Context Minimization Principle
The core theory in the Context Cost research program.
Start with CMPInsights on software engineering in the AI era.
Essays on software design, context cost, and AI-assisted engineering.
By Leric Zhang.
The core theory in the Context Cost research program.
Start with CMPShort arguments around software architecture, AI coding agents, and context engineering.
Read the essaysContext Footprint and related prototypes that operationalize the theory.
See the projectsContext Cost → CMP → Context Footprint → AI-assisted software engineering.
Code generation by AI is no longer a prediction—it's observable reality. But the work of solving real-world problems with software isn't going away. A framework for understanding what remains human territory: value judgments, problem definition, and the future of the software practitioner.
Why do we need multiple AI agents when one LLM can do everything? The answer isn't about skills—it's about memory isolation and context sharding. Exploring how Multi-Agent systems solve the attention problem through context separation.
Exploring the fundamental principles of software design through the lens of cognitive science and information theory. Understanding how limited cognitive bandwidth shapes architecture and why Context Engineering is the endgame of software engineering in the AI era.