Knowledge

AI Glossary: The most important AI terms, simply explained

Understand the core building blocks of modern AI systems — from AI agents to RAG and embeddings to governance and data protection.

34 of 34 terms

A

Agentic AI

Workflow AI systems that track goals, plan sub-steps and use tools.

Artificial Intelligence (AI)

Basics Software that performs tasks that normally require human thinking.

Agent (Agentic Workflow)

Workflows AI systems that plan and execute tasks independently.

AI Governance

Governance Rules and processes for the responsible use of AI.

AI automation

Workflows Automating business processes in which AI understands and processes unstructured information.

AI literacy training (EU AI Act Art. 4)

Governance Training that builds the AI literacy of employees as required by Article 4 of the EU AI Act.

C

Clawdbot / Moltbot / OpenClaw

Basics Terms relating to the development and classification of OpenClaw.

Chunking

Workflows Divide large documents into smaller, meaningful sections.

E

Embeddings

Infrastructure Numerical representations of text that capture meaning.

Evaluation/Evals

Workflows Systematic measurement and evaluation of AI quality.

F

Forward Deployed Engineer (FDE)

Basics An engineer embedded with the customer who builds AI solutions all the way into production.

G

Generative AI (GenAI)

Basics AI that creates new content – text, images, code and more.

Grounding

Basics Base AI answers on real, verifiable sources.

H

Hallucination

Basics When AI generates convincing-sounding but false information.

Human in the loop

Workflows People check and control AI decisions at critical points.

L

LLM (Large Language Model)

Models Large language models that understand and generate human language.

Local LLM

Infrastructure A language model that runs on your own hardware instead of in a provider's cloud.

M

Machine Learning (ML)

Basics Computers learn from data instead of being programmed manually.

MCP (Model Context Protocol)

Infrastructure An open standard that lets AI applications access data, tools and business systems.

Multi-agent system

Workflows Several specialized AI agents working together to solve a complex task.

N

n8n

Workflows A workflow automation tool with AI features that can also be self-hosted.

O

OpenClaw

Workflow Open source framework for agentic AI workflows in companies.

On-premise hosting

Infrastructure Operation of AI components on your own infrastructure or in your own data center.

P

Prompt

Basics The input or instruction you give to an AI model.

Privacy / data protection (for AI)

Governance Data protection requirements when using AI systems.

Prompt engineering

Basics Designing and testing instructions for AI models so they deliver reliably good results.

R

RAG (Retrieval Augmented Generation)

Workflows AI first searches for relevant documents before answering.

Reranking

Workflows Re-sorting search results more precisely by relevance before the AI answers.

T

Training vs. Inference

Models Training = AI learns. Inference = AI works.

Tokens & context windows

Models The unit of measurement for text in AI models and their processing limit.

Temperature (sampling)

Models Controls how creative or predictable the AI responses are.

Tool/function calling

Workflows AI can call external tools and APIs to complete tasks.

V

Vector database

Infrastructure Database optimized for quick searches for similar content.

Vibe coding

Workflows Building software by describing to an AI in plain language what it should create.

No results

Try a different search term or filter.

Ready to make AI actually work?

Book your free 30-minute consultation — no strings attached, fully confidential.

Book a free consultation