AI Glossary

OroCommerce AI Glossary

A practical reference for the AI terms shaping B2B commerce. This glossary covers everything from agentic checkout and multi-agent systems to RAG, vector databases, and enterprise AI governance. Find clear definitions and key protocols in one searchable place.

Agentic AI & Autonomous Commerce

Agentic AI & Autonomous Commerce
Agentic AI

An AI system that can set sub-goals, plan a sequence of actions, use tools, and execute tasks autonomously across multiple steps without requiring human input at each stage.
Read full definition
Agentic AI & Autonomous Commerce
Agentic Commerce

The application of agentic AI to commercial transactions, where buying, selling, quoting, and procurement workflows are executed autonomously or semi-autonomously by AI systems operating within defined business rules.
Read full definition
Agentic AI & Autonomous Commerce
Agentic RAG

An architecture that combines Retrieval-Augmented Generation with agentic behavior, allowing an AI system to decide what to retrieve, from which sources, in what sequence, and to iterate its retrieval strategy when initial results are insufficient.
Read full definition
Agentic AI & Autonomous Commerce
AI Orchestration

The coordination layer that manages multiple AI models, tools, and data sources within a single workflow, controlling the sequence of operations, routing decisions, context passing, and error handling across components.
Read full definition
Agentic AI & Autonomous Commerce
AI Sales Agent

An AI system that performs sales-related tasks on behalf of a sales team: answering product questions, showing recommendations, generating draft quotes, qualifying inbound leads, and guiding buyers through purchase decisions.
Read full definition
Agentic AI & Autonomous Commerce
AI Workflow Automation

The use of AI models to execute, route, or optimize multi-step business processes, going beyond fixed rule-based logic to handle variability, exceptions, and judgment calls within a defined workflow.
Read full definition
Agentic AI & Autonomous Commerce
Multi-Agent System

An architecture in which multiple AI agents, each with a defined role or specialization, collaborate, communicate, or operate in parallel to accomplish tasks that are too complex or broad for a single agent.
Read full definition

AI Infrastructure & Integration

AI Infrastructure & Integration
AI API Integration

The practice of connecting AI model capabilities, including inference, embeddings, classification, and generation, to existing business applications and data systems through API calls, enabling AI features to operate within established enterprise workflows and infrastructure.
Read full definition
AI Infrastructure & Integration
AI Guardrails

Constraints, validation mechanisms, and monitoring systems applied to AI inputs and outputs to prevent harmful, incorrect, policy-violating, or unauthorized behavior in production.
Read full definition
AI Infrastructure & Integration
Function Calling

A capability of modern LLMs that allows the model to identify when a task requires external data or actions, generate a structured call to a defined function or API with the correct parameters, and incorporate the returned result into its response.
Read full definition
AI Infrastructure & Integration
Instruction Tuning

A fine-tuning process in which a pre-trained language model is further trained on examples of instructions paired with desired responses, teaching it to follow directives reliably and behave consistently within a specific domain or context.
Read full definition
AI Infrastructure & Integration
LangFuse

An open-source observability and evaluation platform for LLM applications, providing tracing, prompt versioning, performance monitoring, and evaluation scoring for AI workflows in production.
Read full definition
AI Infrastructure & Integration
LangGraph

An open-source framework built on LangChain for creating stateful, multi-step AI workflows and agent systems, using a graph structure where nodes represent processing steps and edges define the flow of data and control between them.
Read full definition
AI Infrastructure & Integration
LLM (Large Language Model)

A neural network trained on large volumes of text data, capable of generating, summarizing, classifying, translating, and reasoning across a wide range of language tasks.
Read full definition
AI Infrastructure & Integration
MCP (Model Context Protocol)

An open standard developed by Anthropic that defines how AI models connect to external tools, data sources, and services, providing a consistent interface for capabilities like reading data, calling functions, and using reusable prompt templates.
Read full definition
AI Infrastructure & Integration
Private LLM

A large language model deployed within an organization's own infrastructure or a dedicated private cloud environment, ensuring that data processed by the model does not leave the organization's security perimeter.
Read full definition
AI Infrastructure & Integration
Prompt Engineering

The practice of designing, structuring, and iterating on the instructions given to a language model to reliably produce desired outputs for a specific task or context.
Read full definition
AI Infrastructure & Integration
Prompt Versioning

The practice of tracking, storing, and managing different versions of AI prompts used in production systems, enabling rollback, performance comparison, A/B testing, and audit trails for AI application behavior over time.
Read full definition
AI Infrastructure & Integration
RAG (Retrieval-Augmented Generation)

An AI architecture that enhances a language model's responses by retrieving relevant documents or data from an external knowledge base at query time, and passing that retrieved content to the model as context for generating an answer.
Read full definition
AI Infrastructure & Integration
Small Language Model (SLM)

A language model with a significantly smaller parameter count than frontier models, typically under 10 billion parameters, optimized for specific tasks, lower latency, reduced cost, and deployment on constrained or private infrastructure.
Read full definition

AI-Powered Commerce Features

AI-Powered Commerce Features
Agentic Checkout

A checkout process in which an AI agent selects items, applies pricing, and completes payment and order confirmation on a buyer's behalf, within pre-authorized limits, without a human manually working through a cart.
Read full definition
AI-Powered Commerce Features
AI Catalog Management

The use of AI to structure, enrich, categorize, and maintain product data at scale, generating descriptions, mapping attributes, deduplicating SKUs, and keeping catalog data consistent across suppliers and channels.
Read full definition
AI-Powered Commerce Features
AI Inventory Forecasting

The use of AI models to predict future stock demand at the SKU and location level, using historical sales, seasonality, and lead times, to inform replenishment decisions.
Read full definition
AI-Powered Commerce Features
AI Merchandising

The use of AI to determine which products to show, how to price or bundle them, and to which customers, based on behavioral, transactional, and catalog data.
Read full definition
AI-Powered Commerce Features
AI Order Management

AI-assisted coordination of an order across its full lifecycle after creation: allocation, fulfillment routing, exception handling, and status updates, across multiple systems and locations.
Read full definition
AI-Powered Commerce Features
AI Order Processing

The use of AI to automatically read, validate, structure, and route incoming customer orders (from email, EDI, portals, or PDFs) into a commerce or ERP system without manual data entry.
Read full definition
AI-Powered Commerce Features
AI Procurement Automation

The use of AI to automate the buy-side of B2B transactions: identifying need, sourcing from approved vendors, generating and routing purchase requisitions, and reconciling receipts against orders.
Read full definition
AI-Powered Commerce Features
Conversational Commerce

Buying and selling conducted through natural-language interfaces such as chat, voice, or messaging, where the AI answers questions, checks availability, and completes or assists a transaction within the conversation itself.
Read full definition

Data & Observability

Data & Observability
Embeddings

Numerical vector representations of text, images, or other data that capture semantic meaning, allowing a machine to measure how similar two pieces of content are by comparing their vectors.
Read full definition
Data & Observability
Fine-Tuning vs RAG

Two different approaches to making a general-purpose LLM behave like a specialist in your domain: fine-tuning retrains the model's weights on your data, while RAG (retrieval-augmented generation) leaves the model unchanged and feeds it relevant context retrieved at query time.
Read full definition
Data & Observability
Inference vs Training

Training is the process of building or adjusting a model's parameters from data; inference is the process of running a trained model to produce an output for a specific input, in production.
Read full definition
Data & Observability
LLM Benchmarking

The practice of systematically testing an LLM's outputs against defined tasks, datasets, or criteria to measure accuracy, consistency, cost, and suitability for a specific use case, before and after deployment.
Read full definition
Data & Observability
LLM Observability

The practice of monitoring, logging, and analyzing an LLM-based system's inputs, outputs, latency, cost, and failure modes in production to understand and improve its behavior over time.
Read full definition
Data & Observability
Vector Database

A database purpose-built to store and search high-dimensional numerical representations of data, called embeddings, retrieving results by semantic similarity rather than exact keyword match.
Read full definition