# RedCrown Documentation

> RedCrown proves, on your own data, which model configuration is cheapest at equal-or-better quality. Each capability is documented three ways: the app UI, the redcrown CLI, and the MCP tools.

## Start here
- [Concepts](https://redcrown.ai/docs/concepts/): The objects RedCrown works with, and what prove means: Experiment, Run, Report, Receipts, Provenance, Proof link, and Attestation.
- [RedCrown documentation](https://redcrown.ai/docs/): RedCrown proves, on your own data, which model configuration is cheapest at equal-or-better quality. Docs for the UI, CLI, and MCP tools.
- [Quickstart](https://redcrown.ai/docs/quickstart/): Prove one task end to end in RedCrown, shown three ways: in the app UI, with the redcrown CLI, and via the MCP tools.

## Guides
- [Authentication](https://redcrown.ai/docs/guides/auth/): Sign in from the app, the CLI, and agents.
- [Benchmarks](https://redcrown.ai/docs/guides/benchmarks/): Run RedCrown's public weekly benchmarks, or a pinned subset of your own.
- [Bring your own data](https://redcrown.ai/docs/guides/bring-your-own-data/): Turn your CSV, JSONL, or media files into a scored dataset.
- [Connect providers](https://redcrown.ai/docs/guides/connect-providers/): Bring your own provider keys so runs use your accounts and rates.
- [Cost simulator](https://redcrown.ai/docs/guides/cost-simulator/): Estimate hosted and self-hosted cost for a model and token counts.
- [Run a Face-Off](https://redcrown.ai/docs/guides/face-off/): Paste a plain-language task, run it across top models, and get a rubric-ranked verdict with a shareable proof.
- [Import external results](https://redcrown.ai/docs/guides/import-external-results/): Turn an eval you already ran in any harness into a ranked, shareable RedCrown run.
- [Inspect runs and reports](https://redcrown.ai/docs/guides/inspect-runs-and-reports/): List runs and open their ranked reports and receipts.
- [Live proxy and collect](https://redcrown.ai/docs/guides/live-proxy-and-collect/): Capture live traffic and shadow-replay it across candidate models.
- [Prove a task](https://redcrown.ai/docs/guides/prove-a-task/): Run every candidate model on your task and prove the cheapest one that clears your bar.
- [Reviewer portal](https://redcrown.ai/docs/guides/reviewer-portal/): Send a run to a non-technical domain expert for a blinded verdict.
- [Run and rank](https://redcrown.ai/docs/guides/run-and-rank/): Run an experiment spec and read the ranked report.
- [Share a proof](https://redcrown.ai/docs/guides/share-a-proof/): Mint a no-login proof page from a completed run.
- [Signed attestation](https://redcrown.ai/docs/guides/signed-attestation/): Download a tamper-evident, independently verifiable signed proof.
- [Try a sample](https://redcrown.ai/docs/guides/try-a-sample/): See a proof in one step with a public sample, no data, no keys, no account.
- [Workspaces and billing](https://redcrown.ai/docs/guides/workspaces-and-billing/): Organize work into workspaces and manage your plan.

## Reference
- [CLI reference](https://redcrown.ai/docs/reference/cli/): Every redcrown subcommand and flag.
- [MCP reference](https://redcrown.ai/docs/reference/mcp/): Every RedCrown MCP tool at mcp.redcrown.ai.
- [UI reference](https://redcrown.ai/docs/reference/ui/): The app.redcrown.ai screens and what each one does.