Gmail to Google Sheets, feedback logged and routed
You get feedback in five places, on three timelines, in two different “voices.” Then someone is supposed to copy it into a sheet, ping the right channel, and remember to follow up. It slips. Every week.
Product managers feel it when roadmap decisions are based on vibes, not evidence. Support leads feel it when a real bug report sits in an inbox. And for a founder, Gmail Sheets logging can be the difference between “we’ll fix it soon” and actually fixing it.
This workflow pulls feedback from Gmail and forms, uses AI to summarize and classify it, logs everything into Google Sheets, then routes urgent items to Slack or email. You’ll see exactly what it does, what you need, and what results to expect.
How This Automation Works
The full n8n workflow, from trigger to final output:
n8n Workflow Template: Gmail to Google Sheets, feedback logged and routed
flowchart LR
subgraph sg0["On form submission 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/form.svg' width='40' height='40' /></div><br/>On form submission"]
n1@{ icon: "mdi:brain", form: "rounded", label: "Google Gemini Chat Model", pos: "b", h: 48 }
n2@{ icon: "mdi:message-outline", form: "rounded", label: "Send Report", 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/slack.svg' width='40' height='40' /></div><br/>Slack"]
n4@{ icon: "mdi:play-circle", form: "rounded", label: "Receive review/feedbak", 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/code.svg' width='40' height='40' /></div><br/>Extract details"]
n6@{ icon: "mdi:robot", form: "rounded", label: "Transform and summarise", pos: "b", h: 48 }
n7@{ icon: "mdi:database", form: "rounded", label: "Review data", pos: "b", h: 48 }
n8@{ icon: "mdi:swap-horizontal", form: "rounded", label: "Categories", pos: "b", h: 48 }
n8 --> n3
n8 --> n2
n7 --> n8
n5 --> n6
n0 --> n6
n4 --> n5
n6 --> n7
n1 -.-> n6
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,n4 trigger
class n6 ai
class n1 aiModel
class n8 decision
class n7 database
class n5 code
classDef customIcon fill:none,stroke:none
class n0,n3,n5 customIcon
The Problem: Feedback gets captured, but not acted on
Most teams don’t fail at collecting feedback. They fail at turning it into a repeatable system. A form response lands in one tool, a frustrated email lands in Gmail, and someone tries to “triage” it between meetings. Meanwhile, the same issue gets reported three times with slightly different wording, so it never looks urgent. Then when a stakeholder asks, “How many people are asking for this?” you end up scrolling, searching, and guessing. It’s exhausting. And honestly, it’s avoidable.
The friction compounds. Here’s where the process usually breaks down.
- You end up copying feedback into a spreadsheet by hand, which quietly burns about 2 hours a week.
- Important items don’t get routed, so bugs sit in Gmail while your team debates priorities elsewhere.
- Without consistent categories and sentiment, themes stay hidden and decisions take longer.
- Follow-ups are inconsistent because there’s no single source of truth to work from.
The Solution: AI-classify feedback, log it, then route it automatically
This n8n workflow creates a simple feedback loop that doesn’t rely on someone “remembering.” It starts when feedback arrives from two sources: a form submission (for structured reviews) or a new Gmail message (for the messy, real-world stuff). If it’s an email, the workflow parses sender details and extracts the actual review text so you’re not analyzing signatures and quoted replies. Then an AI model summarizes the feedback, assigns sentiment, and classifies it into useful buckets like Bug, Feature Request, UX Issue, or Other. Finally, everything gets appended into a Google Sheets log, and the workflow routes the item to the right place, like Slack for bugs or email for stakeholder updates.
The workflow begins with a new email or form response. AI turns raw text into structured fields your team can sort and filter. Google Sheets becomes the master log, and routing rules push the right feedback to Slack or email so it gets handled.
What You Get: Automation vs. Results
| What This Workflow Automates | Results You’ll Get |
|---|---|
|
|
Example: What This Looks Like
Say you get 25 pieces of feedback a week across Gmail and a form. Manually, logging each one takes maybe 5 minutes (copy text, clean it up, pick a category, paste into Sheets), so you’re at about 2 hours weekly, plus the time spent pinging Slack. With this workflow, you spend roughly 10 minutes setting up the sheet once, then each new item is logged and routed automatically while you keep working. You still review the highlights, but the busywork is gone.
What You’ll Need
- n8n instance (try n8n Cloud free)
- Self-hosting option if you prefer (Hostinger works well)
- Gmail to capture feedback emails and send reports.
- Google Sheets to store your structured feedback log.
- Slack to alert the right team channel quickly.
- OpenAI API key (get it from your OpenAI dashboard’s API keys page).
Skill level: Beginner. You’ll connect accounts, choose a Sheet, and tweak a prompt or two.
Don’t want to set this up yourself? Talk to an automation expert (free 15-minute consultation).
How It Works
New feedback comes in. The workflow triggers from a form submission or when a new feedback email hits your Gmail inbox. Two entry points, one system.
The message gets cleaned up. For emails, a parsing step extracts sender details and isolates the actual feedback text so the AI analyzes the right content (not the email thread clutter).
AI turns text into structured fields. The AI model summarizes what the customer is saying, identifies sentiment, and classifies the feedback into categories like Bug, Feature Request, UX Issue, or Other. A Gemini chat engine can be used as an optional layer if you want stronger classification.
Everything gets logged and routed. Each item is appended to Google Sheets for tracking, then a routing step sends it to Slack (for urgent categories like bugs) or dispatches an email report to stakeholders.
You can easily modify the categories and routing rules to match how your team works. See the full implementation guide below for customization options.
Step-by-Step Implementation Guide
Step 1: Configure the Form Trigger
This workflow starts from two sources: a form submission and monitored email inbox messages.
- Open Form Submission Trigger and set Form Title to
Customer Review. - In Form Fields, add Name and Review with Required enabled for both.
- Open Email Feedback Trigger and set Label IDs to
[YOUR_ID]under Filters. - Set Poll Times to
everyMinutein Email Feedback Trigger.
Credential Required: Connect your Gmail credentials in Email Feedback Trigger.
Step 2: Connect Google Sheets
Summarized feedback is appended to a spreadsheet for logging and analysis.
- Open Append Feedback Log and select your target Document ID and Sheet Name.
- Keep Operation set to
append. - Map columns to the output fields using the existing expressions: summary →
{{ $json.output.summary }}, category →{{ $json.output.category }}, Timestamp →{{ $json.output.Timestamp }}, sentiment →{{ $json.output.sentiment }}, and Feedback text →{{ $json.output["Feedback text"] }}.
Credential Required: Connect your Google Sheets credentials in Append Feedback Log.
Step 3: Set Up Summarize Feedback
This step parses the sender from emails and uses AI to categorize and summarize the feedback text.
- In Parse Sender Details, keep the provided JavaScript Code so it returns
nameandReviewfrom the incoming email. - Open Summarize Feedback and set Text to
{{ $json.Review }}. - In Summarize Feedback, ensure Schema Type is
fromJsonand keep the JSON schema example as provided. - Verify the system prompt template is configured with the expression
=You are a feedback analyst... Feedback: {{ $json.Review }}for consistent classification. - Confirm Gemini Chat Engine is connected as the language model for Summarize Feedback.
Credential Required: Connect your googlePalmApi credentials in Gemini Chat Engine. This AI credential is used by Summarize Feedback, so do not add credentials to the sub-node.
Step 4: Configure Output and Routing
After logging the feedback, the workflow routes by category and sends the appropriate notification.
- Open Route by Category and confirm the two rules compare
{{ $json.category }}toBugandFeature Request. - In Slack Alert Post, set Text to
User {{ $json.candidate_name }} has already applied for {{ $json.role_applied }}and choose a User target. - In Email Report Dispatch, set Subject to
Energy Report, Email Type totext, and Message toYour monthly energy report is as follows {{ $json.url }}.
Credential Required: Connect your Slack credentials in Slack Alert Post.
Credential Required: Connect your Gmail credentials in Email Report Dispatch.
Step 5: Test and Activate Your Workflow
Run a full test from each trigger to verify routing, logging, and notifications.
- Click Execute Workflow and submit a test entry through Form Submission Trigger with a sample review.
- Send an email with the required label ID to trigger Email Feedback Trigger and confirm Parse Sender Details extracts the name and review snippet.
- Verify Summarize Feedback outputs category, summary, sentiment, and feedback text, and that Append Feedback Log appends a new row.
- Confirm Route by Category sends a message to Slack Alert Post for
Bugor to Email Report Dispatch forFeature Request. - When successful, toggle the workflow to Active for production use.
Common Gotchas
- Gmail credentials can expire or need specific permissions. If things break, check the Gmail OAuth connection inside n8n’s Credentials 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.
- Slack webhooks and OAuth scopes trip people up. If alerts stop, confirm the channel still exists and re-check the Slack app permissions for posting messages.
Frequently Asked Questions
About 30 minutes if your Gmail, Slack, and Sheets access is ready.
No. You’ll connect accounts and adjust a few fields and routing rules. The only “technical” part is tweaking the AI prompt, and that’s just writing plain English.
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 (often just a few dollars a month for modest feedback volume).
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.
Yes, and you should. Update the classification instructions in the Summarize Feedback AI step so it outputs your categories (Billing Problem, Support Issue, Churn Risk, and so on). Then adjust the Route by Category switch so each category goes to the right Slack channel or email recipient. You can also add a “Priority” field in the Google Sheets log if you want a clear triage queue.
Usually it’s expired Gmail OAuth credentials inside n8n. Reconnect the Gmail credential and confirm the account still has permission to read the inbox you’re monitoring. Also check that the trigger is watching the right label or mailbox, because it’s easy to point at a quiet folder and think the workflow is broken.
A lot for most small teams: hundreds per week is fine if your AI usage limits allow it.
Often, yes, once you want real routing logic and AI classification in the same workflow. n8n makes it easier to branch by category, add fallbacks, and keep everything in one place without paying extra for each “path.” Zapier and Make can be simpler for a two-step capture, but they get clunky when you’re parsing emails, extracting fields, then splitting into Slack and email. If you’re unsure, pick the tool you’ll actually maintain. Talk to an automation expert and we’ll sanity-check your setup.
Your inbox doesn’t need to be a feedback database. Log it once in Google Sheets, route it automatically, and keep the team focused on fixing the right things.
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.
