Agent. Add your Smallest.ai API credentials for text-to-speech generation. Conn
Create narrated blog audio from RSS with Google Gemini, Smallest.ai and WordPress
Quick Overview This workflow polls a blog RSS feed, rewrites new posts into a spoken-word script using Google Gemini, generates an MP3 with Smallest.ai, uploads it to Google Drive, and updates the matching WordPress post to embed a public audio player. How it works Polls an RSS feed every minute to detect newly published or updated blog items. Extracts the post body and strips HTML, scripts, styles, and common entities to produce clean plain text. Uses Google Gemini to rewrite the text into a single, conversational narration script with an intro/outro and length limits. Sends the rewritten script to Smallest.ai to synthesize an English MP3 audio file. Uploads the MP3 to Google Drive and updates sharing so anyone with the link can play it. Updates the corresponding WordPress post to embed an HTML5 audio player pointing to the Google Drive link and includes the article text below it. Setup Set the RSS feed URL in the RSS Feed Trigger node and confirm the feed provides the fields used for the post content and GUID. Add credentials for Google Gemini (Google AI / Gemini) and select that connection in the chat model used by the rewrite step. Add your Smallest.ai API credentials and verif
Qualify leads and send personalized audio follow-ups with Gemini and Smallest.ai
Quick Overview This workflow receives lead submissions via a webhook, uses Google Gemini to qualify the lead and write a personalized spoken follow-up script, and for qualified leads generates an MP3 with Smallest.ai, shares it from Google Drive, emails it via Gmail, logs outcomes to Google Sheets, and alerts sales in Slack. How it works Receives a POST webhook request containing a lead’s name, email, and message. Sends the lead details to a Google Gemini–powered AI agent to determine whether the lead is qualified and, if so, generate a short personalized audio script. Parses the agent’s JSON response and routes the workflow based on the qualified flag. If the lead is qualified, Smallest.ai synthesizes the script into an MP3 and uploads it to Google Drive. Shares the Google Drive audio file publicly and sends the lead a Gmail message with a link to listen. Appends the qualified lead record (including the audio link and timestamp) to Google Sheets and posts a notification to a Slack channel. If the lead is unqualified, appends the lead details and timestamp to Google Sheets without generating audio or sending email. Setup Enable the webhook and copy the generated /lead-capture URL i
Transcribe and summarize Twilio calls with Smallest.ai, Gemini, Slack, and GoHighLevel
Quick Overview This workflow listens for completed Twilio call recordings, downloads and transcribes the audio with Smallest.ai, summarizes the transcript with Google Gemini, then notifies a Slack user and creates a new opportunity in GoHighLevel. How it works Triggers when Twilio Voice Insights reports a call summary as complete. Downloads the call recording audio from Twilio using the provided recording URL. Sends the audio file to Smallest.ai to generate a speech-to-text transcription. Uses a Google Gemini-powered AI agent to produce a short call summary, caller sentiment, and a suggested next step from the transcript and call metadata. Sends the generated summary to a specified Slack user. Creates a new opportunity in GoHighLevel that includes the caller number and AI summary. Setup Connect your Twilio credentials and ensure Twilio Voice Insights call summary events are enabled for your account. Add your Smallest.ai API credentials for the transcription step. Configure Google Gemini credentials in the LangChain Google Gemini chat model used by the AI agent. Connect your Slack credentials and set the target user (or change to a channel) for notifications. Connect your GoHighLeve
Qualify voicemail leads with Twilio, Google Gemini, Gmail and Google Sheets
Quick overview When a buyer or seller leaves a voicemail, this workflow transcribes it automatically, qualifies their intent using Gemini AI, sends an instant SMS acknowledgment, and alerts the agent for Hot leads — turning every missed call into a qualified lead within seconds. How it works Receives a POST webhook from Twilio when a voicemail recording and transcription are completed. Validates the voicemail by checking that the recording is completed, the transcription is completed, and the call duration is longer than 5 seconds. Extracts the transcript, caller phone number, call SID, duration, and recording URL, then sends the transcript to Google Gemini to return structured lead details, a Hot/Warm/Cold score, and draft SMS/email replies. Parses and sanitizes the Gemini JSON output, applies fallbacks if parsing fails, optionally appends a Google Calendar booking link for Hot leads, and builds an agent-ready HTML summary including the transcript and recording link. Sends an acknowledgment SMS to the caller via Twilio, and sends an acknowledgment email via Gmail only when a caller email address is available. Appends the lead details, transcript, and messaging status to a Google S
Extract and validate invoice data from Google Drive using OCR.Space, Gemini, and Google Sheets
Quick overview This workflow monitors a Google Drive folder for newly uploaded invoice files, extracts text with OCR.Space, uses Google Gemini to convert the OCR text into structured invoice fields, validates required values, then stores results in Google Sheets and sends Gmail notifications for success or manual review. How it works Triggers when a new file is created in a specified Google Drive folder. Downloads the uploaded invoice file from Google Drive and checks that the MIME type is PDF, JPG, JPEG, or PNG. Sends the file to the OCR.Space API to extract the invoice text and stops if OCR reports a processing error. Uses Google Gemini to convert the OCR text into structured JSON containing supplier, invoice metadata, amounts, currency, and line items. Validates and normalizes the extracted fields, flags missing required values, and marks the record for manual review when needed. If manual review is required, sends a Gmail alert listing missing fields; otherwise, appends key invoice fields to Google Sheets and sends a Gmail confirmation email. Setup Connect Google Drive OAuth2 credentials and set the folder ID to watch for invoice uploads. Provide an OCR.Space API key and ensure
Route supplier risk alerts from Gmail to Slack with Gemini and Google Sheets
Quick overview This workflow monitors incoming Gmail messages from suppliers, uses Google Gemini to analyze sentiment and relationship risk, generates an engagement strategy for risky emails, sends an alert to Slack, and logs the analysis and recommended response to Google Sheets. How it works Triggers every minute by checking Gmail for new incoming emails. Filters out irrelevant messages (for example newsletters, unsubscribe emails, no-reply senders, and auto-replies) and keeps only valid supplier emails. Extracts the sender, subject, and email snippet into a single text block and waits briefly to buffer processing. Sends the email text to Google Gemini to return a structured JSON analysis with sentiment score/label, intent, urgency, key concern, and deterioration risk, then normalizes these fields and derives a trend. Flags the interaction as high risk based on the deterioration risk value or a low sentiment score and waits briefly before continuing. Uses Google Gemini to generate a concise engagement strategy (recommended action, draft opening message, and follow-up timeline), then parses it and formats a Slack-ready alert. Sends the alert to a selected Slack user and appends th
Extract Twilio voice donation details with Groq, Gemini, and Google Sheets
Quick overview This workflow receives Twilio call recording callbacks, transcribes the audio with Groq Whisper, uses Google Gemini/Groq LLMs to extract structured donation details, and appends the results (with transcript and review flag) to Google Sheets. How it works Receives a Twilio Recording Status Callback webhook and immediately responds with TwiML (``). Captures call metadata (CallSid, caller number, recording URL/SID, and duration) and continues only if the recording exists and is at least 2 seconds long. Waits briefly for Twilio to finalize the media, then downloads the recording MP3 using Twilio HTTP Basic Auth. Sends the audio file to Groq’s Whisper transcription endpoint to generate a text transcript. Uses a LangChain prompt with Google Gemini and Groq chat models to extract donation amount, fee (if mentioned), beneficiary name, currency, a needs-review flag, and a short summary from the transcript. Parses the model output as JSON and falls back to an error summary with needs_review=yes if parsing fails. Checks Google Sheets for an existing row matching the CallSid/RecordingUrl and, if not found, appends a new row with the extracted fields, transcript, and call details
WHandle WhatsApp support chats with OpenRouter, Pinecone, and Gemini
Quick overview This template implements a WhatsApp support suite that logs inbound events to a dashboard API, routes conversations through an OpenRouter-powered AI agent with Pinecone RAG and memory, exposes a webhook for human outbound replies, and provides a webhook to summarize recent chats for handoff. How it works Triggers on WhatsApp Cloud API events and routes status updates (sent/delivered/read) to a dashboard API endpoint for storage. For inbound messages, looks up the contact in the dashboard API and normalizes the message into a consistent schema (sender, type, timestamp, and best-effort content). If the message contains media (image/video/audio/document), fetches the WhatsApp media URL, downloads the file, uploads it to the dashboard’s media endpoint, and attaches the resulting media URL and MIME type. Stores inbound messages and reactions in the dashboard API, then checks via the cases endpoint whether the sender already has an open case. If the inbound message is text and no open case is found, queries Pinecone as a tool (using Google Gemini embeddings), uses an OpenRouter chat model with conversation memory to draft a reply or create a new case via the dashboard API,
Predict Salesforce deal escalation risk with Gemini and Slack alerts
Quick overview This workflow pulls open Salesforce opportunities and their last-30-days activities, uses Google Gemini to predict escalation risk per deal, then flags high-risk opportunities in Salesforce and notifies a Slack user. How it works Starts manually and fetches open opportunities and recent Salesforce Task activities from the last 30 days. Merges opportunities with their related activities and builds a per-deal context including amount, probability, type, activity list, and whether all activities are completed. Batches the deals and skips ones that have 100% probability and active/completed engagement, then waits briefly between remaining items to reduce API load. Sends each deal context to Google Gemini to classify risk (high/medium/low), identify specific risk flags, and return a one-line summary as JSON. Cleans and validates the Gemini response by stripping formatting, parsing JSON safely, and normalizing invalid risk levels to “unknown.” For deals marked as high risk, updates the Salesforce opportunity description with the risk details and sends a formatted alert message to a specified Slack user. Setup Add Salesforce OAuth2 credentials and ensure the workflow has ac
Detect revenue leakage with Salesforce, Google Sheets, Gemini, and Slack
Quick overview This workflow manually audits Closed Won Salesforce opportunities against billed amounts in Google Sheets, uses Google Gemini to analyze any revenue gap, then alerts a Slack user and writes an audit note back to the Salesforce opportunity. How it works Starts when you run the workflow manually. Fetches up to 20 Salesforce opportunities where the stage is "Closed Won" and processes them in batches with a short delay to reduce API pressure. Looks up matching billing rows in Google Sheets and totals the billed amount for the same Deal ID, then calculates the missing revenue versus the Salesforce Amount. For deals with a positive revenue gap, sends the discrepancy details to Google Gemini to classify severity and generate a root cause, recommendation, and Salesforce-ready audit note. Parses the Gemini JSON response and builds a formatted Slack message containing the deal, gap, severity, and recommended action. Sends the Slack alert and updates the Salesforce opportunity description with the audit note and the expected, billed, and missing amounts. Setup Add credentials for Salesforce OAuth2, Google Sheets OAuth2, Google Gemini (PaLM) API, and Slack OAuth2. In Salesforce,
Monitor ride surge events and analyze ride errors with Sheets, Slack and Gemini
Quick overview This workflow pulls ride events and error records from Google Sheets, detects surge pricing and long waits, and notifies via Slack. For error records, it uses Google Gemini with real-time traffic and weather API lookups to diagnose the issue and send recommended actions to Slack. How it works Runs manually and reads ride records from a Google Sheets spreadsheet. Processes the rows one by one with a short delay and routes each record based on whether its type is an event or an error. For event records, checks if the ride price is more than 1.5× the normal price and the wait time is over 10 minutes. If surge conditions are met, sends a surge and delay notification to Slack and records a surge-alert log entry. If surge conditions are not met, records a normal “no alert needed” log entry. For error records, structures the ride and error context and asks Google Gemini to generate an incident summary, probable cause, and recommended actions, calling traffic and weather APIs as needed. Parses the Gemini response into JSON and posts the formatted error report to Slack. Setup Connect Google Sheets OAuth credentials and set the correct spreadsheet and sheet tab in the Google S
Create TikTok carousel posts with Upload Post, Google Sheets, Gemini, GPT-4.1
Quick overview This workflow runs daily to pull TikTok post and profile analytics from Upload Post, updates a Google Sheets performance log, uses Google Gemini and OpenAI to generate a new carousel concept and caption, creates four images via fal.ai, publishes to TikTok, and updates a persistent “Agent Skill” sheet. How it works Runs on a daily schedule (or manually) and loads product, Upload Post, and Google Sheets configuration values. Reads the Google Sheets “Performance Log,” selects posts missing stats or posted recently, fetches TikTok post analytics from the Upload Post API, and writes updated metrics back to the sheet. Aggregates the refreshed history, fetches TikTok profile analytics from Upload Post, reads the “Agent Skill” sheet, and compiles a single context summary. Uses Google Gemini (via a structured JSON output) to generate a TikTok carousel plan including caption, strategy notes, four slide prompts, hashtags, and an engagement question. Sends the four prompts to fal.ai to generate four 9:16 PNG carousel images and collects their hosted image URLs. Uses OpenAI (GPT-4.1) to write a short TikTok photo-post description, publishes the carousel to TikTok via Upload Post
C
Post TikTok, YouTube Shorts and Instagram Reels with Airtable, OpenAI and Google
Quick Overview This workflow runs on a schedule, pulls the next publish-ready video from Airtable, uses OpenAI, Google Gemini, and CloudConvert to generate a transcript, title, description, tags, and hashtags, then uploads to YouTube Shorts, posts an Instagram Reel via Meta Graph API, and queues TikTok publishing via Google Sheets. How it works Runs on a schedule (or manually) and waits a random number of minutes to stagger posting. Searches Airtable for content marked Publish = true and Status = “In Publish Queue”, then selects a single record to process. Downloads the video, converts it to MP3 with CloudConvert, and transcribes the audio with OpenAI. Uses OpenAI and Google Gemini to extract a main keyword, generate a YouTube-optimized title, and create YouTube tags, hashtags, and a full YouTube description, then derives a shorter content-only caption for Instagram/TikTok. Uploads the video to tmpfiles.org to generate a direct file URL and updates the Airtable record with the generated metadata and set Status = “Published”. Uploads the video to YouTube with the generated title, description, and tags. Creates and publishes an Instagram Reel via the Meta (Facebook) Graph API after a
Send prescription PDFs to patients via WhatsApp with Google Gemini and Supabase
Quick overview This workflow listens for incoming WhatsApp messages from clinic staff, uses Google Gemini to extract prescription details, generates a prescription PDF via an HTML-to-PDF API, uploads it to a public URL, sends the document back over WhatsApp, and logs outcomes to Supabase. How it works Triggers whenever a new WhatsApp message is received on your WhatsApp Business Cloud number. Captures configuration values and the incoming message text and sender number. Uses Google Gemini to extract patient name, doctor name, and medication details into structured data and flags any missing required fields. If required details are missing, replies to staff on WhatsApp with what to fix and inserts a needs_review record into Supabase. If details are complete, renders a prescription HTML document, converts it to a PDF via an external HTML-to-PDF API, and uploads the PDF to an external file-hosting API. Sends the prescription PDF to the sender on WhatsApp and inserts a “sent” log record (including the PDF URL) into Supabase. Setup Connect WhatsApp Business Cloud credentials for the WhatsApp trigger and the WhatsApp send steps, and configure the workflow’s webhook in Meta/WhatsApp so in
WTrack recurring job pain points with SerpApi, Gemini, and Google Sheets
Quick Overview This workflow runs weekly to pull Google Jobs results via SerpApi, uses Google Gemini to extract operational pain points and an automation opportunity from each posting, logs them to Google Sheets, and writes a frequency-ranked pain-point summary to a summary tab. How it works Runs weekly on a schedule. Sets the target job role, location, and Google Sheets tab name to use for this run. Queries Google Jobs through SerpApi and splits the response into one item per job posting. Sends each posting’s title, company, and description to Google Gemini and parses the returned JSON into structured fields. Appends each analyzed posting (company, title, pain points, automation opportunity, and collection date) as a new row in Google Sheets. Reads all rows from the same Google Sheets tab, counts how often each pain-point phrase appears, and sorts the list by frequency. Appends the ranked pain-point frequency list to a Google Sheets "summary" tab. Setup Add a SerpApi API key and update the SerpApi request parameters in the HTTP request step (or store the key in an n8n credential). Connect a Google Sheets OAuth2 credential and replace the placeholder spreadsheet URL/ID with your ow
Turn customer emails into FAQ drafts with Gmail, Gemini, Docs and Sheets
Quick overview This workflow monitors customer-support emails in Gmail, uses Google Gemini to extract FAQ-ready questions and draft answers, logs every candidate to Google Sheets, and routes strong candidates to a Google Docs draft while sending unclear or sensitive messages to a Gmail draft for manual review. How it works Triggers every 5 minutes when Gmail finds new messages matching the configured support-style search query. Cleans and normalizes the email metadata and body text to remove signatures and quoted replies. Sends the normalized email content to Google Gemini to extract the customer question, category, urgency, FAQ value score, draft answer, and a recommended action as structured JSON. Logs the extracted FAQ candidate details (including score, tags, and sensitivity flags) to a Google Sheets tab for tracking. Creates a Google Docs FAQ draft and inserts the generated draft content when the candidate meets the score threshold or is marked as reusable. Creates a Gmail draft to the reviewer with the Google Docs link for high-value candidates, or a separate Gmail draft containing review notes for sensitive or unclear emails. Setup Connect credentials for Gmail, Google Gemin
Answer support FAQs with Google Gemini, Supabase, Google Sheets and WhatsApp
Quick overview This workflow ingests FAQs from Google Sheets into a Supabase vector table using Google Gemini embeddings, then serves a webhook-based support chatbot that answers only from that FAQ knowledge base and escalates unanswered questions to a human via UltraMsg WhatsApp. How it works Runs manually to pull FAQ rows (Question/Answer) from a Google Sheets spreadsheet. Formats each row into a single text document (for example, Q: … A: …), generates embeddings with Google Gemini, and inserts the documents into a Supabase vector store table. Receives incoming chat messages via a POST webhook that includes message and sessionId. Uses a Google Gemini chat model with session-based memory to query the Supabase vector store for the most relevant FAQ matches and generates a reply strictly from the retrieved content. If the agent output indicates escalation to a human, sends the full message content to UltraMsg via an HTTP request to alert a WhatsApp number. Returns a JSON response to the webhook caller with either the FAQ-based answer or a confirmation that a human agent has been notified. Setup Add credentials for Google Gemini (PaLM) API, Supabase, and Google Sheets OAuth2. In Supa