An AI panel debates your goal; a referee rules on re-checkable evidence
Stage
Startup
Not given
Founded
2026
Not given
Based in
FR
Not given
Pricing model
Free trial
Freemium
Pricing
€20 per agent per month, or €200 per agent per year (ten months for twelve). Each agent includes 1,000 inference credits per month. Custom plans available for specific deployment needs.
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.
Key features
Hybrid org chart organizing humans and agents
Human notices system for decisions and approvals
Agent-to-agent communication and delegation
Persistent memory layer across missions
190+ integrations with granular permissions
Scheduled tasks and recurring missions
Voice communication with agents
Projects with shared boards and wikis
Support for multiple AI models and cloud providers
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
What makes it different
Model, harness and cloud are independent choices
Agents can reason beyond tasks and workflows
Unified dashboard for entire AI and human workforce
Human-in-the-loop with automatic escalation
Multiple deployment options including self-hosted
Referee decides on evidence, not argument quality
Panel from different vendors fails in different directions
Atako
Referee.chat