---
title: "Glossary - AI deployment terms in plain English"
description: "Fifty-plus terms you will hear in any serious AI deployment conversation, defined in plain English. Every term has a stable anchor so partners can deep-link from their own proposals and customer materials."
url: "https://www.lmtek.com/sl/ai-solutions/foundations/glossary"
locale: "sl"
---

Prevod v pripravi Ta stran še ni v celoti prevedena v slovenščino. Vsebina je trenutno prikazana v angleščini. [Odpri angleško različico →](/ai-solutions/foundations/glossary)

Foundations · primer 04

# The terms  
in plain English.

Sixty-plus terms you will hear in any serious AI deployment conversation. Each one short. Each one stable-anchored - partners can deep-link from their own proposals to /glossary#fine-tuning and the link will hold.

Open in a second tab while reading the rest of the foundations track. Use Ctrl-F.

## A

5 terms

### [Agent #](#agent)

A model wrapped in a loop that can plan, call tools, observe results, and iterate towards a goal. The architectural pattern that turns "AI assistant" into "AI worker."

### [Agentic workflow #](#agentic-workflow)

A multi-step task in which an agent (or several) decomposes the goal, executes steps using tools, and reasons about the result before continuing. See the workload-patterns primer for the deployment shape.

### [Alignment #](#alignment)

The discipline of training a model to behave in line with intended values - to refuse harmful requests, to hedge appropriately on uncertainty, to follow instructions reliably. RLHF and DPO are alignment techniques.

### [API model #](#api-model)

A model accessed over the network through a provider's service. The model itself runs on the provider's infrastructure; you pay per token of input and output. Contrast with a self-hosted open-weight model.

### [Attention #](#attention)

The mechanism that lets a transformer model relate any token in a sequence to any other. Attention is what makes long-range coherence work - and what makes the context window expensive in compute and memory.

## B

5 terms

### [Base model #](#base-model)

A pre-trained model that has not yet been fine-tuned for a specific use case. Base models complete text plausibly but do not respond to instructions in a chat-shaped way without further training.

### [Batch inference #](#batch-inference)

Running many inference requests through a model together rather than one at a time. Higher throughput, higher latency per individual request - the right choice for offline classification or extraction.

### [Benchmark #](#benchmark)

A standardised test that scores model performance on a defined task. Useful for comparing models in the abstract; less useful for predicting how a model will perform on your specific data.

### [BF16 / FP16 / FP32 #](#precision)

Numeric precision formats. FP32 is full single-precision; FP16 and BF16 are half-precision and reduce memory at the cost of some numerical range. Most modern inference and training run in BF16 by default.

### [Bias #](#bias)

In an AI deployment context, the systematic skew in model outputs traceable to the training data, the labelling process, or the architecture. Bias is a property to be measured and managed, not eliminated.

## C

4 terms

### [Chat model #](#chat-model)

A base model that has been fine-tuned to respond to user messages in a conversational format, typically with instruction-tuning followed by alignment. The form most enterprise deployments use.

### [Classification #](#classification)

A workload pattern: structured output (a category, a score, a flag) from unstructured input. See the workload-patterns primer.

### [Context window #](#context-window)

The maximum number of tokens a model can process in a single call - input plus output combined. Models with larger context windows can read longer documents but cost more in compute per call.

### [Continual pre-training #](#continual-pretraining)

Continuing the training of a base model on additional domain data before fine-tuning. Used to adapt a general model to specialised vocabulary or low-resource languages.

## D

3 terms

### [Distillation #](#distillation)

Training a smaller "student" model to imitate a larger "teacher" model. The result is a model close to the teacher in capability but cheaper to run.

### [DPO #](#dpo)

Direct Preference Optimization. A simpler alternative to RLHF for aligning a model with human preferences. Same goal, less training infrastructure.

### [Drift #](#drift)

The slow degradation of a deployed model's quality over time as the real-world data, user behaviour, or domain shifts away from what the model was trained on. Detected through ongoing evaluation, addressed through retraining or model refresh.

## E

2 terms

### [Embedding #](#embedding)

A numeric vector representation of a piece of text such that similar texts have similar vectors. The mechanism behind semantic search and the retrieval step of RAG.

### [Evaluation (eval) #](#evaluation)

A repeatable test that scores model output against expected behaviour. The single most under-invested-in part of enterprise AI; without an eval, model swaps are hope.

## F

3 terms

### [Fine-tuning #](#fine-tuning)

Training a base model further on additional data to adapt its behaviour to a specific task or domain. See the workload-patterns primer for when this is worth doing.

### [Foundation model #](#foundation-model)

A large model pre-trained on broad data, intended to be the starting point for many downstream applications. The term overlaps with "base model" but emphasises the role rather than the training stage.

### [Function calling #](#function-calling)

A pattern where a model produces structured output describing a function to call rather than generating prose. The mechanism behind tool use in agentic workflows.

## G

3 terms

### [GPU #](#gpu)

Graphics Processing Unit. The hardware that does the parallel arithmetic that makes neural-network training and inference fast. The dominant cost driver in any non-trivial AI deployment.

### [Ground truth #](#ground-truth)

The labelled correct answers used to evaluate model output or to fine-tune a model. The quality of any evaluation is bounded by the quality of the ground truth.

### [Guardrails #](#guardrails)

Programmatic checks applied to model input or output to enforce policy - content filtering, PII redaction, output schema validation, refusal-to-answer for restricted topics. Sit alongside the model rather than inside it.

## H

2 terms

### [Hallucination #](#hallucination)

When a model produces output that is plausible but incorrect - fabricated citations, invented dates, confident wrong numbers. The native failure mode of next-token prediction.

### [Hybrid retrieval #](#hybrid-retrieval)

A retrieval approach that combines lexical matching (keywords) with semantic matching (embeddings). Often outperforms either alone for enterprise documents where exact terminology matters.

## I

3 terms

### [Inference #](#inference)

The act of running a trained model to produce output. Distinct from training (which produces the model). Inference is what costs you in production; training is what cost you to get there.

### [Instruction tuning #](#instruction-tuning)

Fine-tuning a base model on examples of instructions paired with appropriate responses. The training stage that turns a text-completion model into a chat-shaped one.

### [Interconnect #](#interconnect)

The high-speed network between GPUs in a multi-GPU server (and between servers in a cluster). NVLink, InfiniBand, and NVSwitch are common interconnect technologies. The interconnect often determines training throughput.

## J

1 term

### [Jailbreak #](#jailbreak)

A prompt crafted to make a model violate its alignment - produce restricted content, ignore guardrails, leak system instructions. An ongoing arms race between alignment training and adversarial prompting.

## K

1 term

### [KV cache #](#kv-cache)

Key-Value cache. The intermediate state a transformer accumulates while generating tokens, kept in GPU memory to avoid recomputation. The KV cache often dominates GPU memory consumption at long context lengths.

## L

3 terms

### [Latency #](#latency)

The time from request to response. In chat, often measured as time-to-first-token and tokens-per-second separately. Latency is bounded by hardware, model size, prompt length, and queue depth.

### [LLM #](#llm)

Large Language Model. A neural network trained on vast text data to predict the next token in a sequence. The substrate beneath every workload pattern in enterprise AI.

### [LoRA #](#lora)

Low-Rank Adaptation. A parameter-efficient fine-tuning technique that trains a small adapter layer rather than the full model. Faster, cheaper, and stackable - multiple LoRA adapters can be loaded against a single base model.

## M

4 terms

### [MCP #](#mcp)

Model Context Protocol. An open standard for letting models discover and call external tools and data sources. Increasingly the way agentic deployments connect to enterprise systems.

### [MLOps #](#mlops)

The operational discipline around deploying, monitoring, and retraining ML models. The AI-deployment equivalent of DevOps. Mostly partner work - system integrators and AI consultancies, rarely the customer alone.

### [Multi-agent #](#multi-agent)

An agentic deployment with several agents collaborating, often with defined roles (planner, worker, critic). More complex than single-agent; the orchestration framework matters a lot.

### [Multimodal #](#multimodal)

A model that handles more than one input modality - text plus images, text plus audio, text plus video. Increasingly the default for new models; the workload patterns extend to multimodal versions.

## O

1 term

### [Open-weight model #](#open-weight-model)

A model whose weights are published and downloadable, runnable on hardware you control. Llama, Mistral, Qwen, Mixtral are open-weight families. The architecture of choice for sovereign deployments.

## P

6 terms

### [Parameters #](#parameters)

The numerical weights that define a neural network. "Parameter count" is the rough capacity proxy - a 70-billion-parameter model has 70 billion numbers. Bigger correlates with capability but also with inference cost.

### [PoC #](#poc)

Proof of Concept. A narrow, fast experiment to validate technical feasibility before committing to production development. See the PoC-to-production primer for what one is and isn't for.

### [Pre-training #](#pretraining)

The first and most expensive stage of model training, in which a model learns general language patterns from a vast corpus. Done once, by the model maker, before any customer-specific work.

### [Prompt #](#prompt)

The input given to a model - often including a system instruction, conversation history, retrieved context, and the user's current message. Prompt engineering is the discipline of crafting these inputs for reliable output.

### [Prompt injection #](#prompt-injection)

An attack in which malicious instructions are embedded in data the model reads (a document, a web page, a user message) to override the system prompt or guardrails. The dominant security concern in agentic deployments.

### [Proprietary model #](#proprietary-model)

A model whose weights are not published. Accessed through the model maker's API. Top-end quality leads on broad tasks; sovereignty and cost-at-scale work against it.

## Q

2 terms

### [Quantisation #](#quantisation)

Reducing the numeric precision of a model's weights to save memory and speed up inference. INT8 and INT4 quantisation are common; quality cost varies by model and task.

### [QLoRA #](#qlora)

Quantised LoRA. Fine-tuning with LoRA adapters on top of a quantised base model. The cheapest path to fine-tuning any large model.

## R

4 terms

### [RAG #](#rag)

Retrieval-Augmented Generation. The pattern in which a retrieval system finds relevant documents, the model reads them, and the answer is grounded in your data. The most common pattern in enterprise AI.

### [ReAct #](#react)

Reasoning + Acting. A loop in which an agent alternates between thinking step-by-step and calling tools. The simplest agentic pattern that works.

### [Red-teaming #](#red-teaming)

Deliberate adversarial testing of a model - trying to jailbreak it, extract training data, induce harmful output. A required step before production deployment of any non-trivial system.

### [RLHF #](#rlhf)

Reinforcement Learning from Human Feedback. A training stage in which humans rate model outputs and the model is updated to prefer the highly-rated ones. The classic alignment technique; DPO is a simpler alternative.

## S

3 terms

### [Sovereign AI #](#sovereign-ai)

A deployment where the data, the model, and the inference infrastructure are all under the deploying organisation's control or jurisdiction. See the private-AI page for the data classes that force this.

### [Streaming #](#streaming)

Returning model output token-by-token as it is produced rather than waiting for the full response. Improves perceived latency in chat; less relevant for batch workloads.

### [System prompt #](#system-prompt)

The high-level instruction that frames a model's behaviour for a session - its role, the rules it should follow, the tone to use. Distinct from user messages; handled differently by the model.

## T

5 terms

### [Temperature #](#temperature)

A parameter that controls the randomness of model output. Low temperature (close to 0) produces deterministic, predictable output; higher temperatures produce more varied output. Set low for classification, higher for creative drafting.

### [Token #](#token)

The unit a language model reads and produces. Usually a few characters or part of a word. "Tokens" are the unit of cost in API pricing and the unit of capacity in the context window.

### [Tokens per second #](#tokens-per-second)

Throughput metric. How many tokens a model produces in one second on a given hardware setup. The metric chat deployments live and die by.

### [Tool use #](#tool-use)

A model invoking external functions or APIs as part of producing its response. The mechanism behind agentic workflows; usually implemented via function calling or MCP.

### [Transformer #](#transformer)

The neural network architecture underlying every current large language model. The attention mechanism is what distinguishes it. The architecture has been remarkably stable since 2017.

## V

2 terms

### [Vector database #](#vector-database)

A storage system optimised for finding embeddings similar to a query embedding. The "retrieval" half of RAG runs through one. Pinecone, Weaviate, Qdrant, pgvector are common options.

### [VRAM #](#vram)

Video RAM. The on-GPU memory where model weights, the KV cache, and activations live during inference. Insufficient VRAM is the most common reason a model fails to load on given hardware.

## W

1 term

### [Weights #](#weights)

The trained parameters of a neural network. The artefact you actually deploy. A model file is mostly its weights.