A personal trainer, a heating engineer, a care agency, a repair shop. Small accounts, real problems: tracking that never worked, one keyword eating the budget, a typo in the city name. Claude finds them in your account, free.
When the monthly budget is a few hundred, one mistake is most of it. These are real numbers from small accounts Claude audited.
77%of one account’s spend on a keyword with 0 conversionsheating service, Turkey
12 monthswithout a recorded conversionlocal service, Saudi Arabia
66.6 sfor a landing page to show on a phoneGoogle’s bar is 2.5 s
80unrelated searches through one “exact” keywordpersonal trainer, Brazil
What happens after you connect
Step 1
Sign in with Google
No password and no card.
Step 2
Connect Google Ads
Approve access on Google’s own screen and choose the account.
Step 3
Claude reads the account
Tracking, search terms, keywords, budgets, ads, landing pages. Cases appear as each review finishes.
Step 4
Fix the top case
Read the evidence, press Apply, keep the undo. Or follow the steps for anything on your website.
Small business case studies
Real small accounts, anonymised. Open each one for every case Claude filed.
Home physiotherapy providerUnited Kingdom · GBP
21 of 22 conversions in 30 days were landing in secondary actions, so bidding was steering on a single conversion.
Search only, two live campaigns, a daily budget around £22.
conversions bidding could not see
21 of 22
on one broad keyword, 0 conversions
£52.11
keywords blocked by their own negatives
7
What Claude found (6 cases)
Conversion trackingThe actions that record are not the ones steering bidding
The 8 primary actions recorded 1 conversion between them. The bookings that really came in were all counted as secondary.
Recent changesEvery conversion action stopped at the same moment
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.
KeywordsA broad keyword spent more than a conversion costs and got nothing back
£52.11 and 0 conversions on broad match, while the phrase copy of the same keyword won 2 conversions for £18.72.
KeywordsSeven exact keywords were also added word for word as negatives
Each one was bid on and blocked at campaign and ad group level, so it could never show.
Ads and assetsThe ads promised same-day visits, a callout still said same-week
Two promises side by side in the same ad, one of them out of date.
Growth opportunitiesMondays converted for a fraction of the cost
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.
Heating and air-conditioning serviceTurkey · TRY
One keyword with a Quality Score of 3 took 762.56 of the account’s 984.97 TRY and brought no conversions.
One Search campaign, under 1,000 TRY in its first nine days.
of spend on one keyword, 0 conversions
77%
for the landing page to show on a phone
66.6 s
TRY per conversion: one search vs the account
68 vs 787
What Claude found (5 cases)
KeywordsOne poorly scored keyword took most of the spend
Quality Score 3, 762.56 TRY of 984.97, no conversions.
Search termsAds were paying for how-to questions
Six “how” and “how often” searches took 223.47 TRY of 563.84 TRY in 30 days, with no conversions.
Landing pages and speedThe landing page took 66.6 seconds to show on a phone
Google’s bar for a good page is 2.5 seconds. Claude added a message to send to the developer.
Recent changesA negative keyword blocked the company’s own name
A broad negative excluded every search containing a word from the business name.
Search termsA search that converted was not a keyword
It brought one of the account’s two conversions for 68.39 TRY, when a conversion cost 786.80 TRY across the account.
Live-in home care agencyUnited Kingdom · GBP
Google’s auto-apply removed two keywords set up days earlier, and the main campaign nearly stopped showing.
Search plus Performance Max, spending about £50 a day.
days served after the keyword swap
1 of 5
night-care keywords blocked by their own negatives
7
live spend, 0 conversions; the paused campaign had 2
£204.69
What Claude found (5 cases)
Recent changesAuto-apply removed two keywords
Recommendations auto-apply removed two phrase keywords on 31 October that had been set up on 28 October.
Recent changesThe main campaign nearly stopped after its broadest keyword was swapped
Its last daytime impressions came the hour the keyword was removed. After that it served on 1 day out of 5.
KeywordsA whole set of keywords was blocked by its own ad group
7 enabled night-care keywords each matched a negative in the same ad group.
Search termsA misspelled negative blocked nothing
A list held “acility” instead of “facility”, so the singular search still got through.
Budgets and reachThe only campaign that converted was switched off
The paused campaign logged 2 conversions on £22.56. The live one logged 0 on £204.69.
Personal trainerBrazil · BRL
A keyword written as exact was running broad and matching gyms, studios, and people’s names.
One Search campaign, about 113 BRL a month.
different searches through one “exact” keyword
80
per conversion on the campaign losing 37% to budget
18.80 BRL
spelling mistakes in live ad copy
3
What Claude found (5 cases)
Search termsOne keyword written as exact was running broad
80 different searches came through it with no conversions, while the plain service keyword brought both conversions.
Search termsExact-match negatives only blocked the bare word
A price search slipped past the price negative, and gym searches past the gym one.
TrackingThe final URL suffix held a full web address
It should hold key=value tracking parameters; it repeated the site address on every click.
Ads and assetsThe ad copy had spelling mistakes
Three typos across a headline and two descriptions, one in the area name the ad is built around.
Growth opportunitiesThe campaign converted and was still limited by budget
37% of eligible impressions lost to budget, at 18.80 BRL per conversion.
Equipment repair businessSaudi Arabia · SAR
No conversion action had ever recorded anything, and the landing page HTML had no Google tag.
One new Search campaign, under SAR 100 in its first week.
conversions recorded by 3 primary actions
0
spent in the first week with nothing measured
SAR 77
ad, so nothing to test it against
1
What Claude found (4 cases)
Conversion trackingThe site may not have a tag at all
All three primary actions recorded 0 in 30 days, and the page’s HTML showed no Google tag.
Recent changesThe only campaign was paused and stayed off
Nothing served for four days after a pause made in Google Ads.
Ads and assetsOne ad, rated Average, carried every click
With no second ad there was no way to tell whether the copy was the problem.
Ads and assetsHalf the callouts Google recommends
Three callouts, each repeating a sitelink, and no structured snippet.
Local emergency serviceSaudi Arabia · SAR
Phone calls were the goal, but the call asset had call reporting off and the tag had not recorded once in 12 months.
One Search campaign in Arabic, SAR 58–84 a month.
without a single recorded conversion
12 months
phone impressions in the month
0
misspelled headlines, one in the city name
2
What Claude found (3 cases)
Conversion trackingNothing had ever been recorded
The contact tag recorded nothing in 12 months while the campaign took clicks.
Conversion trackingCalls were a goal but could not count
The call goal was left out of the Conversions column, and call reporting was off on the newer call asset.
Ads and assetsTwo headlines were misspelled
One of the errors was in the name of the city the ads target.
Services companySaudi Arabia · SAR
All four enabled campaigns had 0 impressions in 30 days, and two Search campaigns were set to show on Display once they did.
Four enabled campaigns, Search and Performance Max, with SAR 46 a day in budgets.
impressions across 4 enabled campaigns
0
Search campaigns with Display switched on
2
What Claude found (4 cases)
Growth opportunitiesNothing was serving
SAR 46 a day of budget, 0 impressions and 0 spend in 30 days.
StructureSearch campaigns would leak into Display
Display was on in both Search campaigns. No Display spend yet only because nothing had served.
TargetingAds would reach people only interested in the area
Location option set to presence or interest, so searchers outside the area could trigger ads.
Landing pagesThe landing page heading just said “Blog”
Caught before any spend reached it, the cheapest time to fix it.
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.
What Claude checks first in a small account
The full audit covers every area. In small accounts these four decide whether the budget can work at all.
Search terms
Reads: The search terms report for 30 days, every negative keyword and shared list.
Searches that spend without converting, grouped by intent (questions, jobs, competitors, free, DIY)
Converting searches that are not keywords yet
Negatives that leak: exact negatives that only block the bare word, misspellings, lists not attached
Searches for other businesses, places you do not serve, and your own brand
Keywords
Reads: Every keyword with Quality Score parts, match type, bids, and 30-day results.
Keywords that take a large share of spend with no conversions
Keywords blocked by their own negatives at ad group, campaign, or list level
Broad keywords that lose to their own phrase or exact copy
Quality Score parts below average, and keywords that never serve
Conversion tracking
Reads: Every conversion action: primary or secondary, counting, value, attribution model, windows, last recorded date.
Real conversions landing in secondary actions while bidding steers on others
Tags that stopped recording, or never recorded at all
Soft actions (page views, taps, directions) and test actions set as primary
Every-count on lead actions, placeholder values of 1, mixed attribution models, enhanced conversions off
Ads and assets
Reads: Every ad, its strength, approval, headlines and descriptions, and every asset at each level.
Ads that get clicks and no conversions next to ads that convert
Spelling mistakes and promises that contradict each other
Sitelinks hidden by a more specific level, duplicates, missing callouts and snippets
Ad groups with one ad, so nothing is tested
Running ads on your own? Get the audit an agency would charge for, free, in your own currency.
The 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.
Is a Google Ads audit worth it for a small business?
Yes, and often more than for a big one. With a small budget, one bad keyword or one broken tag can be most of the month. In the real audits on this page, one keyword took 77% of a small account’s spend, and another account had never recorded a conversion in 12 months.
How much should a small business spend on Google Ads?
Enough to get a steady number of conversions to learn from; there is no fixed figure. A useful check: if your daily budget is less than your cost per conversion, smart bidding has very little to learn from, and a manual or click-based strategy with tight keywords may work better until volume grows. The audit shows your own cost per conversion.
I do not have time to manage Google Ads. Can Boxoo help?
Yes. Claude reads the account for you and turns what it finds into a short list of cases, each with the fix. You approve fixes in one click, with an undo, and the free Chrome extension shows them right inside Google Ads.
Do I need a marketing agency to audit my Google Ads?
Not for the audit. Boxoo’s free audit checks the same things an agency audit would: tracking, search terms, keywords, budgets, ads, landing pages, and settings. If you work with an agency, you can share the cases with them.
Will the audit change my ads?
No. The audit only reads. Nothing changes until you press Apply on a case, and most changes can be undone.
What is the most common mistake in small Google Ads accounts?
Tracking that does not work. In these audits, small accounts had conversion actions that never recorded, call reporting turned off when calls were the goal, and every-count actions that counted one person twice. Without working tracking, there is no way to tell what the budget is buying.
Is it free?
Yes. The audit is free with no card, and so is the Chrome extension. Pro keeps Claude reviewing the account every day.