> 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/the-forecasting-engine/quality-tiers.md). # Quality tiers ## Quality tiers Not every forecast deserves the same confidence. NFA grades each run and shows the result as a quality badge, so you can tell at a glance whether a call is backed by data, backed by reasoning, or one the engine does not stand behind. This is process quality, not a trade recommendation. ### The tiers | Badge | Meaning | | ------------------- | --------------------------------------------------------------------------------------------------------------------------------------- | | **Verified edge** | The forecast diverges from the market and an independent check found evidence supporting the engine's side. | | **Data-anchored** | The forecast is tied to a live measured value from a structured data source, not just model reasoning. | | **Unverified edge** | A meaningful divergence that rests on argument. The evidence neither confirmed nor refuted it, so it is served with that caveat. | | **Matches market** | The engine sees roughly what the market prices, with no meaningful divergence to flag. | | **Research-based** | A call the engine reasons out when no structured data feed covers the market, resting on researched evidence rather than a live anchor. | | **Do not trade** | The market is effectively already decided, or the engine's own check refuted the divergence. Trading on the run is blocked. | ### How the badge is decided The badge is derived from what actually happened during the run: whether a structured data source anchored the forecast, and what the [self-verification](/nfa-docs/the-forecasting-engine/self-verification.md) step concluded about any divergence. A do-not-trade badge takes precedence over everything else, because a blocked call should never look tradeable. {% hint style="info" %} The badge changes how a run is treated downstream. A do-not-trade run is kept out of the headline accuracy stats when the block was the engine's own veto, and it is not billed when the veto was caused by an engine defect. See [Trading and portfolio](/nfa-docs/trading-and-portfolio.md) and [The economy](/nfa-docs/the-economy.md). {% endhint %} ### Divergence is not a promise A badge describes how the forecast was produced. It is never a signal to trade. Even a verified-edge call can be wrong, and the risk is always yours. The badges exist so that confidence is legible, not so that it can be outsourced. --- # 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/the-forecasting-engine/quality-tiers.md?ask=&goal= ``` `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.