AI Engineering Wiki
Practical reference material for building, evaluating and governing modern AI systems.
AI Agents
A software system in which an AI model operates toward a defined goal using supplied context, tools and control rules.
AI Evaluation
Systematic measurement of AI system behavior against defined expectations -- retrieval, generation, tool selection, workflow execution, and final task success evaluated separately where possible.
AI Governance
The policies, controls, responsibilities and evidence used to ensure AI systems are developed and operated appropriately.
Continuous AI Learning
The controlled process of using observed performance, evaluations, and validated human corrections to improve an AI system -- not automatic training from every interaction.
Embeddings
Numerical representations of content positioned so that items with similar meaning sit near one another in a vector space.
KB Sandbox Vocabulary
Canonical definitions for the terms KB Sandbox uses -- Organization, Project, Workstream, Method, Agent, External Agent, Wiki, Ember, and more -- so everyone means the same thing by the same word.
Retrieval-Augmented Generation (RAG)
Combines information retrieval with an LLM so answers are grounded in retrieved evidence rather than model memory alone.