# Summary / TL;DR

Untitled identifies up to 60% of your website visitors. This rate depends on the type of site, amount of traffic, level of engagement of visitors, etc. For example, deeper engagement with the website gives our technology more ‘shots on goal’ to identify the visitor, as opposed to an immediate bounce due to a slow homepage, where our Tag may not even get a chance to load.

Each identified visitor can have 30+ attributes associated with them, and each of those attributes can be informed by multiple data points.  For example, If someone signed up for an industry working group this week, their work email information is very fresh and likely to be correct. If that same person entered a different work email on a trade show registration two years ago, that’s less likely to be accurate. Our technology would weigh those data points against each other and decide on the most recent address. In lieu of new information, however, Untitled may have provided the old work email address as an attribute if there isn't a reason to think it’s *not* correct.

The Untitled identity graph is constantly taking in millions of datapoints from a massive pool of data and weighing them against each other to provide the most complete, most accurate profile for each identified visitor. That’s the ‘secret sauce’ of the tech. Unfortunately, the only guarantee is it will never be 100% accurate (and if anyone makes that claim, run away!). Any single attribute could be incorrect, but we’re confident that 90% of the records in your account are correct.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.getuntitled.ai/product-overview/untitled-id-tag/data-validation-and-identity-resolution/summary-tl-dr.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.