AI Glossary
Plain-language explanations of AI terms that matter for your business.
AI Agent
An AI system that can take actions autonomously, not just generate text. It can use tools, make decisions, and execute multi-step workflows with minimal human intervention.
Embeddings
A way to convert text (or images, or other data) into lists of numbers that capture meaning. Similar concepts end up with similar numbers, which lets computers find related content efficiently.
Fine-tuning
Taking a pre-trained AI model and training it further on your specific data to make it better at a particular task. Like teaching a generally knowledgeable person the specifics of your industry.
Hallucination
When an AI model generates information that sounds confident and plausible but is factually incorrect. The model isn't "lying." It's generating statistically likely text that happens to be wrong.
LLM (Large Language Model)
An AI model trained on massive amounts of text data that can understand and generate human-like text. GPT-4, Claude, and Llama are examples. Think of it as a very sophisticated text prediction engine.
Prompt Engineering
The practice of crafting instructions (prompts) to get better, more consistent results from AI models. It's part writing skill, part technical understanding of how models process instructions.
RAG (Retrieval-Augmented Generation)
A technique that combines a language model with a search system. Instead of relying solely on what the model was trained on, RAG first retrieves relevant documents from your data, then uses the model to generate an answer based on those documents.
Vector Database
A database designed to store and search embeddings efficiently. Regular databases search by exact matches or keywords. Vector databases search by meaning and similarity.