Skip to content

Welcome to the AmaDema AI Training Programme

Material Science Prompt Engineering

Welcome to this intensive training course on the responsible and effective use of Artificial Intelligence (AI) in materials science and nanotechnology R&D.

The term Artificial Intelligence refers to computer systems that can perform tasks typically requiring human intelligence, such as understanding language, recognising patterns, and making decisions. While the AI field has many years of research and development behind it, today's increased popularity is largely driven by generative AI models; systems that can create new content like text, images, and code based on the patterns they've learned from vast amounts of data.

You've probably heard of and used tools like ChatGPT and Copilot—here we'll learn how to use them effectively for materials science applications whilst protecting intellectual property and maintaining sustainable practices.

AmaDema AI Guidance

This course is built on the foundation of responsible AI use. Our approach emphasises:

  • Precision: Engineering prompts for rigorous scientific outputs
  • Security: Protecting intellectual property and synthesis data
  • Sustainability: Minimising the environmental footprint of AI usage
  • Innovation: Accelerating R&D through intelligent automation

Course Structure

This programme is structured as a four-day intensive workshop (1.5 hours per day), targeting Material Scientists and R&D staff.

Day 1 & 2: Precision Engineering & Operational Safety

Transform from "casual chatters" to "AI Engineers" who can systematically extract value from models. Learn:

  • AUTOMAT Framework: Structured prompt engineering for scientific outputs
  • CO-STAR Framework: Context-rich communication
  • Responsible AI: Risk management and IP protection
  • The Red List: Data security protocols

Day 3 & 4: Technical Architecture & Sustainability

Understand the engine room of these technologies to promote sustainable and efficient usage:

  • NLMs vs LLMs: Choosing the right tool for the task
  • Green AI: Minimising carbon footprint
  • Optimisation Strategies: Efficient prompt design
  • Practical Applications: Real materials science workflows

Learning Objectives

By the end of this course, you will be able to:

  • Understand what LLMs are and their key capabilities and limitations in scientific contexts
  • Apply the AUTOMAT and CO-STAR frameworks to create high-fidelity scientific prompts
  • Protect intellectual property whilst leveraging external AI tools
  • Implement Green AI practices to minimise environmental impact
  • Engineer prompts for routine tasks: literature synthesis, protocol formatting, data analysis
  • Navigate ethical considerations including bias, privacy, and data rights

Getting Started

  1. Read the Fundamentals section to understand LLM basics
  2. Set up the Sandbox environment for hands-on practice
  3. Follow the Day-by-Day curriculum at your own pace
  4. Practice with real examples from materials science
  5. Download the Cheat Sheet for quick reference

Workshop Format

This is an interactive workshop. You'll practice with a local, secure AI model using real materials science data. No external data sharing required.

Ready to begin? Start with What are LLMs? →