UTM markup audit
Insert links from campaigns. The tool will find inconsistencies in case and names, missing parameters, and anything that can cause one source to split into five lines in the report.
The markup breaks the report not by the absence of labels, but by its inconsistency: yandex and Yandex, cpc and CPC, telegram and tg turn one source into four lines, and there is nothing to compare channels with. The tool checks the reference list for such discrepancies, finds missing parameters, and suggests a consistent naming scheme.
AI answers are free, but limited by the overall site limit. If the limit is reached, come back later: repeated clicks will not speed up the response.
What breaks the report is not the lack of labels, but the inconsistency in them
Usually everyone sets the markings and calms down on that. The report breaks later and quietly: yandex, Yandex and yandex.direct, telegram and tg, cpc and CPC appear in the list of sources. Each pair is one channel cut in two, and any comparison of channels after that is invalid.
The second most common problem is values that do not distinguish anything. campaign=test, content=1, term=none look like filled fields and do not answer any questions. A month later, no one remembers what the campaign called test meant, and the data has already been collected.
Therefore, the audit starts from the question, and not from references: first, what should the report answer, then whether there are enough parameters for this. Markup that makes it impossible to understand which creative submitted the application is formally correct and practically useless.
What the tool intentionally doesn't do
Does not insert numbers, deadlines, benchmarks and names of companies that did not exist in your input. If the output requires a number that you did not provide, in the answer will be marked “to clarify” rather than a plausible number. This limitation is worth in the system prompt and works against the main property of language models: It’s difficult to complete what’s missing.
The request text is sent to the AI provider, and the response is returned to the browser. The site does not save these texts in the database. To limit expenses separately the number of requests and the anonymized connection identifier are taken into account. If the free limit is reached, the tool will offer to come back later.