> For the complete documentation index, see [llms.txt](https://docs.zerve.ai/zerve-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.zerve.ai/zerve-docs/superagents/batches/tournament.md). # Tournament Pick the best of several finished pieces of work when quality is a judgement call. A **Tournament** batch picks the best of several finished pieces of work when there's no single number to decide it. Judges compare the entrants head to head and rank them. ## When it's used Use a Tournament when quality is a judgement call. For example: * Choosing the strongest of several drafts of an investment memo * Comparing different designs for a risk dashboard * Picking the most convincing of several research write-ups ## How it works 1. By default, the tournament builds the entrants itself, with each one produced by its own worker. It can also use entrants that already exist. 2. Each entrant **publishes** its work as an artifact. 3. [Judges](/zerve-docs/superagents/batches/how-judging-works.md) compare the published entrants head to head against written criteria. 4. The entrants are ranked, and the winner can be promoted to take over the role on the team. Tournaments always have a limit on the number of comparisons or the time they can take. ## What you see While it runs, the batch shows **Building entrants…** and then **Judging…**. Its results view is the **ranking explorer**, with each entrant's strength and confidence range, its wins, losses and draws, and a grid of how every entrant fared against every other. Rankings can be provisional while it's still running. ## Example request > Write four versions of this week's market briefing for our PMs and have them judged on accuracy, clarity and how actionable they are. If the entrants can be compared on a number, an [Exploration](/zerve-docs/superagents/batches/exploration.md) is usually faster and cheaper. --- # 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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.zerve.ai/zerve-docs/superagents/batches/tournament.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. 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.