Tal MorCase study
eCommerceMentorshipFractional CMOFAQ Case studiesBook a call
Google ShoppingPerformance MaxEcommerce

Every product sorted into winners and losers.

In a Shopping or Performance Max campaign, a handful of products take most of the budget and a long tail spends without selling. I use AI to sort every product by what it actually earns, then scale the winners and exclude the losers.

Book a free AI audit call →AI automation services
Used on client ecommerce accounts and my own stores.
Tal Mor, Google Shopping Product Automation Case Study
Every product lands in one group
WinnersPromisingLosersNot enough data
Every productclassified on its own spend and sales
Store salesused as the judge, not just Google's numbers
Built and running. Happy to show it on a call.
Every product
Scored on its own numbers
Winners
Moved into their own campaign
Losers
Excluded before they drain budget

Where it runs

Ecommerce accounts with real catalogs, including a US medical equipment retailer with about 650 products, and my own stores.

Big catalogs hide waste. Google reports by campaign, so a product that has spent hundreds without a sale can sit quietly inside a campaign that looks fine.

AccountsEcommerce stores with large catalogs
Campaign typesShopping and Performance Max
DataGoogle Ads product performance and real store orders
OutputWinner and loser groups, campaign moves, exclusions
Built withClaude, Google Ads API, store exports, Google Sheets
CadenceRechecked regularly as products move between groups

The problem

  1. Averages hide products. A campaign at a decent ROAS can contain products that lose money every day.
  2. Google's numbers aren't the whole truth. Store orders, refunds and offline sales tell a different story per product.
  3. Nobody checks hundreds of products by hand.
  4. Winners get starved. A best seller inside Performance Max fights the long tail for the same budget.

What I built

  1. A product-level pull. Spend, clicks, conversions and value for every product over a set window.
  2. A cross-check with the store. Google's numbers matched to real orders, to get the true cost per sale for each product.
  3. Classification with rules. Winners, promising, losers and not enough data, with thresholds set by price tier so a $50 accessory and a $2,000 device aren't judged the same way.
  4. Winners scaled. Proven sellers move into their own campaign, so they get budget they don't have to fight for.
  5. Losers excluded. Products that spent past their limit without selling are excluded, and rechecked later.
  6. A sheet I can check. Every call is visible with the numbers behind it.

How it runs

StepWhat happens
01. PullProduct-level performance for the window.
02. MatchGoogle's numbers matched to store orders.
03. ScoreEach product placed in a group by its price tier rules.
04. ActWinners moved up, losers excluded.
05. RecheckGroups updated as seasons, prices and stock change.

What changed

  1. Spend moves from the long tail to the products that sell.
  2. Waste is found per product, not guessed per campaign.
  3. Every decision sits next to its numbers, so a client can sanity-check each one.

How an AI project with me runs

01

Free call

Sixty minutes on your business. I tell you what I would automate first and what I would leave alone.

02

Map the work

I learn how your business actually runs, then rank what to automate by hours saved and risk.

03

Build one thing

We start with the system that saves the most time, with a person approving anything that touches money.

04

Hand over or run it

You get documentation and training, or I keep running and improving it monthly.

Tal Mor
A campaign average is a comfortable lie. The product level is where the money is.

I run my own ecommerce brands, so every system I build has to hold up on a busy Monday, not just in a demo. I build the same kind of system for other businesses: I learn how yours works, decide what to automate, and build it.

20 years operatingAI architect for ecommerceUpwork Top Rated · 100% JSS

Questions about Google Shopping product automation

Straight answers, from a system that runs every day.

How do I find which products waste money in Google Shopping?

Pull product-level performance for at least 30 days and sort by spend with zero or few conversions. Then check those against real store orders before cutting anything.

Should best sellers have their own campaign?

Usually yes. Inside Performance Max they compete with every other product for budget. Their own campaign protects them.

How often should products be reclassified?

Monthly works for most stores, more often around sales seasons. Products move between groups as prices, stock and seasons change.

More AI case studies

Same operator behind all of them.

≡

Bank statements in, an owner's P&L out

Every expense categorized, subscriptions and fees surfaced, a cut list, and a daily P&L per store. Replaces a full-time bookkeeper.

Case study →
◎

A daily social post, approved from my phone

A real product photo restyled by AI, a caption in the brand voice, and one tap on Telegram to approve or redo. Runs in the cloud.

Case study →
▤

All case studies

AI systems plus Meta, Google and Klaviyo accounts, with real numbers.

See all →

Want a system like this in your business?

Sixty minutes, one-on-one, free. Bring the jobs that eat your week and I'll tell you what I'd automate first.

📅Book the free call
60 minutes, bring your numbers✉Email me
contact@talmor.ca💬WhatsApp / SMS
Prefer to message? Reach me directly
Free account review60 min · no pitch
Book →