[00] Glossary
AI and data terms, explained
From LLMs and RAG to embeddings, agents and model drift, the words you will meet when planning or buying an AI project, in plain English.
A
02 terms
- AI agent#
- An AI system that plans and carries out multi-step tasks by calling tools and APIs, such as looking up an order, updating a CRM record or drafting an email, rather than only answering a question. Good agents have limited permissions and ask a person before irreversible actions.Learn more
- Artificial intelligence (AI)#
- Software that performs tasks that normally need human judgement, such as understanding language, recognising images, making predictions or choosing the next step in a process.Learn more
B
01 term
- Business intelligence (BI)#
- The tools and processes that turn business data into reports and dashboards, so managers can see sales, costs and performance in one place instead of compiling spreadsheets.Learn more
C
05 terms
- Chatbot#
- Software that holds a conversation with customers or staff on a website, WhatsApp or an app. Modern chatbots use an LLM to understand free-text questions and answer from approved company content.Learn more
- ChatGPT#
- OpenAI's chat product built on its GPT models. Businesses usually integrate the same models through the OpenAI API, which lets them add their own data, rules and branding.Learn more
- Computer vision#
- AI that interprets images and video: reading documents, counting items, inspecting products for defects or recognising objects and people in a camera feed.Learn more
- Context window#
- The amount of text, measured in tokens, that an LLM can consider in one request, including the instructions, any retrieved documents and the conversation so far.Learn more
- Custom AI vs off-the-shelf AI#
- Off-the-shelf AI is a ready-made product used as it is. Custom AI is built or adapted for your data, workflows and systems. Many projects combine the two: an existing model with custom retrieval, rules and integrations.Learn more
D
04 terms
- Data annotation#
- Labelling raw data, such as drawing boxes around objects in images, tagging text by topic or transcribing audio, so a model can learn from it or be tested against it.Learn more
- Data residency#
- Where your data is stored and processed. Some industries and countries require data to stay in a particular region, which affects which cloud regions and AI models can be used.
- Data warehouse#
- A central database that collects data from sales, finance, operations and other systems in a consistent format, ready for reporting and analysis.Learn more
- Deep learning#
- A branch of machine learning that uses neural networks with many layers. It powers image recognition, speech recognition and large language models.Learn more
E
03 terms
- Embedding#
- A list of numbers that represents the meaning of a piece of text or an image. Items with similar meanings have similar embeddings, which is how semantic search and RAG find relevant content.Learn more
- ETL (extract, transform, load)#
- The process of pulling data out of source systems, cleaning and reshaping it, and loading it into a warehouse or analytics tool. ELT does the transformation after loading.Learn more
- Evaluation set#
- A fixed collection of real questions or examples with known correct answers, used to measure a model's accuracy before launch and to check that changes do not make it worse.Learn more
F
01 term
- Fine-tuning#
- Further training an existing model on your own examples so it follows a specific format, tone or task more reliably. It changes how a model behaves; it is not the best way to give it up-to-date facts.Learn more
G
02 terms
- Generative AI#
- AI that creates new content, such as text, images, code or audio, from a prompt. In business it is used for drafting, summarising, answering questions and producing content at scale with human review.Learn more
- Guardrails#
- Rules and checks around an AI system that limit what it can say or do: blocking off-topic or unsafe answers, masking personal data, validating outputs and handing over to a person when confidence is low.Learn more
H
02 terms
- Hallucination#
- When an AI model states something that sounds plausible but is false or unsupported. It is reduced by grounding answers in your documents (RAG), asking for sources, testing with evaluation sets and human review.Learn more
- Human in the loop#
- A design where a person reviews or approves AI output before it takes effect, for example checking a drafted reply or confirming an extracted invoice total.Learn more
I
01 term
- Intelligent document processing (IDP)#
- Using OCR, computer vision and language models to read invoices, forms, IDs and contracts, extract the fields that matter and pass them into business systems.Learn more
L
02 terms
- Large language model (LLM)#
- A model trained on large amounts of text that can understand and generate language. Examples include OpenAI's GPT models, Anthropic's Claude, Google's Gemini, Meta's Llama and Mistral.Learn more
- LoRA (low-rank adaptation)#
- An efficient fine-tuning method that trains a small set of extra weights instead of the whole model, which cuts the cost and hardware needed to customise open-weight models.Learn more
M
03 terms
- Machine learning (ML)#
- Software that learns patterns from historical data to make predictions or decisions, such as forecasting demand, scoring leads or flagging fraud, instead of following hand-written rules.Learn more
- MLOps#
- The practices and tools for deploying, monitoring, versioning and retraining machine learning models in production, so they stay accurate and reliable after launch.Learn more
- Model drift#
- The gradual drop in a model's accuracy as real-world data changes from the data it was trained on. Monitoring catches drift so the model can be retrained.Learn more
N
01 term
- Natural language processing (NLP)#
- The field of AI that deals with human language: classifying text, extracting names and figures, detecting sentiment, translating and answering questions.Learn more
O
02 terms
- Object detection#
- A computer vision task that finds and labels each object in an image or video frame, with a box showing where it is. Used for counting stock, safety monitoring and quality inspection.Learn more
- Open-weight model#
- A model whose weights are published, such as Meta's Llama or many Mistral models, so it can be hosted on your own cloud or servers and fine-tuned without sending data to a third-party API.Learn more
P
02 terms
- Predictive analytics#
- Using historical data and statistical or machine learning models to forecast what is likely to happen next, such as sales, churn, stock needs or late payments.Learn more
- Prompt engineering#
- Designing the instructions, examples and context given to an LLM so it produces accurate, consistent output in the format you need. Prompts are tested and versioned like code.Learn more
R
03 terms
- Recommendation engine#
- A system that suggests products, content or next actions to each user based on their behaviour and that of similar users. Common in e-commerce, media and learning platforms.Learn more
- Retrieval-augmented generation (RAG)#
- A technique where the system first searches your documents for relevant passages, then gives them to the LLM to answer from. It keeps answers current and traceable without retraining the model.Learn more
- Robotic process automation (RPA)#
- Software bots that repeat rule-based tasks across applications, such as copying data between systems or downloading reports. RPA follows fixed steps; AI agents handle tasks that need judgement.Learn more
T
02 terms
- Token#
- The unit LLMs read and write, roughly three-quarters of an English word. API pricing, speed and context limits are all measured in tokens.
- Training data#
- The examples a model learns from. Its quality, volume and how well it represents real cases matter more to accuracy than the choice of algorithm.Learn more
V
01 term
- Vector database#
- A database that stores embeddings and finds the most similar ones quickly. It is the search layer behind RAG and semantic search. Examples include Pinecone, pgvector, Weaviate and Chroma.Learn more
W
01 term
- Web scraping#
- Automatically collecting publicly available data from websites, such as prices, listings or reviews, and turning it into structured data. It must respect site terms and data protection law.Learn more
0 results
No terms match. Try a different word, or ask us.
Free consultation
Still have questions?
Ask us anything about AI, from what a term means to whether your project needs it. No sales pitch unless you want one.
Enquiry formFields marked * are required.