TL;DR: A Glasgow e-commerce company handling 3,200 support tickets per month had no systematic visibility into customer sentiment trends. The CS manager found out about problems when they hit Trustpilot or the MD's inbox. A delivery partner generating 38% of complaints from 25% of volume went undetected for four months. We designed a four-stage agent that scores every ticket for sentiment, tags by theme, aggregates trends daily, and alerts when patterns shift. The full build guide is below: n8n plus Claude Haiku for classification, specific nodes, step-by-step instructions, and a cost breakdown that lands at roughly £35-£75 per month to run. The Claude API cost for classifying 3,200 tickets per month is approximately $1. Which does raise the question of why anyone does this from memory.
The Monday Sentiment Meeting
Monday morning, 10am. Alison's weekly support meeting. Four agents around the table.
"Lots of complaints about late deliveries last week. Mostly from the new courier we started using in September."
"A few people have been unhappy about the return process. Something about having to print labels."
"Someone posted a pretty angry review on Trustpilot about a damaged item. I responded."
This is the customer sentiment system. Four people reporting what they remember from the previous week's 800 tickets, filtered through recency bias (the angry email from Friday afternoon is more vivid than the pattern that's been building since September), survivor bias (the tickets that got escalated are memorable; the 50 quietly frustrated customers who didn't escalate are invisible), and availability bias (whatever happens to be top of mind at 10am on a Monday).
Alison writes notes. Assigns follow-ups. Moves on.
The delivery partner that was generating 38% of delivery complaints from 25% of delivery volume went undetected for four months. The complaint data was in Zendesk. The volume data was in Shopify. Nobody was dividing one by the other per partner. Alison was reading individual tickets. She saw angry customers. She didn't see the pattern. Because the pattern lived across two systems and one person's memory, and memory doesn't calculate ratios.
The Company
E-commerce fulfilment and customer service operation in Glasgow. Twenty-two employees. £1.8M annual revenue. Three thousand two hundred support tickets per month across email (55%), live chat (35%), and social media (10%).
Alison is the customer service manager. Her team of four agents resolves tickets. What nobody tracks: the emotional trajectory of the customer base. Are customers getting angrier? Are specific product lines generating frustration? Is a delivery partner consistently producing negative interactions?
Alison finds out when a customer posts a one-star review, tags the company on social media, or emails the MD directly. By then, the damage is done. The one-star reviews increased from 29 to 47 in the past year. Estimated revenue impact of declining review scores: £22,000 to £35,000 in lost sales. Customer complaints that reached the MD before Alison knew about them: 12 in the prior year. Each one triggered a fire drill consuming 2-4 hours of senior management time.
Alison spends an estimated 15-20% of her time on manual theme identification: reading ticket samples, scanning social mentions, checking review platforms, preparing for the weekly meeting. That's £6,600 to £8,800 per year in her time alone. For a sentiment picture that is, by her own admission, "anecdotal, unquantified, and probably two weeks behind whatever's actually happening."
The design is next. The design, the build guide, the running costs and the take-away are free to subscribers. Enter your email below and the rest of this Blueprint opens. New ones arrive every Tuesday and Friday.
