Searches for something else
How-to questions, jobs, free, DIY, other businesses, places you do not serve. Six question searches took 40% of one account’s spend.
Clicks from people who wanted something else. Keywords that spend while their better copy is blocked. Ads that land on the wrong page. Claude finds each leak in your account, puts a number on it, and offers the fix.

In a small account in Turkey, one keyword took most of the budget in its first nine days. Nothing in Google Ads flagged it: the keyword was approved and serving.
| Item | TRY | Group |
|---|---|---|
| One keyword, Quality Score 3 | 762.56 TRY | No conversions |
| Everything else | 222.41 TRY | Spend |
How-to questions, jobs, free, DIY, other businesses, places you do not serve. Six question searches took 40% of one account’s spend.
High spend, no conversions, while the phrase or exact copy of the same keyword wins. £52.11 on broad against 2 conversions for £18.72 on phrase.
A negative containing your keyword’s words stops it serving. Seen in four of ten accounts, once on the business’s own name.
AED 5,141 in a month sent specialist-ad clicks to a general checkup page. Claude fetches every spending ad’s landing page.
Connected TV, Display leaking from Search, Demand Gen with no asset groups. AED 404 on Connected TV with zero conversions.
Google’s budget raises, broad match, and auto-apply, checked against your own cost per conversion before you accept them.
Start where the leak is big and the fix is one click. The board ranks every case the same way, by what it costs you now.
Reads: The search terms report for 30 days, every negative keyword and shared list.
Reads: Every keyword with Quality Score parts, match type, bids, and 30-day results.
Reads: The final URL of every spending ad, fetched as a visitor would, and PageSpeed on a phone from your countries.
Reads: Locations, location options, networks, devices, schedules, and audiences.
Reads: Every open recommendation with Google’s own projected impact.
Real accounts, anonymised. Open each one for every case Claude filed.
Search only, two live campaigns, a daily budget around £22.
The 8 primary actions recorded 1 conversion between them. The bookings that really came in were all counted as secondary.
22 events in the 11 days to 21 October, then 0 in the next 11 days on 36 clicks. Claude flagged it as a tracking break, not a slow week.
£52.11 and 0 conversions on broad match, while the phrase copy of the same keyword won 2 conversions for £18.72.
Each one was bid on and blocked at campaign and ad group level, so it could never show.
Two promises side by side in the same ad, one of them out of date.
Monday brought 4 of the 8 conversions on under a tenth of spend: £7.48 per conversion against £38.24 across the week.
What happened next: The owner applied seven of the fixes from the board right after the audit, including pausing the broad keyword.
Several Search campaigns plus one Demand Gen campaign.
AED 3,455 and AED 1,686 in 30 days went to a page selling a checkup, not the specialist service in the ad.
Applying all seven would buy extra conversions at about AED 165 each. The account was running at AED 105.
The one Demand Gen campaign showed zero asset groups while it had spent AED 5,655.74.
Maximize Conversions was learning from 25.5 and 27.25 conversions a month, under the roughly 30 the strategy needs.
One list was uploaded, but its Search size was zero.
One Search campaign, under 1,000 TRY in its first nine days.
Quality Score 3, 762.56 TRY of 984.97, no conversions.
Six “how” and “how often” searches took 223.47 TRY of 563.84 TRY in 30 days, with no conversions.
Google’s bar for a good page is 2.5 seconds. Claude added a message to send to the developer.
A broad negative excluded every search containing a word from the business name.
It brought one of the account’s two conversions for 68.39 TRY, when a conversion cost 786.80 TRY across the account.
Search plus Performance Max, spending about £50 a day.
Recommendations auto-apply removed two phrase keywords on 31 October that had been set up on 28 October.
Its last daytime impressions came the hour the keyword was removed. After that it served on 1 day out of 5.
7 enabled night-care keywords each matched a negative in the same ad group.
A list held “acility” instead of “facility”, so the singular search still got through.
The paused campaign logged 2 conversions on £22.56. The live one logged 0 on £204.69.
One Search campaign, about 113 BRL a month.
80 different searches came through it with no conversions, while the plain service keyword brought both conversions.
A price search slipped past the price negative, and gym searches past the gym one.
It should hold key=value tracking parameters; it repeated the site address on every click.
Three typos across a headline and two descriptions, one in the area name the ad is built around.
37% of eligible impressions lost to budget, at 18.80 BRL per conversion.
From real Boxoo audits, read in November 2026. We removed names, brands, cities, and identifying search terms; the numbers are exactly what Claude reported, in each account’s own currency.
The evidence first, then exactly what changes, then an undo. Demo account screens.

How much of your budget is leaking? Connect Google Ads and see every leak with its amount, free.
Start my free auditThe Boxoo extension for Chrome is free. It puts the audit where you already work: a Boxoo score in the top bar, chips beside the ad groups, keywords, and ads that have a case, and a chat with Claude that already knows your account. Ask “why did my cost per conversion go up?” on the page you are looking at.

Start with the search terms report for the last 30 days and sort by cost: anything that spent more than your cost per conversion with no conversions is a candidate. Then check keywords the same way, then landing pages for the ads that spend most. Boxoo’s free audit runs all of these and gives you the list with the amounts.
Spend that could not have turned into a customer: searches from people who want something else (jobs, free, how-to, another business), clicks from outside the area you serve, ads that land on the wrong page, and keywords that keep spending with no conversions while a better copy of them converts.
Negatives are easy to add and easy to forget. A negative that contains the words of one of your own keywords stops that keyword from ever serving, and Google Ads shows no error. In the real audits on this page, four accounts had this, one with 30 keywords blocked in a single ad group.
Only if the extra conversions cost what you can afford. In one audit, applying Google’s seven budget raises would have bought conversions at about AED 165 each when the account was paying AED 105. Claude compares each recommendation with your own cost per conversion.
Yes, with your approval. Adding negative keywords, pausing a keyword, an ad, or a campaign, and changing a budget are one-click fixes with an undo. Landing pages and match type changes come with exact steps instead.
Yes. It is part of the free Google Ads audit, with no card. The free Chrome extension shows the same cases next to the campaigns in Google Ads.
Boxoo is not affiliated with Anthropic. Claude is a trademark of Anthropic, PBC.
The audit is free and read-only. Claude shows every leak with its amount and a fix you approve.
