January 22, 2026

Gmail + Telegram: consistent support replies, logged

Lisa Granqvist Partner Workflow Automation Expert

Get a free AI assessment → ⬇️ Use template

Your support inbox is doing that thing again. The same questions arrive in Gmail, then show up on Telegram five minutes later, and somehow the replies don’t match. It’s slow, messy, and easy to get wrong.

Support leads feel it first, but marketing managers and operations folks end up pulled in too when customers get stuck. This Gmail Telegram automation keeps replies consistent, remembers the thread, and logs every interaction so you stop losing context.

Below, you’ll see how the workflow routes Gmail and Telegram messages into an AI support agent, pulls answers from your Google Sheets knowledge base, escalates tricky cases, and records clean logs for reporting.

How This Automation Works

The full n8n workflow, from trigger to final output:

n8n Workflow Template: Gmail + Telegram: consistent support replies, logged

Click to explore

flowchart LR

    subgraph sg0["📧 Gmail Customer Inquiry Flow"]
        direction LR
        n6@{ icon: "mdi:play-circle", form: "rounded", label: "📧 Gmail Customer Inquiry Tri..", pos: "b", h: 48 }
        n7@{ icon: "mdi:swap-vertical", form: "rounded", label: "📋 Process Gmail Message", pos: "b", h: 48 }
        n8@{ icon: "mdi:robot", form: "rounded", label: "🤖 Gmail AI Agent", pos: "b", h: 48 }
        n9@{ icon: "mdi:brain", form: "rounded", label: "🧠 OpenAI Chat Model - Gmail", pos: "b", h: 48 }
        n10@{ icon: "mdi:memory", form: "rounded", label: "🧠 Gmail Memory", pos: "b", h: 48 }
        n11@{ icon: "mdi:message-outline", form: "rounded", label: "📧 Send Gmail Reply", pos: "b", h: 48 }
        n12@{ icon: "mdi:message-outline", form: "rounded", label: "✅ Mark Gmail as Read", pos: "b", h: 48 }
        n13@{ icon: "mdi:database", form: "rounded", label: "📊 Log Gmail Interaction", pos: "b", h: 48 }
        n17@{ icon: "mdi:database", form: "rounded", label: "Gmail Escalation Logger", pos: "b", h: 48 }
        n18@{ icon: "mdi:database", form: "rounded", label: "knowledge base", pos: "b", h: 48 }
        n18 -.-> n8
        n10 -.-> n8
        n8 --> n11
        n11 --> n12
        n11 --> n13
        n17 -.-> n8
        n7 --> n8
        n9 -.-> n8
        n6 --> n7
    end

    subgraph sg1["💬 Telegram Customer Message Flow"]
        direction LR
        n0["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/telegram.svg' width='40' height='40' /></div><br/>💬 Telegram Customer Message .."]
        n1@{ icon: "mdi:swap-vertical", form: "rounded", label: "📋 Process Telegram Message", pos: "b", h: 48 }
        n2@{ icon: "mdi:robot", form: "rounded", label: "🤖 Telegram AI Agent", pos: "b", h: 48 }
        n3@{ icon: "mdi:brain", form: "rounded", label: "🧠 OpenAI Chat Model - Telegram", pos: "b", h: 48 }
        n4@{ icon: "mdi:memory", form: "rounded", label: "🧠 Telegram Memory", pos: "b", h: 48 }
        n5["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/telegram.svg' width='40' height='40' /></div><br/>💬 Send Telegram Reply"]
        n14@{ icon: "mdi:database", form: "rounded", label: "📊 Log Telegram Interaction", pos: "b", h: 48 }
        n19@{ icon: "mdi:database", form: "rounded", label: "knowledge base1", pos: "b", h: 48 }
        n20@{ icon: "mdi:database", form: "rounded", label: "Telegram Escalation Logger", pos: "b", h: 48 }
        n19 -.-> n2
        n4 -.-> n2
        n2 --> n5
        n5 --> n14
        n20 -.-> n2
        n1 --> n2
        n3 -.-> n2
        n0 --> n1
    end

    subgraph sg2["🚨 Error Flow"]
        direction LR
        n15@{ icon: "mdi:play-circle", form: "rounded", label: "🚨 Error Trigger", pos: "b", h: 48 }
        n16["<div style='background:#f5f5f5;padding:10px;border-radius:8px;display:inline-block;border:1px solid #e0e0e0'><img src='https://flowpast.com/wp-content/uploads/n8n-workflow-icons/httprequest.dark.svg' width='40' height='40' /></div><br/>📢 Notify Admin of Error"]
        n15 --> n16
    end

    %% Styling
    classDef trigger fill:#e8f5e9,stroke:#388e3c,stroke-width:2px
    classDef ai fill:#e3f2fd,stroke:#1976d2,stroke-width:2px
    classDef aiModel fill:#e8eaf6,stroke:#3f51b5,stroke-width:2px
    classDef decision fill:#fff8e1,stroke:#f9a825,stroke-width:2px
    classDef database fill:#fce4ec,stroke:#c2185b,stroke-width:2px
    classDef api fill:#fff3e0,stroke:#e65100,stroke-width:2px
    classDef code fill:#f3e5f5,stroke:#7b1fa2,stroke-width:2px
    classDef disabled stroke-dasharray: 5 5,opacity: 0.5
    class n6,n0,n15 trigger
    class n8,n2 ai
    class n9,n3 aiModel
    class n10,n4 ai
    class n13,n17,n18,n14,n19,n20 database
    class n16 api
    classDef customIcon fill:none,stroke:none
    class n0,n5,n16 customIcon

The Problem: Support Replies Drift Across Channels

When customers bounce between email and chat, your team’s “single conversation” turns into fragments. Someone answers in Gmail using yesterday’s policy. Another person answers in Telegram with a different tone, different steps, or a different promise. Then comes the follow-up: “But your teammate said…” and now you’re digging through threads, searching for screenshots, and trying to reconstruct what happened. Even if you’re fast, the mental load is real, and the mistakes tend to show up when you’re busiest. Honestly, it’s not the hard questions that burn time. It’s the repeated ones, multiplied by two channels.

The friction compounds. Here’s where it usually breaks down.

Agents answer the same “where’s my order” question several times a day because there is no single, trusted response.
Conversation context gets lost when a customer starts in Gmail and then switches to Telegram, so you re-ask basic details.
Escalations happen too late because no one is tagging “this is complex” consistently in the moment.
Reporting becomes guesswork since support interactions are scattered across inboxes instead of logged in one place.

The Solution: One AI Support Brain for Gmail and Telegram

This workflow monitors both Gmail and Telegram for incoming support questions, then routes them to a dedicated AI support agent built in n8n. The agent reads the message, checks conversation memory so it doesn’t treat every reply like a brand-new ticket, and looks up answers from a Google Sheets knowledge base you control. It generates a consistent, brand-appropriate response and sends it back through the same channel the customer used. If the question is risky or genuinely complicated (billing disputes, angry messages, technical edge cases), the workflow logs an escalation to a separate sheet for a human to pick up. Everything gets recorded: what the customer asked, what the AI responded, when it happened, and whether it was resolved.

The workflow starts when a Gmail email arrives or a Telegram message hits your bot. From there, the AI agent uses your knowledge base sheet plus short-term memory to write the reply. Finally, it sends the message back, marks the email as processed, and logs the full interaction (and any escalation) into Google Sheets.

What You Get: Automation vs. Results

What This Workflow Automates

Results You’ll Get

It watches Gmail and Telegram at the same time for new support inquiries.
It pulls approved answers from a Google Sheets knowledge base before writing a reply.
It keeps short conversation memory per customer so follow-ups stay coherent.
It logs every interaction and writes escalations into a separate tracker automatically.

Most teams get replies out in under a minute instead of “when someone notices.”
You stop rewriting the same core answers all day, which usually frees up a few hours a week.
Customers see one consistent policy and tone across both channels.
Escalations become visible immediately, not buried in a thread.
You end up with clean data in Google Sheets for QA, training, and reporting.

Example: What This Looks Like

Say you handle about 30 support questions a day split across Gmail and Telegram. Manually, if each message takes roughly 6 minutes to read, search past replies, answer, and log, that’s about 3 hours of repetitive work daily. With this workflow, a new message triggers instantly, the agent drafts and sends the reply, and logging happens in the background. You still review escalations, but your “touch time” drops to checking a sheet a couple times a day, which is closer to 15 minutes than half your afternoon.

What You’ll Need

n8n instance (try n8n Cloud free)
Self-hosting option if you prefer (Hostinger works well)
Gmail (or Google Workspace) to receive and send support emails.
Telegram Bot to receive and send chat support messages.
Google Sheets for the knowledge base, logs, and escalations.
OpenAI API key (get it from the OpenAI Platform “API Keys” page).

Skill level: Intermediate. You will connect OAuth credentials, paste a few IDs (sheet IDs), and test with real messages.

Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).

How It Works

A new message arrives in Gmail or Telegram. Gmail triggers when a support email hits your inbox, and Telegram triggers when someone messages your bot. Two entry points, one support brain.

The message is cleaned up and mapped. n8n standardizes the payload (name, contact, subject, message text) so the agent gets the same structure regardless of channel. That small detail is what keeps answers consistent.

The AI agent drafts a response using your knowledge base. The workflow checks Google Sheets for relevant FAQ entries, then uses the OpenAI chat model to write a reply in your tone. It also uses simple session memory so the agent can handle “following up on my last message” without guessing.

Replies, logging, and escalation happen automatically. Gmail gets a response and the email is marked read. Telegram gets a formatted chat reply. Both channels write a row into your Interaction Log sheet, and anything flagged as “needs a human” goes into the Escalations sheet.

You can easily modify the knowledge base structure to match how your team writes answers, or adjust escalation rules based on what you consider high-risk. See the full implementation guide below for customization options.

Step-by-Step Implementation Guide

Step 1: Configure the Telegram Trigger

Set up the Telegram entry point so new messages are captured and mapped into a consistent structure for the AI agent.

Add and configure Telegram Incoming Trigger with Updates set to message.
Credential Required: Connect your telegramApi credentials in Telegram Incoming Trigger.
In Map Telegram Payload, map fields using expressions like {{ $json.message.from.first_name }}, {{ $json.message.chat.id }}, and set channel to telegram.
Confirm Map Telegram Payload sets subject to Customer Support Inquiry and message_content to {{ $json.message.text }}.

Step 2: Configure the Gmail Trigger

Set up email intake and normalize Gmail fields for the AI agent.

Configure Gmail Inquiry Trigger with Filters set to INBOX and CATEGORY_PERSONAL, and Read Status set to unread.
Credential Required: Connect your gmailOAuth2 credentials in Gmail Inquiry Trigger.
In Map Gmail Payload, set customer_email to {{ $json["From"].match(/<(.*?)>/)?.[1] || $json["From"] }} and message_content to {{ $json.text || $json.snippet }}.
Ensure Map Gmail Payload captures subject as {{ $json.Subject }} and message_id as {{ $json.id }}.

Step 3: Set Up AI Agents and Memory

Wire the AI agents to their chat models, memory, and knowledge base tools for both Gmail and Telegram support paths.

In Telegram Support Agent, set Text to {{ $json.message_content }} and keep Prompt Type as define.
Connect Telegram Chat Model as the language model for Telegram Support Agent and set options like Max Tokens to 100 and Temperature to 0.3.
Credential Required: Connect your openAiApi credentials in Telegram Chat Model.
Set Telegram Session Memory with Session Key as telegram_{{ $json.customer_id }} and Session ID Type to customKey.
In Gmail Support Agent, set Text to {{ $json.message_content }} and keep Prompt Type as define.
Connect Gmail Chat Model as the language model for Gmail Support Agent with Max Tokens 1000 and Temperature 0.3.
Credential Required: Connect your openAiApi credentials in Gmail Chat Model.
Set Gmail Session Memory with Session Key as gmail_{{ $json.customer_email }} and Session ID Type to customKey.
Attach knowledge base and escalation tools: Knowledge Base Lookup, Gmail Escalation Log to Gmail Support Agent, and Knowledge Base Lookup TG, Telegram Escalation Log to Telegram Support Agent.

Credential Required: Connect your googleSheetsOAuth2Api credentials in Knowledge Base Lookup, Knowledge Base Lookup TG, Gmail Escalation Log, and Telegram Escalation Log. For AI tool sub-nodes and memory (like Telegram Session Memory and Gmail Session Memory), credentials should be added to the parent agent and model nodes.

Step 4: Configure Output Actions

Send AI responses back to the customer and record interactions.

In Dispatch Telegram Reply, set Text to {{ $json.output }} and Chat ID to {{ $('Map Telegram Payload').item.json.chat_id }}.
Enable Parse Mode as Markdown and set Reply To Message ID to {{ $('Map Telegram Payload').item.json.message_id }}.
Credential Required: Connect your telegramApi credentials in Dispatch Telegram Reply.
In Send Gmail Response, set Operation to reply, Message to {{ $json.output }}, and Message ID to {{ $('Map Gmail Payload').item.json.message_id }}.
Credential Required: Connect your gmailOAuth2 credentials in Send Gmail Response.

Send Gmail Response outputs to both Flag Gmail Read and Record Gmail Interaction in parallel. Make sure both nodes are connected correctly so the email is marked as read while logging the response simultaneously.

In Flag Gmail Read, set Operation to markAsRead and Message ID to {{ $('Map Gmail Payload').item.json.message_id }}.
Credential Required: Connect your gmailOAuth2 credentials in Flag Gmail Read.
In Record Gmail Interaction, keep Operation as append, set Document ID to [YOUR_ID], and Sheet Name to AI_Responses.
Credential Required: Connect your googleSheetsOAuth2Api credentials in Record Gmail Interaction.
In Record Telegram Interaction, keep Operation as append, set Document ID to [YOUR_ID], and Sheet Name to AI_Responses.
Credential Required: Connect your googleSheetsOAuth2Api credentials in Record Telegram Interaction.

⚠️ Common Pitfall: The Google Sheets nodes use [YOUR_ID] placeholders. Replace both Document ID and Sheet Name with your actual sheet IDs and sheet names.

Step 5: Add Error Handling

Ensure failures trigger admin notifications for quick recovery.

Confirm Handle Error Trigger is connected to Notify Admin on Error.
In Notify Admin on Error, set URL to [CONFIGURE_YOUR_WEBHOOK] and keep Method as POST.
Verify the body text contains {{ $json.error.message }}, {{ $json.error.node.name }}, and {{ new Date().toISOString() }} for diagnostics.

⚠️ Common Pitfall: If you do not replace [CONFIGURE_YOUR_WEBHOOK], error alerts will silently fail.

Step 6: Test and Activate Your Workflow

Validate both Telegram and Gmail paths, then enable automation.

Click Execute Workflow and send a test Telegram message to confirm Telegram Incoming Trigger → Map Telegram Payload → Telegram Support Agent → Dispatch Telegram Reply → Record Telegram Interaction.
Send a new unread Gmail message and verify Gmail Inquiry Trigger → Map Gmail Payload → Gmail Support Agent → Send Gmail Response runs, with Flag Gmail Read and Record Gmail Interaction executing in parallel.
Check your Google Sheet to ensure rows append with timestamps and AI responses.
Trigger a controlled error to confirm Handle Error Trigger sends a notification via Notify Admin on Error.
When everything looks correct, toggle the workflow to Active for production use.

🔒

Unlock Full Step-by-Step Guide

Get the complete implementation guide + downloadable template

Common Gotchas

Google (Gmail and Sheets) credentials can expire or need specific permissions. If things break, check n8n’s Credentials page and your Google Cloud OAuth consent settings first.
If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
Default prompts in AI nodes are generic. Add your brand voice early or you’ll be editing outputs forever.

Frequently Asked Questions

How long does it take to set up this Gmail Telegram automation automation?

About an hour if your Gmail, Telegram bot, and Sheets are ready.

Do I need coding skills to automate Gmail Telegram automation?

No. You’ll mostly connect accounts and copy in your Google Sheet IDs.

Is n8n free to use for this Gmail Telegram automation workflow?

Yes. n8n has a free self-hosted option and a free trial on n8n Cloud. Cloud plans start at $20/month for higher volume. You’ll also need to factor in OpenAI API costs, which are usually a few cents per conversation depending on message length.

Where can I host n8n to run this automation?

Two options: n8n Cloud (managed, easiest setup) or self-hosting on a VPS. For self-hosting, Hostinger VPS is affordable and handles n8n well. Self-hosting gives you unlimited executions but requires basic server management.

Can I customize this Gmail Telegram automation workflow for different escalation rules?

Yes, and you should. In the two “Support Agent” sections (one for Gmail, one for Telegram), you can adjust the agent instructions so it escalates on things like refund threats, legal terms, high-value billing disputes, or repeated failed troubleshooting. You can also change what gets written to the Escalations sheet by editing the Google Sheets escalation logging nodes, so your team sees priority, reason, and the exact customer message.

Why is my Telegram connection failing in this workflow?

Most of the time it’s the bot token or webhook setup. Re-check the token from @BotFather, then confirm the Telegram credentials in n8n are using the updated value. If it still fails, look for blocked webhook delivery (common on locked-down networks) and confirm your n8n instance URL is reachable from Telegram.

How many support messages can this Gmail Telegram automation automation handle?

On a typical n8n Cloud plan, you can handle thousands of messages a month as long as you stay within your execution quota.

Is this Gmail Telegram automation automation better than using Zapier or Make?

Often, yes, because this is more than “if message then reply.” You’re combining multi-step logic, memory, a knowledge base lookup, and two-channel handling, and that complexity gets expensive (or awkward) in many no-code tools. n8n also gives you a self-hosted path, which matters once volume grows. Zapier or Make can still be fine for lightweight routing, especially if you don’t need conversation memory or sheet-driven knowledge retrieval. If you’re torn, Talk to an automation expert and you can sanity-check the best fit in a few minutes.

Set this up once and your support stops relying on heroics. The workflow handles the repetitive questions, keeps the story straight across Gmail and Telegram, and leaves you with logs you can actually use.

Need Help Setting This Up?

Our automation experts can build and customize this workflow for your specific needs. Free 15-minute consultation—no commitment required.

Lisa Granqvist

Workflow Automation Expert

Expert in workflow automation and no-code tools.

{
"id": "",
"meta": {
"instanceId": "241b1a872d71e7f6207ed076b2845bbfa2e81c58c68562c3895255f7f9e2fcef"
},
"name": "Automated Support Response Orchestrator",
"tags": [],
"nodes": [
{
"id": "flowpast-topbar-4474",
"name": "Flowpast Branding",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
20
],
"parameters": {
"color": 7,
"width": 1105,
"height": 80,
"content": "## Flowpast.com | Automation Workflow Library\n**\ud83d\udcd6 Full tutorial & setup guide:** flowpast.com"
},
"typeVersion": 1
},
{
"id": "47324b70-8be7-4e92-a739-2ff60f37d14a",
"name": "Telegram Incoming Trigger",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
990,
550
],
"webhookId": "customer-support-telegram",
"parameters": {
"updates": [
"message"
],
"additionalFields": []
},
"credentials": {
"telegramApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1.1
},
{
"id": "23ce0479-3ab0-4150-b893-3e08ed83fd73",
"name": "Map Telegram Payload",
"type": "n8n-nodes-base.set",
"position": [
755,
604
],
"parameters": {
"options": [],
"assignments": {
"assignments": [
{
"id": "channel",
"name": "channel",
"type": "string",
"value": "telegram"
},
{
"id": "customer_name",
"name": "customer_name",
"type": "string",
"value": "={{ $json.message.from.first_name }} {{ $json.message.from.last_name }}"
},
{
"id": "customer_id",
"name": "customer_id",
"type": "string",
"value": "={{ $json.message.from.id }}"
},
{
"id": "chat_id",
"name": "chat_id",
"type": "string",
"value": "={{ $json.message.chat.id }}"
},
{
"id": "message_content",
"name": "message_content",
"type": "string",
"value": "={{ $json.message.text }}"
},
{
"id": "message_id",
"name": "message_id",
"type": "string",
"value": "={{ $json.message.message_id }}"
},
{
"id": "subject",
"name": "subject",
"type": "string",
"value": "Customer Support Inquiry"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "686affeb-1afb-45cf-b9b0-f3ba6c6ffb94",
"name": "Telegram Support Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
535,
560
],
"parameters": {
"text": "={{ $json.message_content}}",
"options": {
"systemMessage": "You are a helpful and professional customer support AI assistant for Telegram inquiries. Your role is to:\n\n1. Understand customer inquiries and provide accurate, helpful responses\n2. Use the knowledge base tool to find relevant information\n3. Maintain a friendly, professional tone that matches the company brand\n4. If you cannot fully resolve an issue, escalate it appropriately\n5. Always aim to provide value and resolve customer concerns\n\nImportant guidelines:\n- Be empathetic and understanding\n- Provide clear, actionable responses\n- Use the customer's name when possible\n- If information is not in the knowledge base, say so honestly\n- For complex technical issues, recommend escalation to human support\n\nCompany context: You represent a professional service business focused on customer satisfaction and quality support via Telegram."
},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "a5e67d73-73c2-4756-9c82-9c05c1dbc36a",
"name": "Telegram Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
570,
710
],
"parameters": {
"options": {
"maxTokens": 100,
"temperature": 0.3
}
},
"credentials": {
"openAiApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1.1
},
{
"id": "bfa0f8a9-58cc-4c15-8d7e-d633c23e10a6",
"name": "Telegram Session Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
448,
734
],
"parameters": {
"sessionKey": "telegram_{{ $json.customer_id }}",
"sessionIdType": "customKey"
},
"typeVersion": 1.3
},
{
"id": "64a05368-29f5-4333-b881-b0ba73e424cb",
"name": "Dispatch Telegram Reply",
"type": "n8n-nodes-base.telegram",
"position": [
295,
574
],
"parameters": {
"text": "={{ $json.output }}",
"chatId": "={{ $('Map Telegram Payload').item.json.chat_id }}",
"additionalFields": {
"parse_mode": "Markdown",
"reply_to_message_id": "={{ $('Map Telegram Payload').item.json.message_id }}"
}
},
"credentials": {
"telegramApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1.2
},
{
"id": "64c36c02-b56d-45dd-b3bf-4f49b3e14b5c",
"name": "Gmail Inquiry Trigger",
"type": "n8n-nodes-base.gmailTrigger",
"position": [
1005,
216
],
"parameters": {
"filters": {
"labelIds": [
"INBOX",
"CATEGORY_PERSONAL"
],
"readStatus": "unread"
},
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
}
},
"credentials": {
"gmailOAuth2": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "baf01d18-d626-4b5c-bbc9-ac45c83b8e0b",
"name": "Map Gmail Payload",
"type": "n8n-nodes-base.set",
"position": [
778,
238
],
"parameters": {
"options": [],
"assignments": {
"assignments": [
{
"id": "channel",
"name": "channel",
"type": "string",
"value": "gmail"
},
{
"id": "customer_email",
"name": "customer_email",
"type": "string",
"value": "={{ $json[\"From\"].match(/<(.*?)>/)?.[1] || $json[\"From\"] }}"
},
{
"id": "customer_name",
"name": "customer_name",
"type": "string",
"value": "={{ $json[\"From\"].split(\" <\")[0] }}"
},
{
"id": "subject",
"name": "subject",
"type": "string",
"value": "={{ $json.Subject }}"
},
{
"id": "message_content",
"name": "message_content",
"type": "string",
"value": "={{ $json.text || $json.snippet }}"
},
{
"id": "message_id",
"name": "message_id",
"type": "string",
"value": "={{ $json.id }}"
},
{
"id": "thread_id",
"name": "thread_id",
"type": "string",
"value": "={{ $json.threadId }}"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "4d1c0b8a-9fed-4977-8ec4-91cb4460c2b6",
"name": "Gmail Support Agent",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
532,
216
],
"parameters": {
"text": "={{ $json.message_content}}",
"options": {
"systemMessage": "You are a helpful and professional customer support AI assistant for Email inquiries. Your role is to:\n\n1. Understand customer inquiries and provide accurate, helpful responses\n2. Use the knowledge base tool to find relevant information\n3. Maintain a friendly, professional tone that matches the company brand\n4. If you cannot fully resolve an issue, escalate it appropriately\n5. Always aim to provide value and resolve customer concerns\n\nImportant guidelines:\n- Be empathetic and understanding\n- Provide clear, actionable responses\n- Use the customer's name when possible\n- If information is not in the knowledge base, say so honestly\n- For complex technical issues, recommend escalation to human support\n- Format responses appropriately for email\n\nCompany context: You represent a professional service business focused on customer satisfaction and quality support via Email."
},
"promptType": "define"
},
"typeVersion": 1.7
},
{
"id": "8da4c0b1-86b7-436b-8d73-e96d3777be29",
"name": "Gmail Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
572,
364
],
"parameters": {
"options": {
"maxTokens": 1000,
"temperature": 0.3
}
},
"credentials": {
"openAiApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1.1
},
{
"id": "b4cb3e8b-3d5c-49fb-9cc2-f46ffe4cd683",
"name": "Gmail Session Memory",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
432,
384
],
"parameters": {
"sessionKey": "gmail_{{ $json.customer_email }}",
"sessionIdType": "customKey"
},
"typeVersion": 1.3
},
{
"id": "442e8879-e6c3-4cd6-8f3b-3f64879047c1",
"name": "Send Gmail Response",
"type": "n8n-nodes-base.gmail",
"position": [
290,
228
],
"webhookId": "c09e3c26-5430-4b47-864d-2344b636fa4e",
"parameters": {
"message": "={{ $json.output }}",
"options": {
"ccList": "",
"bccList": "",
"replyToSenderOnly": true
},
"messageId": "={{ $('Map Gmail Payload').item.json.message_id }}",
"operation": "reply"
},
"credentials": {
"gmailOAuth2": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 2
},
{
"id": "668afdd0-f68b-45cb-afde-93ebaf7627d3",
"name": "Flag Gmail Read",
"type": "n8n-nodes-base.gmail",
"position": [
52,
178
],
"webhookId": "3bae576f-ba6e-4ee2-a389-82171a9101d8",
"parameters": {
"messageId": "={{ $('Map Gmail Payload').item.json.message_id }}",
"operation": "markAsRead"
},
"credentials": {
"gmailOAuth2": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 2
},
{
"id": "2233ac1c-b704-4485-a4dd-3d873fb04538",
"name": "Record Gmail Interaction",
"type": "n8n-nodes-base.googleSheets",
"position": [
30,
314
],
"parameters": {
"columns": {
"value": {
"Status": "Completed",
"Channel": "Email",
"Timestamp": "={{ new Date().toISOString() }}",
"AI_Response": "={{ $('Gmail Support Agent').item.json.output }}",
"Customer_Name": "={{ $('Map Gmail Payload').item.json.customer_name }}",
"Response_Time": "={{ new Date().toISOString() }}",
"Inquiry_Subject": "={{ $json.subject || 'General Inquiry' }}",
"Customer_Contact": "={{ $('Map Gmail Payload').item.json.customer_email }}",
"Customer_Message": "={{ $('Map Gmail Payload').item.json.message_content }}"
},
"schema": [
{
"id": "Timestamp",
"type": "string",
"display": true,
"required": false,
"displayName": "Timestamp",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Channel",
"type": "string",
"display": true,
"required": false,
"displayName": "Channel",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Customer_Name",
"type": "string",
"display": true,
"required": false,
"displayName": "Customer_Name",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Customer_Contact",
"type": "string",
"display": true,
"required": false,
"displayName": "Customer_Contact",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Inquiry_Subject",
"type": "string",
"display": true,
"required": false,
"displayName": "Inquiry_Subject",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Customer_Message",
"type": "string",
"display": true,
"required": false,
"displayName": "Customer_Message",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "AI_Response",
"type": "string",
"display": true,
"required": false,
"displayName": "AI_Response",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Response_Time",
"type": "string",
"display": true,
"required": false,
"displayName": "Response_Time",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Status",
"type": "string",
"display": true,
"required": false,
"displayName": "Status",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": [],
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "AI_Responses"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "customer_support_knowledge_base"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.2
},
{
"id": "6e641113-9da3-430c-873d-59fd0c2997fb",
"name": "Record Telegram Interaction",
"type": "n8n-nodes-base.googleSheets",
"position": [
60,
644
],
"parameters": {
"columns": {
"value": {
"Status": "Completed",
"Channel": "={{ $('Map Telegram Payload').item.json.channel }}",
"Timestamp": "={{ new Date().toISOString() }}",
"AI_Response": "={{ $json.output }}",
"Customer_Name": "={{ $('Map Telegram Payload').item.json.customer_name }}",
"Response_Time": "={{ new Date().toISOString() }}",
"Inquiry_Subject": "={{ $('Map Telegram Payload').item.json.subject }}",
"Customer_Contact": "={{ $('Map Telegram Payload').item.json.customer_id }}",
"Customer_Message": "={{ $('Map Telegram Payload').item.json.message_content }}"
},
"schema": [
{
"id": "Timestamp",
"type": "string",
"display": true,
"required": false,
"displayName": "Timestamp",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Channel",
"type": "string",
"display": true,
"required": false,
"displayName": "Channel",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Customer_Name",
"type": "string",
"display": true,
"required": false,
"displayName": "Customer_Name",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Customer_Contact",
"type": "string",
"display": true,
"required": false,
"displayName": "Customer_Contact",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Inquiry_Subject",
"type": "string",
"display": true,
"required": false,
"displayName": "Inquiry_Subject",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Customer_Message",
"type": "string",
"display": true,
"required": false,
"displayName": "Customer_Message",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "AI_Response",
"type": "string",
"display": true,
"required": false,
"displayName": "AI_Response",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Response_Time",
"type": "string",
"display": true,
"required": false,
"displayName": "Response_Time",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "Status",
"type": "string",
"display": true,
"required": false,
"displayName": "Status",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "defineBelow",
"matchingColumns": [],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": [],
"operation": "append",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "AI_Responses"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "customer_support_knowledge_base"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.2
},
{
"id": "8634105f-1844-4e58-97f3-07697d86ac48",
"name": "Handle Error Trigger",
"type": "n8n-nodes-base.errorTrigger",
"position": [
220,
824
],
"parameters": [],
"typeVersion": 1
},
{
"id": "807781dc-c1ac-4bca-b298-420a3a3d5c2c",
"name": "Notify Admin on Error",
"type": "n8n-nodes-base.httpRequest",
"position": [
0,
846
],
"parameters": {
"url": "[CONFIGURE_YOUR_WEBHOOK]",
"method": "POST",
"options": [],
"sendBody": true,
"bodyParameters": {
"parameters": [
{
"name": "text",
"value": "\ud83d\udea8 Customer Support AI Error Alert\n\nWorkflow: Automated Support Response\nError: {{ $json.error.message }}\nNode: {{ $json.error.node.name }}\nTime: {{ new Date().toISOString() }}\n\nPlease check the workflow execution for details."
}
]
}
},
"typeVersion": 4.2
},
{
"id": "4581974a-7e7c-4b61-b5c7-a6023ef931d0",
"name": "Gmail Escalation Log",
"type": "n8n-nodes-base.googleSheetsTool",
"position": [
388,
134
],
"parameters": {
"options": [],
"sheetName": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "Customer_Inquiries"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "customer_support_knowledge_base"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.5
},
{
"id": "d9f13fc4-0a68-4bee-a36f-67e779bef7fe",
"name": "Knowledge Base Lookup",
"type": "n8n-nodes-base.googleSheetsTool",
"position": [
680,
120
],
"parameters": {
"options": [],
"sheetName": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "Knowledge_Base"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "customer_support_knowledge_base"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.5
},
{
"id": "dfaba1db-fc45-4c09-b83d-2413086f52d8",
"name": "Knowledge Base Lookup TG",
"type": "n8n-nodes-base.googleSheetsTool",
"position": [
675,
470
],
"parameters": {
"options": [],
"sheetName": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "Knowledge_Base"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "customer_support_knowledge_base"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.5
},
{
"id": "a79e16e6-409a-47b1-a7f9-60de7aac1700",
"name": "Telegram Escalation Log",
"type": "n8n-nodes-base.googleSheetsTool",
"position": [
410,
488
],
"parameters": {
"options": [],
"sheetName": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "Customer_Inquiries"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "customer_support_knowledge_base"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4.5
}
],
"active": false,
"pinData": [],
"settings": {
"executionOrder": "v1"
},
"versionId": "",
"connections": {
"Knowledge Base Lookup": {
"ai_tool": [
[
{
"node": "Gmail Support Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Knowledge Base Lookup TG": {
"ai_tool": [
[
{
"node": "Telegram Support Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Gmail Session Memory": {
"ai_memory": [
[
{
"node": "Gmail Support Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Handle Error Trigger": {
"main": [
[
{
"node": "Notify Admin on Error",
"type": "main",
"index": 0
}
]
]
},
"Gmail Support Agent": {
"main": [
[
{
"node": "Send Gmail Response",
"type": "main",
"index": 0
}
]
]
},
"Telegram Session Memory": {
"ai_memory": [
[
{
"node": "Telegram Support Agent",
"type": "ai_memory",
"index": 0
}
]
]
},
"Send Gmail Response": {
"main": [
[
{
"node": "Flag Gmail Read",
"type": "main",
"index": 0
},
{
"node": "Record Gmail Interaction",
"type": "main",
"index": 0
}
]
]
},
"Telegram Support Agent": {
"main": [
[
{
"node": "Dispatch Telegram Reply",
"type": "main",
"index": 0
}
]
]
},
"Gmail Escalation Log": {
"ai_tool": [
[
{
"node": "Gmail Support Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Dispatch Telegram Reply": {
"main": [
[
{
"node": "Record Telegram Interaction",
"type": "main",
"index": 0
}
]
]
},
"Telegram Escalation Log": {
"ai_tool": [
[
{
"node": "Telegram Support Agent",
"type": "ai_tool",
"index": 0
}
]
]
},
"Map Gmail Payload": {
"main": [
[
{
"node": "Gmail Support Agent",
"type": "main",
"index": 0
}
]
]
},
"Map Telegram Payload": {
"main": [
[
{
"node": "Telegram Support Agent",
"type": "main",
"index": 0
}
]
]
},
"Gmail Chat Model": {
"ai_languageModel": [
[
{
"node": "Gmail Support Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Telegram Chat Model": {
"ai_languageModel": [
[
{
"node": "Telegram Support Agent",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Gmail Inquiry Trigger": {
"main": [
[
{
"node": "Map Gmail Payload",
"type": "main",
"index": 0
}
]
]
},
"Telegram Incoming Trigger": {
"main": [
[
{
"node": "Map Telegram Payload",
"type": "main",
"index": 0
}
]
]
}
}
}