The Physics of Requirement Sciences Through Application [...]
summary
Proposes a concrete SCRIPT methodology (Subject/viewpoint, iterative Refinement, Importance of context, Purpose/objectives, Templates/start points) to tame GenAI risks like hallucinations and token exhaustion, and shows a live demo app and book on GitHub. Uses GenAI with Node.js Express, n8n workflows and templates (MCP) as tooling. Claims colleagues hit between 160 and 100,000 lines generated in a weekend and reports one application with 10,000 lines vs 5 lines actually hand-authored, arguing iterative subject-first prompts cut effort.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 1:51GenAI impact on productivity
- 3:59Newton’s laws for software
- 7:52GenAI math foundations and risks
- 8:56SCRIPT methodology
- 10:43SCRIPT components
- 13:56SCRIPT examples
- 16:49Summary and tools
- 18:53Q&A
related talks
44mSpec-driven Development: How AI Changed Everything (And Nothing)
21mRevolutionizing software creation: Harnessing the power of GenAI
41mImproving DevOps workflows with GenAI
30mUsing AI to Create Better Requirements and Designs
12mNavigating the World of AI Development Without Going Insane
01h 02mArchitecture Patterns for AI-Powered Applications
47mThe Art of Prompt Engineering: Best Practices for Effective AI Interactions
47mAI-Powered Software Development From the Trenches