Rachana Vidhi, PhD
Co-founder & President
- 10 US patents in batteries and renewables enabling 1,000MW+ of BESS deployments
- PhD Chemical Engineering (USF), Master's in Management (Harvard), IIT Kharagpur
- Former Director, NextEra Energy
How It Works
Physics based empirical models
Modeling Approach
- Physics-informed ML on real operations
- Dynamic re-training as project ages
- Holistic compute across entire project
- Long-term context for inference
Training Pipeline
Pre-training
Lab cycling data, simulated conditions
↓
Fine-tuning
Historical telemetry, per-project
↓
Expert Validation
Domain experts + physics guardrails
- Pre-trained models for quick onboarding
- In-built data pipelines for telemetry
- Fine-tuning with feedback closes the loop
Agentic Interface
Natural language question
↓
LLM interprets intent
Routes to the right tool
↓
ML models + RAG
Computation + project context
↓
Precise answer
Traceable, auditable results
- LLM handles intent, not computation
- Tool calling routes to validated models
- RAG pulls project-specific context
- No hallucinated numbers in decisions
