8 terms
Definitions in this topic
- Agentic AIAgent memoryAgent memory explained: short-term versus long-term memory, and why a stateless model needs it to feel consistent.
- ProductionContext compactionContext compaction explained: shrinking an agent's history while preserving the state needed to continue long work.
- Agentic AIContext engineeringContext engineering explained: how it differs from prompt engineering, and why it matters most inside agentic systems.
- ProductionContext rotContext rot explained: why LLM accuracy degrades as context grows, where lost in the middle comes from, and how to fight it.
- LLM foundationsContext windowContext window explained: what fills it up in a real system, and why bigger is not automatically better.
- LLM foundationsKV CacheKV cache explained: why transformer inference reuses attention states, and why long contexts consume serving memory.
- ProductionPrompt cachingPrompt caching explained: how reused prompt prefixes cut latency and input cost, and how to structure prompts for high cache hit rates.
- LLM foundationsPrompt engineeringPrompt engineering in 2026: why it is now one layer inside context engineering, not a standalone chat trick.