An AI panel debates your goal; a referee rules on re-checkable evidence
A small board for one developer and their agents
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
AT
Pricing model
Freemium
Freemium
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: $0 with 3 projects, 250 cards per project, 3 pages per project, Scratchpad, and full MCP access. Pro (Founder): $3.99/month or $34.99/year (27% savings) with unlimited projects, cards, pages, Scratchpad, and full MCP access.
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
Scratch notes for rough ideas
Automatic card creation with dependencies
Ready card querying for agents
Agent-written summaries on completion
Support for multiple coding agents
Agent switching mid-plan
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
Built specifically for solo developers with coding agents
Automatic dependency management keeps work in order