> For the complete documentation index, see [llms.txt](https://nfa.gitbook.io/nfa-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://nfa.gitbook.io/nfa-docs/appendix/design-principles.md).

# Design principles

## Design principles

Everything in this reference follows from a small set of commitments. They are worth stating on their own, because they explain why NFA is built the way it is.

* **Independent by default.** The engine forms its own view from evidence and debate, so its number is a real second opinion rather than an echo of the crowd.
* **Grounded in evidence.** Forecasts are built from research and, wherever possible, anchored to authoritative live data rather than model recall.
* **Willing to doubt itself.** A separate check audits every meaningful divergence and can veto the engine's own forecast. NFA would rather withhold a call than serve an over-confident one.
* **Measured honestly.** Accuracy is scored against the market, forward-tested, with exclusions recorded rather than hidden. When NFA is wrong, the record says so.
* **Transparent.** Every forecast comes with a reasoning trace, and every run records what it did, so a result can be audited rather than taken on faith.
* **Non-custodial.** NFA gives you analysis and a place to act on it. It never takes custody of your funds.
* **Disciplined about edge.** NFA forecasts where research and data can beat the crowd, and deliberately sits out the markets where they cannot.

{% hint style="info" %}
The throughline is trust through verifiability. NFA does not ask you to believe it is accurate. It shows its work, checks itself, and keeps an honest score.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://nfa.gitbook.io/nfa-docs/appendix/design-principles.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.