# Search
[Search](mailto:undefined) is Edgen’s question-and-answer interface to the markets. A user can type a natural question (about a stock, a token, or an investment theme) and receive a structured response in seconds.
Behind each answer, agents retrieve the relevant layers: filings and earnings, on-chain flows and derivatives, sentiment and curated news. EDGM links them into one narrative. Instead of fragments, the output carries context that traders can act on and engineers can trace.
Search operates on two levels:
* **Direct Answers**: fast synthesis for frequent queries. A trader asking “What drives ETH this week?” gets a concise view that merges flows, funding, and narratives. Hours of manual checking compressed into one answer.
* **Deep Research**: higher resolution analysis. Multiple agents scan filings, social data, and market structure to assemble a full report. The result is an auditable document with sources, tables, and a single actionable score.
By joining natural language with structured financial and on-chain intelligence, Search makes the market explorable in any direction. There is no need to switch between terminals or APIs. One query becomes one coherent answer, with the depth adjustable to the task.
---
# 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/inside-edgen/search.md?ask=
```
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.