Glossary
The vocabulary of keeping humans and AI agents in step, defined plainly.
- ADR (Architecture Decision Record)An ADR is a short document recording one architectural decision (what you chose, what you rejected, and why), kept in version control next to the code.
- Agent MemoryAgent memory is what an AI agent retains across sessions, unlike context, which is loaded fresh into each request. Memory persists; context is per-run.
- Context EngineeringContext engineering is deliberately assembling the information an AI model needs — instructions, constraints, decisions — and keeping it true over time.
- Context WindowThe context window is the maximum text, in tokens, a model can consider in one request: its working memory. Anything outside it is invisible to the model.
- Decision DriftDecision drift is the gap between what a team decided and what its code, docs, and AI agents actually do — decisions made but never delivered to the work.
- MCP (Model Context Protocol)MCP is an open protocol that lets AI applications connect to external tools and data through one standard interface — agents fetch context and act on demand.
- PRD (Product Requirements Document)A PRD is the document that describes what a product or feature should do and why: the requirements, scope, and constraints a team agrees on before building.
- RAG (Retrieval-Augmented Generation)RAG is a technique where a system retrieves relevant documents and adds them to the model's prompt before it answers, grounding output in fetched text.
- Spec DriftSpec drift is when code and its written spec stop agreeing: the spec says one thing, shipped behavior does another, because nobody updated the spec.