An AI panel debates your goal; a referee rules on re-checkable evidence
Your company's collective intelligence
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
FR
Pricing model
Freemium
Paid
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.
From €199 per seat per month (12-month commitment, prices excluding VAT). Founding customers receive 2 months free per seat, with guided installation included.
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
Unified client records with documents, emails and meetings
Automatic email sorting and organization
Video call transcription
AI agents that read documents and fill forms
Automated routines and recurring tasks
OAuth integrations with 52+ external tools
Complete audit trail of all actions
Permissions-based access control
GitHub and Slack integration for routine triggers
Multi-AI model support
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
Collective intelligence for entire teams, not just individual users
Deployed on your own infrastructure by their engineers
AI works under your control with manual approval before actions
Consolidates multiple tools into single workspace with shared memory
Forward deployed engineers setting up workspace for your business
Referee.chat
Standards