Developing a new battery cell involves a complex design process with many variables, including materials, geometries, and performance trade-offs. Tests can be costly, and delays are critical.

Although traditional methods like Design of Experiments (DOE) help with planning, they often lack the speed and insights needed for quick decision-making.
 
This is where Monolith’s newest AI module, NTR-Optimisation, comes in. 
 
Built on the foundation of our trusted Next Test Recommender, NTR-Optimisation suggests the next best tests by actively exploring and exploiting your design space to surface high-performing configurations faster and more efficiently. 

Why Traditional DOE Alone Isn’t Enough

In high-dimensional design problems, DOE can’t always keep up. 

• The number of test combinations explodes exponentially with the number of dimensions 
• You often need to test blindly before identifying informative regions
  
  

The result? Weeks or months of testing that yield little actionable insight.

Introducing NTR-Optimisation: AI-Driven Design Space Exploration 

In this session, we’ll show how NTR-Optimisation uses statistical exploration and exploitation techniques to identify promising regions and guide you toward optimal designs—without brute-force testing. You’ll learn how it: 

• Combines exploration and exploitation intelligently using your real test data 
• Surfaces optimal combinations faster than manual DOE 
• Integrates directly into your Monolith workflow for seamless use