An AI panel debates your goal; a referee rules on re-checkable evidence
Publish documents for feedback, pull edits and comments back into your agent
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
GB
Pricing model
Freemium
Not given
Pricing
Free: $1.00 starting credit once. Credit plans from $10 top-up with no expiration. Your own key: 5% infrastructure fee after the first $5.00 of usage.
Free plan: $0, up to five active documents, documents up to 4 MB, 1 GB storage, last ten versions restorable, invite up to ten people per document. Pro plan: $10 USD per month (billed as $120 per year) or $12 USD per month (billed monthly), unlimited active documents, documents up to 16 MB, 50 GB st
Key features
Panel of up to six AI models from different vendors
Referee rules on re-checkable evidence only
Searches academic databases: arXiv, OpenAlex, Crossref, Europe PMC
Executes Python code to verify claims
Customizable acceptance standards
Matches pause and resume without losing work
Shared ledger prevents re-derivation
Spending limit per match
Publish HTML or Markdown files with shareable links
Readers can leave comments and edit text with author permission
Pull edits and comments back as structured data
MCP server for agents without file or command access
Custom share links with passwords and expiry dates on Pro
Version history with restore capability
Publish entire folders as sites on Pro plan
Connect to external APIs and embed sites on Pro
What makes it different
Referee decides on evidence, not argument quality
Panel from different vendors fails in different directions
Stuck is a targeted question, not model thrashing
Cost grows with ledger, not round count
Published matches become research record
Documents stay active at stable links across multiple published versions
Works natively with AI coding agents without requiring manual context management
CLI does not require Node, Python or other runtime dependencies
Screenshots in comments are listed by ID and only fetched on request