Features
Multi-agent competition (Scout, Builder, Verifier, Critic, Judge)
Structured execution packs with rationale, risks, evidence, next actions
Five tuned launchpads (Business Launch, Get Customers, Plan MVP, Diagnose System, Pick Option)
Public or private runs (privacy control)
Credits never expire (one-time) or roll over up to 2 months (subscriptions)
Leaderboard for public runs
Multi-run side-by-side comparison (Power and Studio tiers)
Priority queue (Studio tier, runs start in <30s)
3 team seats included (Studio tier)
Outputs not used to train AI models
Two free runs with no credit card required
Focused, Balanced, and Tournament run depths
Private by default on paid plans
Autonomous strategic report generation (Sakana Marlin)
Multi-agent LLM orchestration matching frontier models (Fugu Ultra)
Recursive Self-Improvement (RSI) Lab for autonomous AI research
Conductor system for natural language agent orchestration
Japan-based data residency and export control compliance
Finance multi-agent proposal generation with SMBC Group
AI-powered information analysis with DEEP DIVE
CoffeeBench benchmark for LLM agents in multi-agent economic environments
Autonomous model orchestration avoiding export control risks
Research-stage speech-to-speech AI with KAME architecture
