# Under the hood

{% hint style="success" %}
This is the official documentation of the `forestadmin-agent-django` and `forestadmin-agent-flask` Python agents.
{% endhint %}

Join emulation works by transparently analyzing the requests that are performed by the frontend and customer API in your Agent, and translating them into multiple requests to the relevant data sources.

For instance, assuming that:

* you defined a jointure between 2 Collections: `books` and `authors`,
* both Collections are hosted on different SQL databases
* you display the `books` list in your admin panel

```sql
-- The frontend needs the result of that query to display the 'list view'
-- which cannot be performed, because books and authors are on different databases
SELECT books.title, authors.firstName, authors.lastName
FROM books
INNER JOIN authors ON authors.id = books.id
WHERE books.title LIKE 'Found%'
```

The request will be transparently split and its result merged to produce the same output as if the original query was run.

```sql
-- Step 1: Query database containing books (including foreign key)
SELECT books.title, books.authorId FROM books WHERE books.title LIKE 'Found%';

> | title      | authorId |
> | Foundation | 83948934 |

-- Step 2: Query database containing authors (including pk)
SELECT authors.id, authors.firstName, authors.lastName FROM authors WHERE id IN (83948934);
> | id       | firstName | lastName |
> | 83948934 | Isaac     | Asimov   |

-- Step 3: Merge results (using books.authorId === authors.id)
> | title      | authorId | firstName | lastName |
> | Foundation | 83948934 | Isaac     | Asimov   |
```

{% hint style="warning" %}
Automatic query splitting is a very powerful tool however not all queries are created equal.

In this simple example, it is a straightforward three-step process, but the feature can come at the cost of performance on more complex queries.
{% endhint %}


---

# 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.forestadmin.com/developer-guide-agents-python/agent-customization/relationships/under-the-hood.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.