# Megabrain Investors Picks

<figure><img src="/files/Cp1YKCSjCyVdUkeBNTPU" alt=""><figcaption></figcaption></figure>

### What it does for you

Megabrain lets you “chat” with AI versions of well-known investors and market personalities. Each persona carries its own style (aggressive, cautious, contrarian, or narrative-driven) and responds in that voice.

This makes it both entertaining and instructive, as you can test how different strategies interpret the same market data.

The experience includes:

* **Character-driven insights**: AI agents modeled on legendary investors and market personalities.
* **Conversation starters**: pre-set prompts for fast engagement (e.g., market-moving tweets, sector views, global trade).
* **Generated commentary**: real-time responses aggregated from data sources, then expressed in the voice of the persona.
* **Feedback layer**: users can upvote, downvote, or share outputs, which reinforces credibility scores.

<figure><img src="/files/aVfXoD6p0viWmzyX7TkF" alt=""><figcaption></figcaption></figure>

This feature blends intelligence with narrative simulation. Traders can stress-test their views against the “voice” of an archetype, while the community contributes to a sentiment layer that reveals bias and conviction in unique ways.

### How it works

Megabrain is powered by narrative simulation agents. EDGM’s router classifies the query as simulation, retrieves relevant market and news data, and activates the Sentiment/Narrative sub-agent. That data is reformulated into commentary styled to the chosen persona’s bias and tone.

The result is a living layer of market dialogue grounded in data, but colored by personality.


---

# 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://gitbook.edgen.tech/edgen-litepaper/store/megabrain-investors-picks.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.