Reference
The AI writing & communication glossary.
Plain-language definitions of the terms you actually encounter — from perplexity and burstiness to retrieval-augmented generation and tone axes. Maintained as a living reference.
28 entries · updated regularly
AI Writing
4 termsLarge Language Model (LLM)
A neural network trained on very large text corpora to predict the next token in a sequence, capable of producing fluent natural-language output.
AI Writing
Retrieval-Augmented Generation (RAG)
A pattern in which a model is given relevant context retrieved from your own sources before generating an answer.
AI Writing
Fine-Tuning
Further training a pre-trained model on additional task-specific examples to specialise its behaviour.
AI Writing
Hallucination
A hallucination is a fluent, confident-sounding statement produced by a language model that is factually wrong — a fabricated citation, a misattributed quote, an invented statistic, or a plausible but false claim.
AI Writing
AI Detection
1 termHumanization
1 termTone & Voice
3 termsTone
The emotional register and stance a piece of writing communicates, independent of its literal content.
Tone & Voice
Sentence Rhythm
The pattern of sentence lengths and structures in a passage, which controls pacing and reader attention.
Tone & Voice
Voice Consistency
The degree to which writing maintains a recognisable, repeatable identity across pieces, authors, and time — the sound of a publication or brand staying like itself.
Tone & Voice
Prompting
7 termsPrompt Engineering
The discipline of crafting model inputs — instructions, context, examples, and constraints — to produce reliably better outputs.
Prompting
Chain-of-Thought Prompting
A prompting technique that asks the model to reason step-by-step before producing a final answer, often improving accuracy on multi-step tasks.
Prompting
Few-Shot Prompting
Showing a model two to five worked examples of the desired input-output pattern before asking it to handle a new case.
Prompting
System Prompt
A persistent set of instructions that frames a model's behaviour across an entire interaction or product.
Prompting
Temperature
A generation parameter that controls how deterministic or varied a model's output is — lower values produce more predictable text, higher values produce more diverse and surprising text.
Prompting
Zero-Shot Prompting
Asking a model to perform a task with instructions alone, without showing any worked examples of the expected output.
Prompting
Role Prompting
A prompting technique that asks the model to respond as if it were a specific kind of expert, persona, or professional role.
Prompting
NLP Fundamentals
8 termsPerplexity
A measurement of how predictable a sequence of words is to a language model. Lower perplexity means the text follows patterns the model expects.
NLP Fundamentals
Burstiness
A measure of variation in sentence length and complexity across a passage. Human writing tends to be bursty; AI writing tends to be uniform.
NLP Fundamentals
Tokenization
The process of breaking text into the discrete units (tokens) a language model actually processes.
NLP Fundamentals
Embeddings
Numerical vector representations of text whose distances capture semantic similarity between pieces of content.
NLP Fundamentals
Vector Database
A specialised database optimised for storing high-dimensional vectors and retrieving nearest neighbours efficiently.
NLP Fundamentals
Semantic Search
Search that retrieves results by meaning rather than exact keyword match, typically using embeddings and vector similarity.
NLP Fundamentals
Context Window
The maximum amount of text — measured in tokens — that a language model can consider at once when generating its response, including both the prompt and the output.
NLP Fundamentals
Transformer Architecture
The neural network architecture underlying every modern large language model — characterised by self-attention layers that let the model weigh relationships between all tokens in a sequence simultaneously.
NLP Fundamentals
Content Strategy
3 termsAudience Fit
The degree to which a piece of writing matches the vocabulary, expectations, and decision-making style of its intended reader.
Content Strategy
AI Content Policy (search)
The set of guidelines that search engines use to evaluate AI-assisted content for ranking purposes.
Content Strategy
E-E-A-T
Google's evaluation framework for content quality — Experience, Expertise, Authoritativeness, and Trustworthiness — used by quality raters and reflected in ranking signals.
Content Strategy