January 22, 2026

Gmail to Slack, urgent emails surfaced fast

Lisa Granqvist Partner Workflow Automation Expert

Get a free AI assessment → ⬇️ Use template

Your inbox is not your ticketing system. But it quietly becomes one the second customers, partners, and internal teams start emailing “quick requests” that turn into real work.

Support leads feel it first. Then ops managers trying to keep requests moving, plus marketers watching inbound leads. Gmail Slack automation fixes the messy middle by pulling out the important emails, summarizing them, and pushing the right alert into Slack before it gets buried.

This guide walks you through what the workflow does, what you need to run it, and how to adapt it so urgent messages get handled fast (without living in your inbox).

How This Automation Works

Here’s the complete workflow you’ll be setting up:

n8n Workflow Template: Gmail to Slack, urgent emails surfaced fast

Click to explore

flowchart LR

    subgraph sg0["Gmail Intake Flow"]
        direction LR
        n0@{ icon: "mdi:play-circle", form: "rounded", label: "Gmail Intake Trigger", pos: "b", h: 48 }
        n1["<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/code.svg' width='40' height='40' /></div><br/>Derive Email Details"]
        n2@{ icon: "mdi:swap-horizontal", form: "rounded", label: "Validate Attachment Presence", pos: "b", h: 48 }
        n3["<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/code.svg' width='40' height='40' /></div><br/>Handle Attachment Data"]
        n4["<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/code.svg' width='40' height='40' /></div><br/>Bypass Attachment Handling"]
        n5@{ icon: "mdi:robot", form: "rounded", label: "Structured Result Parser", pos: "b", h: 48 }
        n6@{ icon: "mdi:brain", form: "rounded", label: "Azure Chat Model", pos: "b", h: 48 }
        n7@{ icon: "mdi:memory", form: "rounded", label: "Context Memory Buffer", pos: "b", h: 48 }
        n8@{ icon: "mdi:robot", form: "rounded", label: "AI Email Analyst", pos: "b", h: 48 }
        n9["<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/code.svg' width='40' height='40' /></div><br/>Interpret AI Output"]
        n10@{ icon: "mdi:swap-horizontal", form: "rounded", label: "Urgency Branch Check", pos: "b", h: 48 }
        n11@{ icon: "mdi:swap-horizontal", form: "rounded", label: "Attachment Route Check", pos: "b", h: 48 }
        n12["<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/slack.svg' width='40' height='40' /></div><br/>Urgent Slack Alert"]
        n13["<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/slack.svg' width='40' height='40' /></div><br/>Attachment Slack Alert"]
        n14["<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/slack.svg' width='40' height='40' /></div><br/>General Slack Notice"]
        n15["<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/code.svg' width='40' height='40' /></div><br/>Prepare Sheet Payload"]
        n16@{ icon: "mdi:database", form: "rounded", label: "Append to Google Sheet", pos: "b", h: 48 }
        n15 --> n16
        n8 --> n9
        n10 --> n12
        n10 --> n11
        n12 --> n15
        n0 --> n1
        n14 --> n15
        n7 -.-> n8
        n4 --> n8
        n2 --> n3
        n2 --> n4
        n9 --> n10
        n11 --> n13
        n11 --> n14
        n13 --> n15
        n1 --> n2
        n3 --> n8
        n6 -.-> n8
        n5 -.-> n8
    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 n0 trigger
    class n5,n8 ai
    class n6 aiModel
    class n7 ai
    class n2,n10,n11 decision
    class n16 database
    class n1,n3,n4,n9,n15 code
    classDef customIcon fill:none,stroke:none
    class n1,n3,n4,n9,n12,n13,n14,n15 customIcon

Why This Matters: Email Triage Turns Into Hidden Work

Most teams don’t miss important emails because they’re careless. They miss them because the signal is mixed into a steady stream of receipts, threads, CC noise, “quick questions,” and messages that look harmless until they’re suddenly urgent. So you skim. You flag things. You promise yourself you’ll come back later. Then Slack pings, a meeting starts, and the email disappears into page two of your inbox where nothing good happens. It’s mentally exhausting, and it steals attention from actual work.

It adds up fast. Here’s where the friction usually shows up day to day.

Important requests sit unread because “I’ll check email after this call” becomes three calls.
Manual forwarding to Slack is inconsistent, so teammates don’t trust what they see there.
Someone ends up copying details into a sheet anyway, usually late and with mistakes.
Attachments create a second problem because you need context plus a file, not just a subject line.

What You’ll Build: Gmail Intelligence That Routes to Slack and Logs to Sheets

This workflow watches your Gmail inbox for new or unread messages, pulls out the parts you actually care about (sender, subject, body, and attachment context), then asks GPT-4 to classify the intent and urgency in plain language. After the AI analysis, the workflow branches. If it’s urgent, it posts a higher-priority Slack alert. If there’s an attachment, it can use a dedicated route so the team knows a file is involved. Everything, urgent or not, gets logged into Google Sheets in a structured way so you can track trends, response performance, or recurring request types. And if something breaks (bad credentials, API issues, parsing problems), the error path notifies you so failures don’t silently pile up.

The flow starts with a Gmail trigger, then a short “prep” stage that extracts and cleans the email content for analysis. GPT-4 returns structured intent and urgency, Slack gets the right message, and Google Sheets becomes your lightweight audit trail.

What You’re Building

What Gets Automated

What You’ll Achieve

New or unread Gmail messages get captured automatically using a search filter.
Email fields are extracted and cleaned so the AI receives usable context.
GPT-4 classifies intent and urgency, then outputs a structured result you can trust.
Slack notifications branch based on urgency and attachment presence.

Most teams get about 5 hours back each week by removing manual triage.
Urgent emails surface in Slack in near real time, so nothing “waits until later.”
Your team sees consistent summaries instead of long forwarded threads.
Google Sheets becomes a simple reporting layer for volume and intent trends.
Error alerts make failures obvious, which prevents silent inbox drift.

Expected Results

Say your shared inbox gets about 40 meaningful emails a day. If a person spends only 3 minutes reading, deciding urgency, forwarding to Slack, and logging a row, that’s roughly 2 hours daily. With this workflow, the “human time” becomes a quick scan of Slack alerts plus responding to the truly urgent ones, which is often 15 minutes total. The AI and logging run in the background, so you get most of that time back without losing visibility.

Before You Start

n8n instance (try n8n Cloud free)
Self-hosting option if you prefer (Hostinger works well)
Gmail for monitoring unread or new inbox messages
Slack to post alerts into a channel
Google Sheets to store a structured email log
OpenAI or Azure OpenAI API key (get it from your OpenAI or Azure portal)

Skill level: Intermediate. You’ll connect OAuth credentials, set a Gmail filter, and paste IDs for Slack and Sheets.

Want someone to build this for you? Talk to an automation expert (free 15-minute consultation).

Step by Step

Gmail triggers the run. The workflow starts when a new email lands (or matches your unread filter), so you’re not relying on someone to remember to check the inbox.

The email gets turned into clean input. It extracts sender, subject, and body text, then handles attachments differently when needed so the analysis includes the right context.

GPT-4 classifies intent and urgency. An AI agent analyzes the message and returns a structured result (summary, intent label, urgency tag) that the workflow can reliably branch on.

Slack and Sheets receive the output. Urgent items go to a dedicated Slack alert path, attachment-related emails can be highlighted, and every processed message is appended to Google Sheets for tracking.

You can easily modify the Gmail search filter to match your team’s inbox rules. See the full implementation guide below for customization options.

Step-by-Step Implementation Guide

Step 1: Configure the Gmail Trigger

Set up the workflow to listen for new emails and pull full message content.

Add and open Gmail Intake Trigger.
Set Poll Times to everyMinute.
Credential Required: Connect your gmailOAuth2 credentials.

Step 2: Configure Email Parsing and Attachment Routing

Extract structured email fields and route messages based on attachment presence.

In Derive Email Details, keep the JavaScript logic as provided to extract sender, subject, bodyForAnalysis, and hasAttachments.
Open Validate Attachment Presence and confirm the boolean conditions reference {{ $json.hasAttachments }} for both checks.
Leave Handle Attachment Data and Bypass Attachment Handling scripts intact; they normalize attachment data and create combinedContent.

⚠️ Common Pitfall: If your Gmail data uses different fields for attachments, update the parsing in Derive Email Details to match your payload structure.

Step 3: Set Up AI Analysis and Parsing

Configure the AI agent to analyze email content and return structured JSON output.

Open AI Email Analyst and set Text to {{ $json.subject }},{{ $json.bodyForAnalysis }}{{ $json.bodyHtml }}{{ $json.links }}.
Confirm Prompt Type is define and Has Output Parser is enabled.
Open Azure Chat Model and set Model to gpt-4o.
Credential Required: Connect your azureOpenAiApi credentials in Azure Chat Model.
Configure Structured Result Parser with the JSON schema example provided.
Configure Context Memory Buffer with Session Key set to "json_review" and Context Window Length set to 7.

Structured Result Parser and Context Memory Buffer are AI sub-nodes connected to AI Email Analyst; ensure credentials are added to Azure Chat Model, not these sub-nodes.

Step 4: Configure AI Output Interpretation and Routing

Normalize the AI response and branch to the correct notification path.

Keep Interpret AI Output as-is to parse multiple response formats and standardize aiAnalysis.
In Urgency Branch Check, verify the condition checks {{ $json.aiAnalysis.callToAction }} equals Reply Needed.
In Attachment Route Check, verify the condition checks {{ $json.aiAnalysis.callToAction }} equals Review Attachment.

Step 5: Configure Slack Notifications

Send formatted alerts to the correct Slack channels for urgent, attachment, or general messages.

Open Urgent Slack Alert and confirm Text uses the provided template with expressions like {{ $('Derive Email Details').item.json.subject }}.
Open Attachment Slack Alert and confirm Text includes links using {{ $json.output.links }}.
Open General Slack Notice and confirm the summary and action placeholders reference {{ $json.aiAnalysis.summary }} and {{ $json.aiAnalysis.callToAction }}.
Credential Required: Connect your slackApi credentials for Urgent Slack Alert, Attachment Slack Alert, and General Slack Notice.
Update each Slack node Channel to the correct destination for your team.

⚠️ Common Pitfall: If Slack channel IDs are left as [YOUR_ID], messages will fail. Replace with real channel IDs.

Step 6: Configure Google Sheets Logging

Capture essential data from Slack notifications and append it to a tracking sheet.

Review Prepare Sheet Payload to confirm it extracts sender, subject, ai_summary, action_required, and slack_channel from the Slack text.
Open Append to Google Sheet and set Operation to appendOrUpdate.
Select your Document ID and Sheet Name for the email log.
Credential Required: Connect your googleSheetsOAuth2Api credentials.

Step 7: Test and Activate Your Workflow

Validate the end-to-end flow and confirm notifications and logging work as expected.

Use Gmail Intake Trigger to trigger a manual test by sending a sample email to the monitored inbox.
Confirm the message flows through Derive Email Details → AI Email Analyst → Interpret AI Output → routing checks.
Verify the correct Slack node fires (Urgent Slack Alert, Attachment Slack Alert, or General Slack Notice).
Check that Append to Google Sheet logs a new row with the expected fields.
Activate the workflow by switching it to Active once tests succeed.

🔒

Unlock Full Step-by-Step Guide

Get the complete implementation guide + downloadable template

Troubleshooting Tips

Gmail credentials can expire or need specific permissions. If things break, check the Gmail OAuth connection in n8n’s Credentials first, then confirm the inbox scope is allowed.
If you’re using Wait nodes or external rendering, processing times vary. Bump up the wait duration if downstream nodes fail on empty responses.
Slack alerts often “fail” because the bot can’t post to that channel yet. Confirm your Slack app has chat:write, invite the bot to the channel, and re-check the channel ID inside the Slack node.

Quick Answers

What’s the setup time for this Gmail Slack automation automation?

About 30 minutes if your Gmail, Slack, and Sheets accounts are ready.

Is coding required for this Gmail Slack automation?

No. You’ll mostly connect accounts and paste in a few IDs (like the Slack channel and Sheet).

Is n8n free to use for this Gmail Slack 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/Azure OpenAI usage, which is usually a few cents per email for GPT-4-level analysis.

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 modify this Gmail Slack automation workflow for different use cases?

Yes, and you should. You can adjust the Gmail Trigger filter (for example, only messages to a shared inbox label), tune the AI Email Analyst instructions to match your categories, and change the Urgency Branch Check rules so “urgent” reflects your business. Many teams also tweak the Google Sheets columns in the Prepare Sheet Payload step to match internal reporting.

Why is my Gmail connection failing in this workflow?

Usually it’s expired OAuth or the wrong Gmail account connected. Reconnect the Gmail credential in n8n, then confirm the workflow has permission to read the inbox you actually monitor. If you changed the search query, test it in Gmail first because a bad filter can look like “no emails found.”

What volume can this Gmail Slack automation workflow process?

On a typical n8n Cloud plan, handling a few thousand emails a month is normal. If you self-host, you’re mainly limited by your server and your AI API rate limits, not n8n executions. The practical ceiling is usually the model throughput plus how many emails arrive at once. If your inbox spikes (campaign launches, incident days), add a queueing approach or reduce how much text you send to the model.

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

Often, yes, because this workflow relies on branching logic (urgent vs attachment vs general), structured AI output parsing, and a clean error path. n8n also gives you the self-hosting option, which is handy when email volume grows and per-task pricing gets annoying. Zapier or Make can still be fine if your needs are basic, like “email comes in, post to Slack.” The moment you want consistent intent labels and an audit log in Google Sheets, complexity creeps in. Talk to an automation expert if you want help choosing.

Once this is running, your inbox stops being a hiding place for urgent work. Slack gets the signal, Google Sheets keeps the record, and you spend your attention where it actually pays off.

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": "53236b01c74d284eb014a6043ebeb1d9756a75f35ce06c125cd0c70e002fcbd4",
"templateCredsSetupCompleted": null,
"templateId": null
},
"name": "Automated Email Triage Workflow",
"tags": [],
"nodes": [
{
"id": "flowpast-topbar-9680",
"name": "Flowpast Branding",
"type": "n8n-nodes-base.stickyNote",
"position": [
0,
20
],
"parameters": {
"color": 7,
"width": 1838,
"height": 80,
"content": "## Flowpast.com | Automation Workflow Library\n**\ud83d\udcd6 Full tutorial & setup guide:** flowpast.com"
},
"typeVersion": 1
},
{
"id": "0165f79d-f529-425c-8b1c-acdb665c4e04",
"name": "Gmail Intake Trigger",
"type": "n8n-nodes-base.gmailTrigger",
"position": [
1738,
270
],
"parameters": {
"simple": false,
"filters": [],
"options": [],
"pollTimes": {
"item": [
{
"mode": "everyMinute"
}
]
}
},
"credentials": {
"gmailOAuth2": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "ad5d0c60-0851-4084-89b8-29f93541cba9",
"name": "Derive Email Details",
"type": "n8n-nodes-base.code",
"position": [
1177,
340
],
"parameters": {
"jsCode": "const emailData = items[0].json;\n\nconst extractedData = {\n  sender: emailData.from || 'Unknown Sender',\n  subject: emailData.subject || 'No Subject',\n  bodyText: emailData.textPlain || emailData.text || '',\n  bodyHtml: emailData.html || '',\n  attachments: emailData.attachments || [],\n  messageId: emailData.id,\n  receivedDate: emailData.date || new Date().toISOString(),\n  threadId: emailData.threadId\n};\n\nconst linkRegex = /https?:\\/\\/[^\\s<>\"{}|\\\\^`\\[\\]]+/gi;\nconst textLinks = (extractedData.bodyText.match(linkRegex) || []);\nconst htmlLinks = (extractedData.bodyHtml.match(linkRegex) || []);\nconst allLinks = [...new Set([...textLinks, ...htmlLinks])];\n\nextractedData.links = allLinks;\n\n// ENHANCED ATTACHMENT DETECTION LOGIC\nlet attachmentCount = 0;\nlet hasAttachments = false;\n\n// Check the original attachments array first\nif (extractedData.attachments && extractedData.attachments.length > 0) {\n  attachmentCount = extractedData.attachments.length;\n  hasAttachments = true;\n}\n\n// Check Gmail payload parts for attachments\nif (!hasAttachments && emailData.payload && emailData.payload.parts) {\n  const attachmentParts = emailData.payload.parts.filter(part => \n    part.filename && part.filename !== '' && part.body && part.body.attachmentId\n  );\n  if (attachmentParts.length > 0) {\n    attachmentCount = attachmentParts.length;\n    hasAttachments = true;\n  }\n}\n\n// Check content-type header for multipart/mixed (indicates attachments)\nif (!hasAttachments && emailData.headers && emailData.headers['content-type']) {\n  const contentType = emailData.headers['content-type'];\n  if (contentType.includes('multipart/mixed')) {\n    hasAttachments = true;\n    attachmentCount = 1; // At least one attachment\n  }\n}\n\n// Check email content for attachment keywords as final fallback\nif (!hasAttachments) {\n  const emailText = (extractedData.bodyText + ' ' + extractedData.bodyHtml).toLowerCase();\n  const attachmentKeywords = ['attached', 'attachment', 'please review the attached', 'pdf', 'excel', 'document'];\n  \n  if (attachmentKeywords.some(keyword => emailText.includes(keyword))) {\n    hasAttachments = true;\n    attachmentCount = 1;\n  }\n}\n\nextractedData.hasAttachments = hasAttachments;\nextractedData.attachmentCount = attachmentCount;\n\nconst bodyForAnalysis = extractedData.bodyText || extractedData.bodyHtml.replace(/<[^>]*>/g, ' ').replace(/\\s+/g, ' ').trim();\nextractedData.bodyForAnalysis = bodyForAnalysis.substring(0, 3000);\n\nreturn [{ json: extractedData }];"
},
"typeVersion": 2
},
{
"id": "0a775b80-163e-4048-8fd3-01ab020a3d2a",
"name": "Validate Attachment Presence",
"type": "n8n-nodes-base.if",
"position": [
836,
280
],
"parameters": {
"options": [],
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "or",
"conditions": [
{
"id": "has-attachments",
"operator": {
"type": "boolean",
"operation": "equal"
},
"leftValue": "={{ $json.hasAttachments }}",
"rightValue": true
},
{
"id": "bdea6274-0c71-4d15-b97d-8cd325208efe",
"operator": {
"type": "boolean",
"operation": "true",
"singleValue": true
},
"leftValue": "={{ $json.hasAttachments }}",
"rightValue": 0
}
]
}
},
"typeVersion": 2
},
{
"id": "60bdd6dc-2c09-4e41-bd24-2d191827cfde",
"name": "Handle Attachment Data",
"type": "n8n-nodes-base.code",
"position": [
286,
475
],
"parameters": {
"jsCode": "const emailData = items[0].json;\nlet attachmentText = '';\nconst processedAttachments = [];\n\nif (emailData.attachments && emailData.attachments.length > 0) {\n  for (const attachment of emailData.attachments) {\n    const processed = {\n      filename: attachment.filename || 'unknown',\n      contentType: attachment.contentType || 'unknown',\n      size: attachment.size || 0,\n      textExtracted: false,\n      extractedText: ''\n    };\n    \n    if (attachment.contentType) {\n      if (attachment.contentType.includes('text/')) {\n        processed.extractedText = 'Text file content available';\n        processed.textExtracted = true;\n      } else if (attachment.contentType.includes('pdf')) {\n        processed.extractedText = 'PDF attachment detected - text extraction requires additional service';\n        processed.textExtracted = false;\n      } else if (attachment.contentType.includes('word') || attachment.contentType.includes('document')) {\n        processed.extractedText = 'Word document detected - text extraction requires additional service';\n        processed.textExtracted = false;\n      }\n    }\n    \n    processedAttachments.push(processed);\n    \n    if (processed.textExtracted) {\n      attachmentText += `\\n[Attachment: ${processed.filename}] ${processed.extractedText}`;\n    }\n  }\n}\n\nconst combinedContent = emailData.bodyForAnalysis + attachmentText;\n\nreturn [{\n  json: {\n    ...emailData,\n    processedAttachments,\n    combinedContent: combinedContent.substring(0, 4000),\n    attachmentProcessingComplete: true\n  }\n}];"
},
"typeVersion": 2
},
{
"id": "cabfad79-67be-4fb5-83ca-a22b73275101",
"name": "Bypass Attachment Handling",
"type": "n8n-nodes-base.code",
"position": [
1030,
450
],
"parameters": {
"jsCode": "const emailData = items[0].json;\n\nreturn [{\n  json: {\n    ...emailData,\n    processedAttachments: [],\n    combinedContent: emailData.bodyForAnalysis,\n    attachmentProcessingComplete: true\n  }\n}];"
},
"typeVersion": 2
},
{
"id": "93b2c1f4-b532-4102-aef9-42fd0192b6ba",
"name": "Structured Result Parser",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1040,
160
],
"parameters": {
"jsonSchemaExample": "{\n  \"summary\": \"string\",\n  \"callToAction\": \"Reply Needed | Review Attachment | For Your Information\",\n  \"insights\": \"string\",\n  \"links\": [\"string\"],\n  \"attachments\": [\"string\"]\n}\n"
},
"typeVersion": 1.3
},
{
"id": "80a7ba77-5601-4a8b-a45d-5dea98b1d112",
"name": "Azure Chat Model",
"type": "@n8n/n8n-nodes-langchain.lmChatAzureOpenAi",
"position": [
1705,
120
],
"parameters": {
"model": "gpt-4o",
"options": []
},
"credentials": {
"azureOpenAiApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 1
},
{
"id": "c9b3832f-eef9-4c7f-a7a0-b5585cf5b610",
"name": "Context Memory Buffer",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
900,
170
],
"parameters": {
"sessionKey": "\"json_review\"",
"sessionIdType": "customKey",
"contextWindowLength": 7
},
"typeVersion": 1.3
},
{
"id": "5a329a24-6335-4f09-aed3-c410023c520d",
"name": "AI Email Analyst",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
1276,
470
],
"parameters": {
"text": "={{ $json.subject }},{{ $json.bodyForAnalysis }}{{ $json.bodyHtml }}{{ $json.links }}",
"options": {
"systemMessage": "=You are an AI email assistant. Analyze the provided email content (subject, body text, HTML, and links) and return a structured JSON with the following fields:\n\n- summary: A concise plain text summary of the email.\n- callToAction: Choose one of [\"Reply Needed\", \"Review Attachment\", \"For Your Information\"] based on the email\u2019s intent.\n- insights: Key points, deadlines, or important notes mentioned in the email.\n- links: Extract all valid links from the email content. If none are present, return an empty array [].\n- attachments: If attachments are mentioned in the text, list them as [\"PDF\", \"Excel\", \"Word\"] or return [].\n\nAlways respond with valid JSON only.\n"
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 2.1
},
{
"id": "8a4771ff-2e1f-4411-9b7f-7c57b663494e",
"name": "Interpret AI Output",
"type": "n8n-nodes-base.code",
"position": [
935,
620
],
"parameters": {
"jsCode": "// Parse AI response and handle the actual output structure\nlet aiData;\ntry {\n  // Get the AI response - handle multiple possible structures\n  let aiResponse;\n  \n  // Check if it's the direct output structure you showed\n  if (items[0].json.output) {\n    aiResponse = items[0].json.output;\n  }\n  // Check for standard OpenAI response formats\n  else if (items[0].json.message?.content) {\n    const content = items[0].json.message.content;\n    // Try to parse JSON from content\n    const jsonMatch = content.match(/\\{[\\s\\S]*\\}/);\n    if (jsonMatch) {\n      aiResponse = JSON.parse(jsonMatch[0]);\n    } else {\n      aiResponse = content;\n    }\n  }\n  // Check for other possible response formats\n  else if (items[0].json.text) {\n    const text = items[0].json.text;\n    const jsonMatch = text.match(/\\{[\\s\\S]*\\}/);\n    if (jsonMatch) {\n      aiResponse = JSON.parse(jsonMatch[0]);\n    } else {\n      aiResponse = text;\n    }\n  }\n  // Check if the response is directly in the json\n  else if (items[0].json.summary || items[0].json.callToAction || items[0].json.insights) {\n    aiResponse = items[0].json;\n  }\n  else {\n    throw new Error('Unknown AI response format');\n  }\n  \n  // Now handle the parsed response\n  if (typeof aiResponse === 'object' && aiResponse.summary) {\n    // Direct object format (like your output)\n    aiData = {\n      summary: aiResponse.summary || 'AI analysis unavailable',\n      callToAction: aiResponse.callToAction || 'For Your Information',\n      insights: aiResponse.insights || 'No specific insights available'\n    };\n  } else if (typeof aiResponse === 'string') {\n    // String format - try to parse JSON\n    const jsonMatch = aiResponse.match(/\\{[\\s\\S]*\\}/);\n    if (jsonMatch) {\n      const parsed = JSON.parse(jsonMatch[0]);\n      aiData = {\n        summary: parsed.summary || 'AI analysis unavailable',\n        callToAction: parsed.callToAction || 'For Your Information',\n        insights: parsed.insights || 'No specific insights available'\n      };\n    } else {\n      throw new Error('Could not extract JSON from AI response');\n    }\n  } else {\n    throw new Error('Unexpected AI response format');\n  }\n  \n  // Validate and clean up the data\n  if (!aiData.summary) aiData.summary = 'AI analysis unavailable';\n  if (!aiData.callToAction) aiData.callToAction = 'For Your Information';\n  if (!aiData.insights) aiData.insights = 'No specific insights available';\n  \n  // Ensure callToAction is one of the expected values\n  const validActions = ['Reply Needed', 'Review Attachment', 'For Your Information'];\n  if (!validActions.includes(aiData.callToAction)) {\n    aiData.callToAction = 'For Your Information';\n  }\n  \n} catch (error) {\n  // Fallback if AI parsing fails\n  aiData = {\n    summary: 'Email received but AI analysis failed. Please review manually.',\n    callToAction: 'For Your Information',\n    insights: 'Manual review required due to AI processing error.',\n    aiError: true,\n    aiErrorMessage: error.message\n  };\n}\n\n// Get the original email data from the previous node\n// Try multiple node references in case the node name is different\nlet emailData;\ntry {\n  emailData = $node['AI Email Analyst'].json || $input.first().json;\n} catch (e) {\n  // Fallback to items[0].json if node reference fails\n  emailData = items[0].json;\n}\n\n// Return the processed data\nreturn [{\n  json: {\n    ...emailData,\n    aiAnalysis: aiData,\n    processingComplete: true,\n    timestamp: new Date().toISOString()\n  }\n}];"
},
"typeVersion": 2
},
{
"id": "e654bdf6-3782-4220-ade3-19bf09294e2a",
"name": "Urgency Branch Check",
"type": "n8n-nodes-base.if",
"position": [
319,
655
],
"parameters": {
"options": [],
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "reply-needed",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.aiAnalysis.callToAction }}",
"rightValue": "Reply Needed"
}
]
}
},
"typeVersion": 2
},
{
"id": "1a1f32a6-67f2-4bb4-92b1-3c0e6b6c40ee",
"name": "Attachment Route Check",
"type": "n8n-nodes-base.if",
"position": [
0,
625
],
"parameters": {
"options": [],
"conditions": {
"options": {
"version": 1,
"leftValue": "",
"caseSensitive": true,
"typeValidation": "strict"
},
"combinator": "and",
"conditions": [
{
"id": "review-attachment",
"operator": {
"type": "string",
"operation": "equals"
},
"leftValue": "={{ $json.aiAnalysis.callToAction }}",
"rightValue": "Review Attachment"
}
]
}
},
"typeVersion": 2
},
{
"id": "7f338c68-740c-48b0-9776-c57bd4707d60",
"name": "Urgent Slack Alert",
"type": "n8n-nodes-base.slack",
"position": [
540,
815
],
"webhookId": "4e77062d-a1d4-46ca-8d70-1a3bf3beaa71",
"parameters": {
"text": "=\ud83d\udea8 URGENT EMAIL REQUIRES REPLY\n\n*From:* {{ $('Derive Email Details').item.json.sender.value[0].address }}\n*Subject:* {{ $('Derive Email Details').item.json.subject }}\n*Received:* {{ $('Derive Email Details').item.json.receivedDate }}\n\n*AI Summary:*\n{{ $json.aiAnalysis.summary }}\n\n*Action Required:* {{ $json.aiAnalysis.callToAction }}\n*Insights:* {{ $json.aiAnalysis.insights }}\n",
"select": "channel",
"channelId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultName": "reply-needed"
},
"otherOptions": []
},
"credentials": {
"slackApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 2
},
{
"id": "09091b5d-fbae-4fb4-b23c-077a7b59d36f",
"name": "Attachment Slack Alert",
"type": "n8n-nodes-base.slack",
"position": [
240,
880
],
"webhookId": "9e25a820-c2f1-4639-91ad-aa55a1a2d976",
"parameters": {
"text": "=\ud83d\udcce EMAIL WITH ATTACHMENTS TO REVIEW\n\n*From:* {{ $('Derive Email Details').item.json.sender.value[0].address }}\n*Subject:* {{ $('Derive Email Details').item.json.subject }}\n*Received:* {{ $('Derive Email Details').item.json.receivedDate }}\n\n*AI Summary:*\n{{ $json.aiAnalysis.summary }}\n\n*Action Required:* {{ $json.aiAnalysis.callToAction }}\n*Insights:* {{ $json.aiAnalysis.insights }} \n\n*Links* {{ $json.output.links }}\n\n\n",
"select": "channel",
"channelId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultName": "review-needed"
},
"otherOptions": []
},
"credentials": {
"slackApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 2
},
{
"id": "e752f272-dc3f-4e8b-a9c7-729cfd1a9862",
"name": "General Slack Notice",
"type": "n8n-nodes-base.slack",
"position": [
748,
830
],
"webhookId": "4f99f77b-98ab-4dd9-b6c2-c4284c6ebfbe",
"parameters": {
"text": "=\ud83d\udce7 EMAIL FOR YOUR INFORMATION\n\n*From:* {{ $('Derive Email Details').item.json.sender.value[0].address }}\n*Subject:* {{ $('Derive Email Details').item.json.subject }}\n*Received:* {{ $('Derive Email Details').item.json.receivedDate }}\n\n*AI Summary:*\n{{ $json.aiAnalysis.summary }}\n\n*Action Required:* {{ $json.aiAnalysis.callToAction }}\n*Insights:* {{ $json.aiAnalysis.insights }} ",
"select": "channel",
"channelId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultName": "general-information"
},
"otherOptions": []
},
"credentials": {
"slackApi": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 2
},
{
"id": "e8db91ad-dbbf-47de-9ad0-c632909dc1ad",
"name": "Prepare Sheet Payload",
"type": "n8n-nodes-base.code",
"position": [
1331,
840
],
"parameters": {
"jsCode": "// Format only essential data for Google Sheets logging\nconst slackResponse = items[0].json;\nconst slackMessage = slackResponse.message || {};\nconst messageText = slackMessage.text || '';\n\n// Extract key information from Slack message\nconst fromMatch = messageText.match(/\\*From:\\*\\s*(?:<mailto:([^|>]+)\\|([^>]+)>|([^\\n*]+))/);\nconst subjectMatch = messageText.match(/\\*Subject:\\*\\s*([^\\n*]+)/);\nconst summaryMatch = messageText.match(/\\*AI Summary:\\*\\s*([\\s\\S]*?)(?=\\n\\n\\*|\\n\\*|$)/);\nconst actionMatch = messageText.match(/\\*Action Required:\\*\\s*([^\\n*]+)/);\n\n// Determine channel based on message content\nlet channelName = '#general';\nif (messageText.includes('URGENT EMAIL REQUIRES REPLY')) {\n  channelName = '#urgent';\n} else if (messageText.includes('EMAIL WITH ATTACHMENTS')) {\n  channelName = '#attachments';\n}\n\n// Check for attachments\nconst hasAttachments = messageText.includes('\ud83d\udcce') || messageText.includes('Attachments');\n\n// Essential data only (6-7 columns)\nconst essentialData = {\n  timestamp: new Date().toISOString(),\n  sender: fromMatch?.[1] || fromMatch?.[2] || fromMatch?.[3] || 'Unknown',\n  subject: subjectMatch?.[1]?.trim() || 'Unknown',\n  ai_summary: summaryMatch?.[1]?.trim().replace(/\\n/g, ' ').substring(0, 200) || 'No summary',\n  action_required: actionMatch?.[1]?.trim() || 'For Your Information',\n  slack_channel: channelName,\n  has_attachments: hasAttachments\n};\n\nreturn [{\n  json: essentialData\n}];"
},
"typeVersion": 2
},
{
"id": "87dededf-da46-4af9-9537-5a837f8bc3f8",
"name": "Append to Google Sheet",
"type": "n8n-nodes-base.googleSheets",
"position": [
1650,
805
],
"parameters": {
"columns": {
"value": [],
"schema": [
{
"id": "timestamp",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "timestamp",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "sender",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "sender",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "subject",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "subject",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "ai_summary",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "ai_summary",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "action_required",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "action_required",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "slack_channel",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "slack_channel",
"defaultMatch": false,
"canBeUsedToMatch": true
},
{
"id": "has_attachments",
"type": "string",
"display": true,
"removed": false,
"required": false,
"displayName": "has_attachments",
"defaultMatch": false,
"canBeUsedToMatch": true
}
],
"mappingMode": "autoMapInputData",
"matchingColumns": [
"id"
],
"attemptToConvertTypes": false,
"convertFieldsToString": false
},
"options": [],
"operation": "appendOrUpdate",
"sheetName": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "Sheet1"
},
"documentId": {
"__rl": true,
"mode": "list",
"value": "[YOUR_ID]",
"cachedResultUrl": "",
"cachedResultName": "Emails Sync data"
}
},
"credentials": {
"googleSheetsOAuth2Api": {
"id": "credential-id",
"name": ""
}
},
"typeVersion": 4
}
],
"active": false,
"pinData": [],
"settings": {
"executionOrder": "v1"
},
"versionId": "",
"connections": {
"Prepare Sheet Payload": {
"main": [
[
{
"node": "Append to Google Sheet",
"type": "main",
"index": 0
}
]
]
},
"AI Email Analyst": {
"main": [
[
{
"node": "Interpret AI Output",
"type": "main",
"index": 0
}
]
]
},
"Urgency Branch Check": {
"main": [
[
{
"node": "Urgent Slack Alert",
"type": "main",
"index": 0
}
],
[
{
"node": "Attachment Route Check",
"type": "main",
"index": 0
}
]
]
},
"Urgent Slack Alert": {
"main": [
[
{
"node": "Prepare Sheet Payload",
"type": "main",
"index": 0
}
]
]
},
"Gmail Intake Trigger": {
"main": [
[
{
"node": "Derive Email Details",
"type": "main",
"index": 0
}
]
]
},
"General Slack Notice": {
"main": [
[
{
"node": "Prepare Sheet Payload",
"type": "main",
"index": 0
}
]
]
},
"Context Memory Buffer": {
"ai_memory": [
[
{
"node": "AI Email Analyst",
"type": "ai_memory",
"index": 0
}
]
]
},
"Bypass Attachment Handling": {
"main": [
[
{
"node": "AI Email Analyst",
"type": "main",
"index": 0
}
]
]
},
"Validate Attachment Presence": {
"main": [
[
{
"node": "Handle Attachment Data",
"type": "main",
"index": 0
}
],
[
{
"node": "Bypass Attachment Handling",
"type": "main",
"index": 0
}
]
]
},
"Interpret AI Output": {
"main": [
[
{
"node": "Urgency Branch Check",
"type": "main",
"index": 0
}
]
]
},
"Attachment Route Check": {
"main": [
[
{
"node": "Attachment Slack Alert",
"type": "main",
"index": 0
}
],
[
{
"node": "General Slack Notice",
"type": "main",
"index": 0
}
]
]
},
"Attachment Slack Alert": {
"main": [
[
{
"node": "Prepare Sheet Payload",
"type": "main",
"index": 0
}
]
]
},
"Derive Email Details": {
"main": [
[
{
"node": "Validate Attachment Presence",
"type": "main",
"index": 0
}
]
]
},
"Handle Attachment Data": {
"main": [
[
{
"node": "AI Email Analyst",
"type": "main",
"index": 0
}
]
]
},
"Azure Chat Model": {
"ai_languageModel": [
[
{
"node": "AI Email Analyst",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Structured Result Parser": {
"ai_outputParser": [
[
{
"node": "AI Email Analyst",
"type": "ai_outputParser",
"index": 0
}
]
]
}
}
}