> 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-market-lifecycle/discovery-and-the-picker.md). # Discovery and the picker ## Discovery and the picker NFA does not drop you into the entire prediction-market universe and wish you luck. It presents a **curated feed** of the markets it is actually built to forecast well, so you choose from a tailored shortlist rather than hunting for something to run. ### A feed tailored to where NFA has an edge The feed is assembled from the live market catalogue and then shaped to NFA's strengths. Markets where research, data, and reasoning can move the number are surfaced; the families where the crowd is already efficient are held back (more on that below). The result is a list where almost anything you pick is a market NFA can say something useful about. The feed is organized by category and can be sorted and filtered: by how soon a market resolves, by whether it is a simple yes/no market, and browsed with a live chance gauge on each card. Markets that group several independent questions open into their own sub-market picker so you can forecast each one cleanly. You can always paste a market link directly as well, but most people just pick from the feed. ### Where NFA chooses not to play Just as important as what the feed includes is what it leaves out. Some market families are held back because NFA has no reliable edge there: * **Single-game sports.** Outcome swings on the day are not something research moves. * **Very short-horizon crypto price and direction.** The market is already efficient over a few hours (see [Price models](/nfa-docs/live-data-and-adapters/price-models.md)). * **City temperature.** The resolving station routinely diverges from every freely available forecast, so there is no honest edge to claim. {% hint style="info" %} This restraint is a feature. A forecasting engine that claims an edge everywhere has one nowhere. The curated feed concentrates you on the markets where evidence, data, and reasoning can actually beat the crowd. {% 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/the-market-lifecycle/discovery-and-the-picker.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.