Skip to content
PreReqs

AI Engineering

Glossary.

Every acronym and term used across AI Engineering material, with the one-line meaning you should be able to say out loud.

TermExpansionWhat it means
LLMLarge Language ModelA transformer-based model trained on massive text corpora — the generation engine in Gen AI systems.
FMFoundation ModelA large pre-trained model adapted to many downstream tasks; what managed model-hosting services offer.
RAGRetrieval-Augmented GenerationGrounding generation in retrieved evidence rather than relying only on parametric model knowledge.
CRAGCorrective RAGA RAG variant where retrieved context is graded for relevance before generation, with rewrite/retry on a failing grade.
GraphRAGGraph-based Retrieval-Augmented GenerationRetrieval over an entity-relationship graph rather than passage similarity alone — valuable for multi-hop relational queries.
SFTSupervised Fine-TuningTraining on input-output example pairs to teach a model a behavior, format, or domain language.
PEFTParameter-Efficient Fine-TuningA family of methods (LoRA, adapters, prompt tuning) that adapt a model by training a small fraction of its weights.
LoRALow-Rank AdaptationFreezes base model weights and learns small low-rank delta matrices — a swappable, cheap-to-train adapter.
QLoRAQuantized LoRALoRA applied to a 4-bit quantized base model, enabling fine-tuning of larger models on smaller GPUs.
RLHFReinforcement Learning from Human FeedbackTrains a reward model from human preference rankings, then optimizes the LLM against it.
RLAIFReinforcement Learning from AI FeedbackLike RLHF, but the preference signal comes from another model rather than human raters.
ANNApproximate Nearest NeighborVector search that trades a small amount of recall for a large speed gain, instead of scanning every vector exhaustively. HNSW and IVF are common ANN index families.
HNSWHierarchical Navigable Small WorldAn approximate nearest-neighbor (ANN) graph index widely used for fast vector similarity search.
MRRMean Reciprocal RankAn evaluation metric scoring how high the first correct/relevant result ranked, averaged across queries.
LLMOpsLLM OperationsThe operational discipline around prompt/model versioning, evaluation gates, monitoring, and rollback for LLM systems.
HITLHuman-in-the-LoopA design pattern requiring explicit human confirmation before a system takes a consequential or irreversible action.
MCPModel Context ProtocolA standardized interface for exposing tools and context to an LLM or agent, independent of any one vendor's API.
A2AAgent-to-AgentA protocol pattern for structured communication and capability discovery between autonomous agents.
PIIPersonally Identifiable InformationData that can identify an individual — a first-class concern for redaction, authorization, and output scanning.
PHIProtected Health InformationHealth-related PII subject to additional regulatory controls (e.g. HIPAA) in applicable jurisdictions.