AI Glossary

Fact-check status

Reviewed claim by claim on 2026-09-02 against the primary or official sources identified inline as S1 and S2. Recommendations are design guidance unless a cited standard makes them normative.

Key jargon

Term	Plain-language meaning
Term	A word or phrase with a defined meaning in a field. S1
Definition	A concise statement of what a term means in this curriculum. S1
Alias	An alternative name or abbreviation pointing to the same concept. S1
Scope note	A clarification limiting how a definition should be interpreted. S1

Key concepts

Definitions should explain distinctions that change design or evaluation decisions. S1
Return to the lesson context because one term may have different meanings across research, products, and organizations. S1

Concept map

flowchart LR
    A["Encounter unfamiliar term"] --> B["Read plain definition"]
    B --> C["Follow lesson context"]
    C --> D["Apply distinction in practice"]

Diagram semantics verified against S1 and S2 on 2026-09-02.

Term	Meaning in this curriculum
Agent	System in which a model selects some actions or next steps from observations and available tools S1
AI harness	Software/policy around models for context, tools, state, permissions, validation, recovery, observability, and evals S1
CAG	Cache-augmented generation; reuse of prepared context/cache where supported, not a universal replacement for retrieval S1
Context	Information available to one model invocation S1
Embedding	Vector representation optimized so some relationships are useful geometrically S1
Evaluation	Structured measurement of system behavior against defined tasks and criteria S1
Fine-tuning	Additional optimization of model parameters for data or behavior objectives S1
Foundation model	Broadly trained model adaptable to many downstream tasks S1
Grounding	Connecting output to supplied evidence or an external source of truth S1
Hallucination	Unsupported or false generated content presented as grounded S1
Inference	Running a trained model to produce predictions/output S1
LLM	Large language model, usually trained to model token sequences S1
Memory	Persisted state or information available beyond one invocation; always qualify its type S1
MCP	Model Context Protocol, an interoperability protocol for hosts/clients/servers and capabilities S1
Multimodal	Processing or generating more than one modality such as text, image, audio, or video S1
Prompt	Instructions and/or data supplied to a model; only part of the context S1
RAG	Retrieval-augmented generation; retrieved material is supplied to a generator S1
Reranker	Component that reorders retrieval candidates using an additional relevance model or rule S1
Structured output	Model output constrained to a machine-validated schema S1
Token	Model/tokenizer-specific unit represented by an integer ID S1
Tool	External capability exposed through a schema and executed by the host/harness S1
Transformer	Attention-centered neural architecture introduced for sequence transduction and widely extended since S1
Workflow	Code-defined sequence or graph of steps and transitions S1