AI (Artificial Intelligence): Technology that enables machines to perform tasks that typically require human intelligence, like understanding language and generating content.
AI Model: A specific AI system designed for particular tasks. Different models have different strengths (e.g., GPT-5 Mini for general tasks, Grok 4 Fast for cost-efficient multimodal tasks).
Batch Generation: Creating multiple variations of an image or video at once.
Base Model: The underlying AI model used when creating a custom model. Determines the capabilities of your custom model.
Custom Model: A personalized AI assistant you create by combining a base model with custom instructions and a knowledge base. Uses RAG (Retrieval Augmented Generation) to access your specific data.
Conversation: A chat session with an AI assistant. Can contain multiple messages back and forth.
Daily Limit: The maximum number of times you can use a feature per day. Limits reset at midnight in your local timezone.
Document Processing: The ability to upload and analyze documents (PDFs, Word docs, etc.) to extract information or answer questions.
Embedding: A mathematical representation of text that captures its meaning, used for semantic search.
Export: Downloading your data from Nexal AI, including conversations, images, and other content.
Generation: Creating new content (images, videos, text) using AI.
Knowledge Base: A collection of documents and data that a custom AI model references using RAG (Retrieval Augmented Generation) to provide personalized responses.
Model: See AI Model.
Persona: A pre-configured AI assistant with specific instructions and personality traits for particular tasks.
Premium Model: Advanced AI models that provide better quality and accuracy but may have usage limits. Examples include GPT-5, Grok 4, and Gemini 2.0 Flash Lite.
Prompt: The text you write to tell the AI what you want. Better prompts = better results!
Prompt Engineering: The skill of writing effective prompts to get the best AI responses.
Semantic Search: Searching by meaning rather than exact keywords. Finds relevant content even if words don’t match exactly.
Streaming: When AI responses appear word-by-word in real-time, rather than all at once.
Subscription Plan: Your chosen pricing tier (Free, Plus, or Max) that determines your features and limits.
Text-to-Image: Generating images from text descriptions using AI.
Text-to-Video: Generating videos from text descriptions using AI.
Vector Storage: A way of storing and searching documents by their meaning, used in custom models and semantic search.
Additional Terms
Claude: A family of AI models developed by Anthropic. Includes Claude 3.5 Haiku and other variants.
Gemini: A family of AI models developed by Google. Includes Gemini 2.0 Flash Lite, Gemini 2.5 Flash Preview, and Gemma 3 27B.
Grok: AI models developed by xAI. Includes Grok 4 Fast (multimodal with 2M token context) and Grok 3 Mini.
GPT: AI models developed by OpenAI. Includes GPT-5 Mini, GPT-5 Nano, and GPT-4.1 Nano.
RAG (Retrieval Augmented Generation): A technique used in custom models where the AI retrieves relevant information from a knowledge base before generating responses, providing more accurate and personalized answers.
OCR (Optical Character Recognition): Technology that converts scanned images of text into editable text.
If you encounter a term you don’t understand, check this glossary or ask the AI assistant to explain it!
