RedCrown.aiRedCrown.ai Docs Open the app

UI reference

The app.redcrown.ai screens and what each one does. The primary nav is Prove, Face-Off, Proofs, Models & keys, and Agent, plus an Advanced menu.

ScreenPathWhat it does
Prove/Paste a task and examples (or pick a sample) and prove the cheapest good-enough model.
Proofs/proofsYour runs and their ranked reports; mint or open a proof link, or run a saved experiment again on its stored examples.
Models & keys/advanced/modelsConnect provider API keys (BYO), AWS Bedrock, or a custom HTTP endpoint; the model registry and connection hub, one click from the primary nav.
Agent/connectMCP connector and CLI setup for running Prove from an agent or a terminal. Not where provider keys are connected, that is Models & keys above.
Experiment builder/advanced/experimentsPick the models, the quality metric and the bar yourself, instead of letting the scaffolder infer them.
Live traffic/advanced/live-trafficProxy endpoints, capture, shadow replay, and reviewer sessions.
Simulator/advanced/simulatorEstimate hosted and self-hosted cost for a model and token counts.
Upload/advanced/uploadImport an eval you ran elsewhere as a ranked, shareable run.
Workspace/advanced/workspaceOrganizations, members, and invites.
Billing/advanced/billingPlan and usage.
Proof (public)/proof/:tokenNo-login ranked proof report with receipts, provenance, and attestation download.
Reviewer (public)/review/:tokenNo-login blinded reviewer portal for a domain expert.

Last verified .