# AI Modular Infrastructure

<figure><img src="/files/bRMxeyA1ULMkbityb32Y" alt=""><figcaption></figcaption></figure>

**In-Network Timeline Indexer**&#x20;

Timeline: Refers to the chronological order of posts, usually displayed on a user's profile in a social media platform and In-Network posts are the messages, pictures, or updates shared by people within a specific social network or platform.

This module generates recommendations of in-network posts for the timeline of the user using the mobile app.

**Ex-Network Timeline Content Recommendation Mixer**

In the context of social media, "Ex-Network" refers to people or content that is not part of your group of followed users. This module is similar to the In-Network module above but recommends content from users that you do not follow.

**AN XX-Like**&#x20;

This Recommender sub-module is tasked with recommending content, users ‘may also like’ based on the ML analysis of their previous actions and actions of users that the machine learning algorithm has determined as being alike in multi-dimensional vector space.

**ML Equalizer**

This module takes all of the recommendations from the In-Network, Ex-Network, and likes analysis and does one final analysis to generate the most probable posts that elicit user interaction.

**Filtering /  Heuristics**

This module serves as the last stage in the process, considering user preferences and post-filtering settings. It ultimately achieves a delicate equilibrium by incorporating a mix of advertisements into the user's timeline feed.


---

# 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://aann-ai.gitbook.io/social-authenticity-network/an-social-authenticity-solutions/an-ai-powerhouse/ai-modular-infrastructure.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.