Features
Autonomous operation of physical businesses (cafés, radio stations, retail)
Vending-Bench 2: long-horizon business simulation benchmark
Vending-Bench Arena: competitive multi-agent benchmark
Blueprint-Bench 2: spatial intelligence evaluation from photos to floor plans
Butter-Bench: household robot delivery task evaluation
AI-operated radio stations (Andon FM) with 24/7 autonomous DJ
AI-run cafés with full operational autonomy (Andon Café)
AI-run retail store with 3-year lease (Andon Market)
Safety protocol testing for autonomous organizations
Integration with frontier AI models (Gemini, Claude, GPT, Opus, Fable)
Published case studies and failure analysis reports
Hardware vending machines bundled with AI control software
Real-world evaluation of Gemini 3.1 Pro, Opus 4.8, Fable 5, GPT-5.5
Support for multi-modal agent evaluation (spatial, robotic)
Open-source benchmarks and datasets
Sparkpage synthesis from multiple sources with citations
Deep research mode with transparent source links
Conversational AI search with follow-up questions
AI Employee for no-code internal tool creation
Custom Super Agent creation without coding
AI Slides with Canva and Figma integration
AI Sheets for data analysis and visualization
AI Docs for document generation
AI Pods for podcast generation
Clip Genius for AI video editing
AI Designer for design creation
AI Browser with ad blocking and agentic browsing
Cross-platform support: web, mobile app, desktop app
Google Workspace integration (Drive, Docs, Sheets)
Canva and Figma integration
