Context engineering curates the smallest high-signal token set for LLM tasks. The goal: maximize reasoning quality while minimizing token usage.
| Fundamentals | Understanding context anatomy, attention mechanics | context-fundamentals.md | | Degradation | Debugging failures, lost-in-middle, poisoning | context-degradation.md | | Optimization | Compaction, masking, caching, partitioning | context-optimization.md | | Compression | Long sessions, summarization strategies | context-compression.md |
| Memory | Cross-session persistence, knowledge graphs | memory-systems.md | | Multi-Agent | Coordination patterns, context isolation | multi-agent-patterns.md | | Evaluation | Testing agents, LLM-as-Judge, metrics | evaluation.md | | Tool Design | Tool consolidation, description engineering | tool-design.md |
Master in ingegneria del contesto per agenti AI: ottimizzazione dei token, modelli di degrado, compressione, sistemi di memoria, coordinamento multi-agente, valutazione. Da utilizzare durante la progettazione di agenti, il debug di errori di contesto o la creazione di pipeline LLM. Fonte: vibery-studio/templates.