Tal MorCase study
eCommerceMentorshipFractional CMOFAQ Case studiesBook a call
Google AdsLocal lead genEcommerce

An AI agent that reads every search term, every day.

I manage Google Ads for a personal injury law firm, a chiropractic office, a remodeling contractor and a fashion dropshipping store in Europe. Wasted spend in Google Ads hides in the search terms, and nobody reads them all. So I built an agent that does.

Book a free AI audit call →AI automation services
Real client accounts. Names withheld.
Tal Mor, Google Ads Automation Case Study
Accounts the agent watches
Law firmChiropracticRemodelingFashion store
Dailysearch term review on every account
Approvedevery change goes through me before it touches an account
Built and running. Happy to show it on a call.
4
Accounts in 4 industries
Every day
Search terms reviewed
0
Changes applied without approval

The accounts

Four very different accounts. A personal injury law firm, where clicks are some of the most expensive in Google Ads. A chiropractic office and a remodeling contractor, both local, both paying for calls and form fills. And a fashion store selling into Europe through Shopping.

What they share: Google matches ads to searches loosely, and broad and phrase match keep finding new ways to spend on the wrong people.

AccountsPersonal injury law, chiropractic, home remodeling, fashion ecommerce (Europe)
Campaign typesSearch, Performance Max, Shopping
What the agent doesReads search terms, flags waste, drafts negative keywords
What it never doesChange budgets, or apply anything without my approval
Built withClaude, Google Ads API, Postgres, my own agent fleet
StatusRunning daily

The problem

  1. Search terms nobody reads. A busy account shows a long list of new search terms every week, and reviewing them by hand is the first thing that gets skipped.
  2. Irrelevant clicks add up. The classic leaks: job seekers, people researching a career, DIY questions, competitors' brand names.
  3. Different accounts, different rules. What's waste for one client is a lead for another.
  4. Daily tinkering hurts Google. The account needs steady small cleanups, not big swings.

What I built

  1. A daily read of every search term, per account, judged against that account's own rules.
  2. Findings with reasons. Every suspected waste term comes with its cost, clicks and conversions, and why the agent thinks it's waste.
  3. Negative keywords drafted at the right level: campaign, ad group or a shared list.
  4. An approval queue. I approve or reject from one place, and only approved changes go through.
  5. Hard limits built in. The agent has no code to touch budgets, and accounts set to read-only refuse changes at the database level.
  6. A log of everything: what it found, what I decided and why.

How it runs

StepWhat happens
01. PullYesterday's search terms for every account.
02. JudgeEach term checked against the account's rules and its numbers.
03. QueueSuspected waste goes into a findings queue with reasons.
04. ApproveI approve or reject each one.
05. ApplyApproved negatives go into the account.
06. LogEvery finding and decision is kept, so the rules keep improving.

What changed

  1. Search terms get reviewed every day on every account, not when someone finds the time.
  2. Wasted spend gets cut while it's small, not after a month of leaking.
  3. My time goes to decisions, not to scrolling search term reports.
  4. Adding a new account is configuration, not a new build.

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
Google Ads doesn't need daily tinkering. It needs daily reading, and that's exactly what AI is good at.

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 automating Google Ads

Straight answers, from a system that runs every day.

How often should I review Google Ads search terms?

Weekly at minimum, and daily on accounts with real spend. An agent makes daily practical because reading costs it nothing.

Can AI add negative keywords automatically?

It can, but I don't let it. The agent drafts them and I approve. One wrong negative can block your best customers.

Does this work for local businesses like law firms and contractors?

Yes. Local lead gen is where search term waste hurts most, because clicks are expensive and intent varies a lot.

Will an AI agent change my budgets?

Not mine. Budget decisions stay with a person, and my agents have no code to change them.

More AI case studies

Same operator behind all of them.

◆

Every product sorted into winners and losers

Product-level spend checked against real store sales. Winners get their own campaign, losers get excluded, and every call sits next to its numbers.

Case study →
≡

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 →
▤

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 →