AI Engineering Glossary | Versalist Documentation

Use case

Shared vocabulary

This page is here so the docs and product routes use terms consistently.

Best pairing

Docs + challenges

Glossary terms land better when you can see them used in a real workflow.

Key themes

Prompting, evaluation, infra

Most terms cluster around those three layers.

Next route

/docs/skills

After the glossary, move into the skill or guide surfaces for context.

How to use this page

Read definitions here, then validate them against a real route.

Terms like rubric, gold item, tool use, RAG, or context window stay abstract until you see them inside a challenge, prompt, or workspace workflow. Use the glossary as a reset, not as the only place you learn the concept.

Read challenge docs

Core LLM concepts

These are the terms you will see most often when reading the public docs and using tool, prompt, or challenge surfaces across the product.

System design

Agentic workflow

A multi-step system where a model reasons, uses tools, and decides what to do next instead of producing a single isolated answer.

Prompting

Context window

The total amount of text the model can process in one request, including your prompt, supporting context, and generated output.

Protocol

MCP

Model Context Protocol. A standard way for editors or agent hosts to talk to external tools and data systems through a consistent interface.

Tooling

Tool use

A model capability that lets the system call deterministic tools or APIs while solving a broader task.

Prompting and retrieval terms

These concepts matter most when you are using the prompt library, public skill tracks, or challenge workflows that depend on prompt quality and grounded output.

Prompt structure

System prompt

The higher-order instruction that sets the behavior, role, and boundaries for the model across a conversation or workflow.

Prompt strategy

Few-shot prompting

Providing a small number of examples in the prompt so the model can imitate the expected style or output shape.

Reasoning pattern

Chain of thought

A prompting technique that asks for intermediate reasoning steps when the task benefits from more explicit decomposition.

Grounding

RAG

Retrieval-augmented generation. Relevant documents are fetched first, then inserted into context so answers are better grounded.

Model and runtime parameters

These terms show up when you are thinking about cost, performance, determinism, or how a provider should be used in a challenge or workspace flow.

Cost and scale

Token

The unit models use to process text. Cost, context-window size, and output length are usually expressed in tokens.

Output behavior

Temperature

A sampling parameter that affects how deterministic or varied the output is. Lower values are more stable; higher values are more creative.

Search and retrieval

Embedding

A vector representation of text or other content used for semantic search, retrieval, or similarity-based grouping.

Failure mode

Hallucination

When a model produces confident-sounding output that is unsupported, incorrect, or not grounded in the provided context.

Infrastructure and operations

These terms matter when the work moves beyond a single prompt and becomes something you want to run, monitor, or maintain over time.

Lifecycle

Inference

Running a trained model against live inputs to generate output. In practice, this is the “actual usage” phase of the model.

Customization

Fine-tuning

Further training a base model on task-specific data so it performs better in a narrower domain or format.

Ops

LLMOps

The operational layer around deploying, evaluating, monitoring, and governing LLM-based systems.

Data layer

Vector database

A storage system optimized for embeddings and similarity search, commonly used in retrieval-heavy applications.

Best next step

Use the glossary as a map, then move into a route where the term becomes concrete.

If you just learned a term like RAG, MCP, rubric, or gold item, open the related docs, skill, or challenge page next. The concept becomes much more useful once you can see it inside a real product surface.

Open skills docs