Core terms

Definitions for the agent evaluation and developer terms used in these guides.

Versalist terms

Agent

A system that uses a model, instructions, tools, and state to complete a task.

Challenge

A repeatable task environment with inputs, constraints, tools, outputs, and evaluation criteria.

Episode

One recorded agent attempt against a challenge.

Trace

A time-ordered record of model calls, tool calls, events, logs, and artifacts from an Episode.

Evaluation

A defined method that measures an Episode result.

Judge

A test, rubric, model, or person that applies evaluation criteria to a result.

Reward

A structured evaluation result, such as a score, pass state, or failure category.

Skill bundle

A versioned set of reusable agent instructions, references, scripts, examples, and provenance data.

Baseline

A recorded result used as the reference for a later comparison.

Candidate

A changed agent, skill, tool, model, or configuration under evaluation.

Model terms

Large language model

A large language model (LLM) processes and generates language from the context that it receives.

Context window

The maximum token quantity that a model can process in one request.

Token

A unit that a model uses to process input and output.

Temperature

A sampling setting that changes output variation. Lower values usually produce more repeatable output.

Embedding

A numeric representation used for similarity search, retrieval, and grouping.

Hallucination

Model output that is incorrect or unsupported by the available evidence.

Inference

The operation in which a trained model processes an input and produces an output.

Fine-tuning

Additional model training on selected data for a task, domain, or output format.

Prompt and retrieval terms

System prompt

Instructions that define model behavior and constraints for a conversation or task.

Few-shot prompting

A prompt method that provides examples of the required input and output pattern.

Retrieval-augmented generation

Retrieval-augmented generation (RAG) finds relevant records and adds them to the model context before generation.

Developer terms

Application programming interface

An application programming interface (API) defines how software sends requests and receives results.

Command-line interface

A command-line interface (CLI) lets a user run Versalist commands from a terminal.

Model Context Protocol

Model Context Protocol (MCP) defines how an agent host communicates with external tools and data sources.

Bring your own key

Bring your own key (BYOK) means that a user supplies a provider credential for supported model calls.

Provider

An external service that supplies a model, tool, storage system, or compute service.

Was this page helpful?