30 Minutes Saved Every Day — With a $6\/Month Automation

In plain English

The problem Sarah had: Sarah manages catering requests for Fuel Bakehouse. Every quote request followed the same 5-step manual process: extract customer details from email, populate a spreadsheet, generate a quote in Excel, fill in an email template, attach the PDF, and send it. She was doing this 6 times a day, 6 days per week.

What I built: An automation workflow that handles most of it. The moment an email arrives, it extracts the customer details, writes them into her spreadsheet, generates the email, attaches the menu PDF, and alerts Sarah to review, attach quote, and send.

The outcome: 5 minutes saved per quote request. 6 requests a day, 6 days a week. That's 30 minutes daily, 15 hours a month back in her pocket. The cost to run it all: $6 a month on DigitalOcean.

Nerd Speak

I met Sarah Taylor at Dale Beaumont's AI in Business seminar a month ago.

She manages catering requests for Fuel Bakehouse and every single quote followed the same manual process:

1. Customer submits a form ➜ email lands in Gmail
2. Sarah extracts key details ➜ populates two tabs in Google Sheets
3. Opens Excel ➜ generates the quote manually
4. Creates an email from a template, fills in the name, date, and To: address
5. Attaches the menu PDF and quote ➜ hits send

She was doing this 6 times a day. Every day.

Here's what we built:

  • Gmail filter + label to detect incoming quote requests the moment they arrive.

  • n8n running on a DigitalOcean VPS (US$6/month) to trigger on that label.

  • AI Agent to extract customer details from the email and write them directly into the right columns in her Google Sheet.

  • Code nodes to format dates correctly before insertion.

  • Auto-generated email: subject line, body, dates, menu PDF attached, addressed to the customer.

  • Label update to mark emails as processed.

  • Telegram alert to Sarah so she can review, generate the quote, attach it, and hit send.

  • Error handler that fires a Telegram message to us if anything breaks.

The result? Each quote request now takes Sarah a fraction of the time.

5 minutes saved × 6 requests a day = 30 minutes daily ➜ 15 hours a month. Back in her pocket.

The takeaway:
I used to build n8n workflows node by node. Now I use Claude Code to build them in a fraction of the time and case studies like this one give me documented setups I can roll out faster for the next client.

And this was just the starting point. With full access to the website, we could have added a Voice AI agent, auto-generated quotes, and a custom order management app.

If you've mapped out an online process clearly enough that someone new could follow it ➜ AI can be trained to do it too.

Mark Reynolds

Learning by Building

What’s Mark Building?

Want to see what I’m building next? Join my email list and I’ll send my latest builds, messy updates, and solutions straight to your inbox.

MARK REYNOLDS

I use AI to build custom tools that handle my boring, repetitive tasks. I’m on a mission to optimise my workflow and help you do the same.

Created with ©systeme.io