# Account analysis

Kernel identifies and fixes accounts with incoherent identities (e.g., company name is Pepsi, but the website is fritolay.com), resolving the dilemma by identifying how a rep would see the account.

Kernel uses the following data to make its recommendation:

* Related opportunity names
* Related contact domains
* Alternative websites
* Account/billing emails
* Account notes
* Existing LinkedIn
* Legal name
* Crawling the website of the current URL

### Kernel recommends determining an account’s identity based on how a rep would see the account

When data vendors use the Website listed in this CRM, a common error occurs: they enrich the account with incorrect data compared to what the representative would consider accurate.

<figure><img src="/files/lpnXieeO2XnRE6PMY6BM" alt=""><figcaption></figcaption></figure>

### Account identity analysis

The output of the account identity analysis is the following data:

| Data                         | Definition                                                                   |
| ---------------------------- | ---------------------------------------------------------------------------- |
| Suggested name               | Suggested name of the account                                                |
| Suggested website            | Suggested website of the account                                             |
| Account identity - Reasoning | Short paragraph summarizing the analysis and the reasoning behind the choice |

<figure><img src="/files/G8tzvZCeuMuKiGaKv263" alt=""><figcaption></figcaption></figure>


---

# 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.kernel.ai/legacy/data/account-analysis.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.