WhatsApp AI assistant for Q&A & bookings with Gemini, Pinecone & Google Sheets

Open on n8n.io

$20/month : Unlimited workflows

2500 executions/month

Try free

THE #1 IN WEB SCRAPING

Scrape any website without limits

Try free

HOSTINGER

Early Deal
DISCOUNT 20%

Self-hosted n8n

Unlimited workflows - from $4.99/mo

Try free

#1 hub for scraping, AI & automation

6000+ actors - $5 credits/mo

Try free

Important notice

This workflow is provided as-is. Please review and test before using in production.

1. Workflow Overview

Overview Turn WhatsApp chats into instant answers and real time bookings—all in one n8n workflow. Your AI Agent leverages Gemini embeddings + Pinecone for on the fly knowledge retrieval, then logs ...

Best for

Automation automation workflows
advanced n8n builders looking for reusable templates

Tools used

n8n-nodes-base.code, n8n-nodes-base.whatsapp, n8n-nodes-base.stickynote, @n8n/n8n-nodes-langchain.lmchatgooglegemini, n8n-nodes-base.datetime, @n8n/n8n-nodes-langchain.memorybufferwindow, @n8n/n8n-nodes-langchain.vectorstorepinecone, @n8n/n8n-nodes-langchain.embeddingsgooglegemini

Source and attribution

This workflow is cataloged by N8N Workflows and links back to its original n8n.io source page by Tharwat Mohamed.

Original n8n.io source

1.1 Workflow description

Title: WhatsApp AI assistant for Q&A & bookings with Gemini, Pinecone & Google Sheets
Workflow name: WhatsApp AI assistant for Q&A & bookings with Gemini, Pinecone & Google Sheets

Overview

Turn WhatsApp chats into instant answers and real-time bookings—all in one n8n workflow. Your AI Agent leverages Gemini embeddings + Pinecone for on-the-fly knowledge retrieval, then logs reservations directly into Google Sheets.

Features

AI-powered Q&A: Natural-language responses driven by Gemini + Pinecone vector search

Seamless Reservations: Book services via WhatsApp; entries auto-append to Google Sheets

Auto-Embedding Sub-workflow: Drag-and-drop Google Drive docs get indexed in Pinecone

24-Hour Follow-Up: Automated template messages if no response within a day

Personal Support Pledge: Hands-on help until your workflow runs flawlessly

Requirements

n8n account (self-hosted or n8n.cloud)

Google Cloud project with Gemini & Drive APIs enabled

Pinecone account (free tier works)

Google Sheets account

WhatsApp Business API credentials (e.g. Twilio, 360dialog)

Setup Instructions

Import Workflow

Download the .json file from your Gumroad purchase

In n8n Editor → Import → From File → select the JSON

Add Credentials

Google Service Account (Gemini & Drive APIs)

Pinecone (API Key + Environment)

Google Sheets OAuth2

WhatsApp Business API (HTTP credential or native)

Configure Nodes

AI Agent: select Gemini credentials; update system prompt with your business name & services

Pinecone Loader: point “Google Drive” node to your docs folder

Sheets Append: set Spreadsheet ID, sheet name “reservations”, map Timestamp, UserID, Service, Date, Time, Notes

WhatsApp Trigger & Send: set webhook URL; choose approved template name

Test End-to-End

Activate the workflow → send a test WhatsApp message → verify AI reply + new row in your sheet

Google Sheet Structure

Column Description Timestamp Auto-generated when a user books UserID : Unique WhatsApp user identifier Service : Chosen service or product name Date : Booking date Time : Booking time slot Notes : Any extra information (e.g., special requests)

Customization

Add New Services: Edit the system prompt’s services list

Change Follow-Up Window: Adjust the “24-hour window check” node logic

Embed Different Docs: Point the Drive node at any folder of PDFs/TXT

📞 Personal Support Pledge: I’ll work with you (via WhatsApp or email, remote desktop ) until your workflow is running flawlessly—no extra fees, no “good luck” drop‐off. Just send a message via:

Email: [email protected]

WhatsApp: +20 106 180 3236

1.2 Logical Blocks

This catalog entry is organized from the workflow JSON. The node-level section below shows the executable blocks available for review before importing the template.

2. Block-by-Block Analysis

Block 1 - cleanAnswer

Type / Role: n8n-nodes-base.code - code
Config choices: Version 2

Block 2 - 24-hour window check

Type / Role: n8n-nodes-base.code - code
Config choices: Version 2

Block 3 - Send Pre-approved Template Message to Reopen the Conversation

Type / Role: n8n-nodes-base.whatsApp - whatsApp
Config choices: Version 1

Block 4 - Send AI Agent's Answer

Type / Role: n8n-nodes-base.whatsApp - whatsApp
Config choices: Version 1

Block 5 - Sticky Note

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 6 - Google Gemini Chat Model

Type / Role: @n8n/n8n-nodes-langchain.lmChatGoogleGemini - lmChatGoogleGemini
Config choices: Version 1

Block 7 - Date & Time

Type / Role: n8n-nodes-base.dateTime - dateTime
Config choices: Version 2

Block 8 - Simple Memory

Type / Role: @n8n/n8n-nodes-langchain.memoryBufferWindow - memoryBufferWindow
Config choices: Version 1.3

Block 9 - Pinecone Vector Store

Type / Role: @n8n/n8n-nodes-langchain.vectorStorePinecone - vectorStorePinecone
Config choices: Version 1.2

Block 10 - Embeddings Google Gemini

Type / Role: @n8n/n8n-nodes-langchain.embeddingsGoogleGemini - embeddingsGoogleGemini
Config choices: Version 1

Block 11 - Google Gemini Chat Model1

Type / Role: @n8n/n8n-nodes-langchain.lmChatGoogleGemini - lmChatGoogleGemini
Config choices: Version 1

Block 12 - AI Agent

Type / Role: @n8n/n8n-nodes-langchain.agent - agent
Config choices: Version 1.7

Block 13 - reservations

Type / Role: n8n-nodes-base.googleSheetsTool - googleSheetsTool
Config choices: Version 4.6

Block 14 - When clicking ‘Execute workflow’

Type / Role: n8n-nodes-base.manualTrigger - manualTrigger
Config choices: Version 1

Block 15 - Google Drive

Type / Role: n8n-nodes-base.googleDrive - googleDrive
Config choices: Version 3

Block 16 - Default Data Loader

Type / Role: @n8n/n8n-nodes-langchain.documentDefaultDataLoader - documentDefaultDataLoader
Config choices: Version 1

Block 17 - Recursive Character Text Splitter

Type / Role: @n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - textSplitterRecursiveCharacterTextSplitter
Config choices: Version 1

Block 18 - Pinecone Vector Store1

Type / Role: @n8n/n8n-nodes-langchain.vectorStorePinecone - vectorStorePinecone
Config choices: Version 1.2

Block 19 - Embeddings Google Gemini1

Type / Role: @n8n/n8n-nodes-langchain.embeddingsGoogleGemini - embeddingsGoogleGemini
Config choices: Version 1

Block 20 - Sticky Note1

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 21 - Sticky Note2

Type / Role: n8n-nodes-base.stickyNote - stickyNote
Config choices: Version 1

Block 22 - whatsapp trigger

Type / Role: n8n-nodes-base.whatsAppTrigger - whatsAppTrigger
Config choices: Version 1

Block 23 - Check 24-Hour Follow-Up

Type / Role: n8n-nodes-base.if - if
Config choices: Version 2.2

Block 24 - Pinecone Vector Search

Type / Role: @n8n/n8n-nodes-langchain.toolVectorStore - toolVectorStore
Config choices: Version 1.1

Showing the first 24 of 25 workflow blocks. Download the JSON for the full node graph.

3. Summary Table

Workflow	WhatsApp AI assistant for Q&A & bookings with Gemini, Pinecone & Google Sheets
Complexity	advanced
Nodes	25
Categories	Automation
Author	Tharwat Mohamed
Published	08 Jul 2025

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

Use the JSON export at /data/workflows/5781/5781.json as the source template for this automation.
2. Import the template into n8n

Open n8n, import the downloaded JSON, and review each node before activating the workflow.
3. Configure credentials and variables

Replace placeholder credentials, API keys, webhook URLs, account IDs, and environment-specific values with your own settings.
4. Test with sample data

Run the workflow manually or in a staging workspace, inspect node output, and confirm downstream systems receive the expected data.
5. Activate and monitor

Enable the workflow only after testing, then monitor executions, errors, and rate limits during the first production runs.

5. General Notes & Resources

Review imported nodes carefully before activation. This catalog entry is intended to help you inspect the workflow structure, understand required services, and find related templates faster.

Node names, credentials, schedules, webhook paths, and external service limits may need adjustment for your workspace.

Download workflow JSON Original n8n.io source Automation workflows

Frequently asked questions

What does WhatsApp AI assistant for Q&A & bookings with Gemini, Pinecone & Google Sheets do?

What do I need before importing this workflow?

Review the workflow JSON, configure any required credentials in n8n, and test the automation in a safe workspace before using it in production.

Can I customize this workflow?

Yes. Use the block-by-block analysis and the downloadable JSON to inspect each node, then adjust credentials, prompts, schedules, filters, or destinations for your Automation use case.

Tharwat Mohamed

6 workflows

Nodes

n8n-nodes-base.code n8n-nodes-base.whatsapp n8n-nodes-base.stickynote @n8n/n8n-nodes-langchain.lmchatgooglegemini n8n-nodes-base.datetime @n8n/n8n-nodes-langchain.memorybufferwindow @n8n/n8n-nodes-langchain.vectorstorepinecone @n8n/n8n-nodes-langchain.embeddingsgooglegemini

Complexity

advanced

Published 08 Jul 2025

Likes 0

View on n8n.io Download Workflow

Install path: /data/workflows/5781/5781.json

Share Your Workflow

Have a useful automation to share? Publish it and help the community.

Submit Your Template How to Submit

Related Workflows

Generate and publish AI home cam Shorts with OpenAI, kie.ai and YouTube

## Quick overview This workflow runs three times daily to generate an AI “home cam” short video concept with OpenAI, create the video via kie.ai, then download and archive it to Google Drive, upload it to YouTube as a public video, and send a confirmation email via Gmail. ## How it works 1. Runs on a schedule three times a day (08:00, 12:00, and 18:00). 2. Selects a random scenario number from the configured range and asks OpenAI (GPT-4.1-mini) to generate a title, description, tags, and a detailed text-to-video prompt as structured JSON. 3. Builds a kie.ai Sora-2 text-to-video job request using the generated prompt and submits it to the kie.ai API. 4. Waits and repeatedly polls kie.ai until the job succeeds and returns a result payload containing a video download URL. 5. Downloads the generated video file from the returned URL. 6. Uploads the video to a specified Google Drive folder, publishes it to YouTube with the AI-generated metadata, and emails you a notification containing the prompt and video link. ## Setup 1. Add an OpenAI API credential, a kie.ai API key using HTTP Header Auth, and OAuth credentials for Google Drive, YouTube, and Gmail. 2. In the workflow variables, set your notification email address, the target Google Drive folder ID, and the callback URL value used in the kie.ai request. 3. Review or adjust the random scenario range (videoIdeaMin/videoIdeaMax) and YouTube upload settings (for example, privacyStatus and notifySubscribers) before activating the workflow. ## Requirements - OpenAI API credential - kie.ai API key - OAuth credentials for Google Drive, YouTube, and Gmail

View

Score company ad spend from Meta, Google and LinkedIn Ads with Google Sheets

## Quick Overview This workflow pulls Pending companies from Google Sheets, checks their ad activity via Adyntel for Meta (Facebook), Google Ads, and LinkedIn Ads, calculates a budget signal score from ad volume and channel diversity, and writes the results back to the same sheet. ## How it works 1. Runs when you manually execute the workflow in n8n. 2. Reads rows from Google Sheets where the Status column is set to Pending. 3. Processes each company domain in sequence and queries Adyntel for Meta (Facebook) ads, Google Ads, and LinkedIn Ads. 4. Combines the three ad search results into a single dataset for the current company. 5. Calculates per-platform ad counts, total ads, active platforms, channel diversity, and a composite budget_signal_score. 6. Updates the matching row in Google Sheets (by domain), writes the scoring fields, and sets Status to Done before moving to the next company. ## Setup 1. Connect Google Sheets OAuth credentials and set the target spreadsheet and sheet where your company list lives. 2. Add Adyntel API credentials so the workflow can query Meta (Facebook), Google Ads, and LinkedIn Ads by company domain. 3. Ensure your Google Sheet includes at least company_name, domain, and Status columns, with Status set to Pending for rows you want to process.

View

Prioritize exception queues with Gemini, Google Sheets, Slack and Gmail

## Quick Overview This workflow receives a webhook trigger, reads exception records from Google Sheets, uses Google Gemini (Generative Language API) to rank and summarize them, posts a prioritized report to Slack, writes summary metrics back to Google Sheets, and emails a critical alert via Gmail when needed. ## How it works 1. Receives a webhook request to start an exception-queue analysis run. 2. Reads the current exception list from a Google Sheets worksheet and stops with a “No open exceptions found” webhook response if there are no rows. 3. Formats the sheet rows into a structured text list and sends it to the Google Gemini API to generate a ranked, scored priority list plus summary counts. 4. Parses the Gemini response and builds Slack Block Kit content, an HTML email body for critical items, and fields for saving analysis metadata. 5. Appends or updates a summary row in a second Google Sheets worksheet with the AI summary and severity counts. 6. Posts the ranked exception report to a Slack channel. 7. If any critical exceptions are detected, sends an alert email via Gmail, then returns a JSON “Done” response to the original webhook caller with processing statistics. ## Setup 1. Add credentials for Google Sheets OAuth2, Slack OAuth2, and Gmail OAuth2 in n8n. 2. Provide a Google Gemini API key and update the HTTP request to use it (preferably via an n8n credential or environment variable rather than hard-coding). 3. Update the Google Sheets document ID and ensure Sheet1 contains columns like ExceptionID, Title, Severity, System, and ReportedAt, and Sheet2 has columns for summary and count fields used by the workflow. 4. Select the target Slack channel in the Slack node and confirm it matches where you want the priority report posted. 5. Configure the Gmail node with the recipient(s) and ensure your webhook URL (path: /exception-trigger) is used by the system that should trigger the analysis.

View

Need Custom Automation?

Get help designing a custom n8n workflow that connects your stack and fits your process.

WhatsApp AI assistant for Q&A & bookings with Gemini, Pinecone & Google Sheets

Workflow preview

Important notice

1. Workflow Overview

Best for

Tools used

Source and attribution

1.1 Workflow description

Overview

Features

Requirements

Setup Instructions

Google Sheet Structure

Customization

1.2 Logical Blocks

2. Block-by-Block Analysis

Block 1 - cleanAnswer

Block 2 - 24-hour window check

Block 3 - Send Pre-approved Template Message to Reopen the Conversation

Block 4 - Send AI Agent's Answer

Block 5 - Sticky Note

Block 6 - Google Gemini Chat Model

Block 7 - Date & Time

Block 8 - Simple Memory

Block 9 - Pinecone Vector Store

Block 10 - Embeddings Google Gemini

Block 11 - Google Gemini Chat Model1

Block 12 - AI Agent

Block 13 - reservations

Block 14 - When clicking ‘Execute workflow’

Block 15 - Google Drive

Block 16 - Default Data Loader

Block 17 - Recursive Character Text Splitter

Block 18 - Pinecone Vector Store1

Block 19 - Embeddings Google Gemini1

Block 20 - Sticky Note1

Block 21 - Sticky Note2

Block 22 - whatsapp trigger

Block 23 - Check 24-Hour Follow-Up

Block 24 - Pinecone Vector Search

3. Summary Table

4. Reproducing the Workflow from Scratch

1. Download the workflow JSON

2. Import the template into n8n

3. Configure credentials and variables

4. Test with sample data

5. Activate and monitor

5. General Notes & Resources

Frequently asked questions