AI Basics
AI (Artificial Intelligence)
Artificial Intelligence - computer systems that perform tasks normally requiring human intelligence, such as understanding language, analyzing, and making decisions.
Machine Learning (ML)
Teaching computers to learn patterns from data to predict or decide, without hand-coding every rule.
Deep Learning
A branch of ML using multi-layer neural networks; the foundation of modern AI.
Generative AI
AI that creates new content - text, images, code, or audio - based on what it has learned. Learn more →
LLM (Large Language Model)
Large Language Model - AI trained on massive text to understand and generate natural language, e.g. GPT and Claude. Learn more →
Working with AI
Prompt
The instruction or question you give an AI to get the output you want; the clearer it is, the better the result.
Prompt Engineering
The skill of designing prompts so AI understands what you want and delivers usable results. Learn more →
Token
The unit of text an AI processes (a word or word-piece); used to measure cost and input/output size.
Context Window
The maximum amount of text an AI can consider at once; larger means it can handle longer input.
Hallucination
When AI produces plausible-sounding but false or made-up information - always have a person verify. Learn more →
Fine-tuning
Further-training a model on specialized data to specialize it for a task or style.
Few-shot / Zero-shot
Prompting an AI with a few examples (few-shot) or none at all (zero-shot).
Multimodal
AI that handles multiple formats together - text, images, and audio.
Agentic AI & Systems
AI Agent
An AI that acts as an 'agent' - takes a goal, then chooses tools and acts to achieve it. Learn more →
Agentic AI
AI that doesn't just answer but plans and carries out multi-step tasks on your behalf, under human supervision. Learn more →
RAG (Retrieval-Augmented Generation)
A technique where AI retrieves your real data before answering - reduces hallucination and lets it cite sources. Learn more →
Embedding
Converting text or images into numeric vectors so AI can find things with similar meaning.
Vector Database
A database that stores embeddings for meaning-based search; the heart of RAG systems.
Knowledge Base
An organization's repository of documents and knowledge that AI uses as its reference. Learn more →
MCP (Model Context Protocol)
An open standard for connecting AI to external data and tools in a structured, secure way.
Workflow Automation
Letting AI or systems run process steps automatically to reduce repetitive human work. Learn more →
API
A standard interface that lets software talk to each other; used to connect AI to existing systems.
Enterprise & Strategy
AI Transformation
Transforming an organization's processes, people, and strategy to truly work with AI - not just buying tools. Learn more →
AI Governance
A framework for using AI safely, transparently, accountably, and in compliance with rules like PDPA. Learn more →
AI Roadmap
A phased plan for adopting AI across an organization, from first steps to scaling. Learn more →
Proof of Concept (PoC)
A limited trial to prove an AI idea works and is worthwhile before full investment. Learn more →
Use Case
A specific application of AI, e.g. 'summarize contracts' or 'auto-answer customer questions'.
ROI (Return on Investment)
Return compared to money invested; the measure of whether an AI project is worthwhile. Learn more →
Human-in-the-loop
Designing for human oversight or approval at key points to keep AI safe when it acts on its own.
PDPA
Thailand's Personal Data Protection Act B.E. 2562, which organizations must comply with when using data with AI.
Private AI / On-premise AI
AI that an organization fully controls, keeping data in-house; suited to sensitive data. Learn more →
No matching terms
Want to put these into practice in your organization?
Talk to the Intelevo team for a free initial consultation on AI strategy, training, and implementation.
Start a consultation →