> 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/concepts-and-glossary.md).

# Concepts and glossary

## Concepts and glossary

A short, shared vocabulary. These terms mean specific things in NFA, and the docs use them precisely.

{% hint style="warning" %}
**Divergence is not edge.** Divergence is the signed gap between the engine and the market *before* a market resolves. Edge is a *realized* improvement in accuracy, and it only exists *after* settlement. The product never calls a pre-resolution number "edge."
{% endhint %}

### Core terms

| Term                  | Meaning                                                                                                                                              |
| --------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Forecast**          | A calibrated probability distribution over a market's outcomes, produced by one engine run.                                                          |
| **Advocate**          | An AI persona that argues for exactly one outcome. Advocates are generic archetypes, never real named people.                                        |
| **Judge**             | The impartial model that reads the debate and rules a calibrated distribution.                                                                       |
| **Crux**              | The single most decisive unresolved question the judge identifies mid-debate, then researches.                                                       |
| **Anchor**            | A firm input injected into a forecast: either a reference-class base rate or a live measured value from a data source.                               |
| **Base rate**         | The historical reference-class prior for a question.                                                                                                 |
| **Live metric**       | A current measured value fetched from a structured data source.                                                                                      |
| **Divergence**        | The signed gap between the engine's probability and the market's implied probability, before resolution.                                             |
| **Edge / skill**      | A realized accuracy improvement over the market, measured only after a market resolves.                                                              |
| **Brier score**       | The standard accuracy measure for probabilistic forecasts. Lower is better; 0.25 is a coin flip on a binary.                                         |
| **Self-verification** | An independent check that audits a divergent forecast and can confirm or veto it.                                                                    |
| **Quality badge**     | A read-time tier describing how much to trust a run: verified edge, data-anchored, unverified edge, matches market, research-based, or do not trade. |
| **Credit**            | The prepaid unit that pays for a run.                                                                                                                |
| **$NFA**              | The platform token, used for staking, governance, and the reward rails.                                                                              |

### Divergence and edge

The two most important words to keep straight. **Divergence** is how far the engine sits from the market right now; it is a claim, not a result. **Edge** is how much more accurate the engine turned out to be once the market resolved; it is a result, not a claim. NFA is careful never to present one as the other.


---

# 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/concepts-and-glossary.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.