Tidio Agents 25 terms
AI Glossary
The terms behind custom AI agents, defined plainly and shown at work: how models and agents operate, how they reach company data, and what it takes to run them safely in customer service and operations.
- Agents and autonomyAgentic AIAgentic describes an AI system that pursues a goal by choosing its own next steps: it plans, calls tools or APIs, checks what happened, and adapts until the task is done or it hands over to a person.
- Agents and autonomyAI agentAn AI agent is a software system that uses a language model to reach a goal on someone's behalf: it reads the situation, chooses which tools to call, acts in other systems, and stops or hands over to a person when it reaches its limits.
- Agents and autonomyAI guardrailsAI guardrails are the checks and limits placed around an AI system to keep its inputs, outputs, and actions within rules a company sets.
- Models and how they workAI hallucinationAn AI hallucination is output from a generative model that sounds fluent and confident but is false, invented, or not supported by the sources the model was given.
- AI strategy and buyingAI proof of conceptAn AI proof of concept (POC) is a short, bounded test that shows whether an AI system can perform one specific task well enough, on a company's real data, to justify building it for production.
- AI strategy and buyingAI ROIAI ROI (return on investment) is the net value an AI system creates, in savings or extra revenue, divided by everything it costs to build and run, over a stated period.
- Models and how they workArtificial general intelligence (AGI)Artificial general intelligence (AGI) is a hypothetical AI system that can match or exceed human ability across a wide range of cognitive tasks, including ones it was not built or trained for.
- Customer serviceChatbotA chatbot is software that holds a conversation with people in text or voice, usually to answer questions or collect information.
- Customer serviceCustomer satisfaction score (CSAT)Customer satisfaction score (CSAT) is the percentage of surveyed customers who say they were satisfied with a specific interaction, product, or service, usually those who answer 4 or 5 on a five-point scale.
- Models and how they workGenerative AIGenerative AI is artificial intelligence that creates new content, such as text, images, audio, video, or code, by learning the patterns in its training data and producing new examples that follow them.
- Models and how they workGroundingGrounding in AI is the practice of tying a model's output to verifiable sources of information, such as documents, databases, or live system data, so that each claim in an answer is supported by a source and can be checked.
- Models and how they workInferenceIn AI, inference is the step in which a trained model is run on new input to produce an output, such as a reply, a classification, or a tool call.
- AutomationIntelligent document processingIntelligent document processing (IDP) is software that reads documents such as invoices, claim forms, and identity papers, works out what each one is, extracts the fields a business needs, checks them against rules and other systems, and passes uncertain cases to a person.
- Customer serviceInteractive voice response (IVR)Interactive voice response (IVR) is a telephone system that answers calls automatically and lets callers choose options by pressing keys or speaking, then plays information, completes a simple self-service task, or routes the call to the right team.
- Models and how they workLarge language model (LLM)A large language model (LLM) is a neural network trained on very large amounts of text to predict the next token in a sequence, which lets it read, write, summarize, translate, and reason over language.
- Models and how they workMachine learningMachine learning (ML) is a branch of artificial intelligence in which software learns patterns from examples, instead of following rules a programmer wrote, and uses them to make predictions or decisions about new cases.
- Agents and autonomyModel Context Protocol (MCP)The Model Context Protocol (MCP) is an open standard that defines how AI applications connect to external tools and data sources.
- Training and customizationModel distillationModel distillation, or knowledge distillation, is a training technique in which a smaller "student" model learns to reproduce the outputs of a larger "teacher" model.
- Models and how they workNatural language processing (NLP)Natural language processing (NLP) is the field of computer science and AI that builds software to read, interpret, and produce human language, in text or speech.
- Customer serviceOmnichannel customer serviceOmnichannel customer service is support in which every channel a customer uses (chat, email, phone, app, social messaging, and the store) shares one customer record and one conversation history, so the customer can switch channels without starting over.
- Safety, privacy and governancePersonally identifiable information (PII)Personally identifiable information (PII) is information that can be used to distinguish or trace a specific person, either on its own (a name, a passport number) or combined with other data linked to them (a date of birth, an order history).
- Knowledge and retrievalRetrieval-augmented generation (RAG)Retrieval-augmented generation (RAG) is a method in which a language model first retrieves relevant passages from an external source, such as a knowledge base or a product catalog, and then writes its answer using those passages.
- AutomationRobotic process automation (RPA)Robotic process automation (RPA) is software that repeats rule-based tasks a person would do on a computer, such as copying data between applications, filling in forms, or clicking through a legacy system, by operating the user interface the way a person does.
- Safety, privacy and governanceSovereign AISovereign AI is the ability of a country or an organization to develop, run, and control artificial intelligence on its own terms: where its data is stored and processed, which infrastructure the systems run on, and who controls the models.
- Models and how they workTokenA token is the unit of text a language model reads and writes: usually a whole word, part of a word, a number, or a punctuation mark.