Back to Applied AI Engineering
🗂️
Phase 3
Context Engineering & Memory
What actually belongs in a context window, how short-term, long-term, and semantic memory differ, and how to keep token spend and coherence under control across long sessions.
1
Context Architecture & Assembly
What belongs in a context window — instructions, tool definitions, history, retrieved documents — and why the order you assemble them in changes model behavior.
context-engineeringcontext-windowcontext-assembly
2
Memory Systems: Short-Term, Long-Term & Semantic
Why a session's conversation buffer, a user's persisted preferences, and a searchable store of facts are three different memory mechanisms, not one.
memorysemantic-memorypersonalization
3
Token Budgeting, Compression & Selective Loading
The eviction, summarization, and compression strategies that keep a long-running agent coherent and cut its per-session token spend.
token-budgetingcompressioncontext-rot