# EDGM: The Commander Model

The **Efficient Decision Guidance Model (EDGM)** is the core of Edgen. It is not one giant model but a structured process that routes every request through layers of reasoning, agents, and tools. It is the operating system abstracting away complexity, allowing human users to make the most out of markets.

<figure><img src="/files/oITkYCpEsa2ervW9tHiw" alt=""><figcaption></figcaption></figure>

### Reasoning Model

A dynamic investment framework interprets user queries and assigns them to the right agents.

### Specialized Agents

Each agent has a clear role: long-term memory, macro, technical, fundamentals, momentum, sector, or knowledge. These specialists can be expanded without limit.

### Guidance & Knowledge Models

The Guidance Model decides which external market tools to call, while the intern knowledge model retrieves and organize relevant research it has stored. Both include filings, earnings, technical indicators, social data, and web search.

### Market Tools & LLMs

Tools execute and collect information. State-of-the-art LLMs synthesize results into text, charts, tables, or reports on the Edgen interface.

### Output and Feedback

[The system returns a single coherent answer.](mailto:undefined) Every step is logged, and feedback (manual or reinforcement learning) improves future performance.

***

This architecture achieves three outcomes:

* **Scalability**: more agents and tools can be added without redesigning the system.
* **Transparency**: each stage is explicit and reviewable.
* **Compounding**: reinforcement learning and memory make the system sharper with use.

EDGM turns fragmented processes into one coordinated intelligence pipeline, delivering outputs that are precise, adaptive, and built for markets.


---

# 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/technical-principles/edgm-the-commander-model.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.