EN
Sign inGet started
Glossary

Conversational AI

What is Conversational AI?

Conversational AI covers technologies that enable computers to hold dialogues in natural language, either in writing via chat or spoken via voice assistants. Modern systems are usually based on large language models that understand requests, take the conversation history into account and formulate suitable replies. Organisations use them in customer service, for booking appointments or for internal help desks. Reliable knowledge, clear limits and a handover to people when the AI cannot help are essential.

How KI.ordo helps

With KI.ordo's website chat, an agent can be embedded on your own website with a single line of code, including handover to the team via a contact form in the chat.

Learn more →: Conversational AI

Matching templates

Topics

  • Chatbot
  • Dialogue
  • Customer service

Try KI.ordo

Agents, flows and templates in one workspace – free 24-hour demo.

Start demo
← All terms

Related terms

Chatbot

A chatbot is a program that receives questions in text or speech and answers them in a dialogue. Simple chatbots follow fixed rules and decision trees, while modern ones use large language models and understand freely worded requests. Typical uses include customer service, internal help desks and appointment requests – for example a website chat that answers questions about delivery times around the clock.

  • customer service
  • dialogue system
  • +1
Template

Natural Language Understanding (NLU)

Natural language understanding is the part of language processing that captures the meaning of an utterance: what intent lies behind it, which people, places or dates are mentioned, and what is its tone? Together with natural language generation (NLG), NLU forms one of the two sides of NLP. One example is a customer service system that recognises “My parcel still hasn't arrived” as a delivery enquiry.

  • NLP
  • Intent detection
  • +1

Customer service automation

Customer service automation means having software handle recurring customer enquiries fully or partly – for example through chatbots, suggested replies or pre-sorting tickets. Common questions about opening hours, delivery status or returns can be answered around the clock, while the team gains time for difficult cases. Reliable knowledge sources and an easy hand-over to people are essential.

  • Customer service
  • Chatbot
  • +1
Template

Large language model (LLM)

A large language model (LLM) is a neural network trained on very large amounts of text, enabling it to understand and generate language. It works by calculating the most likely next token, step by step. LLMs write, summarise, translate, answer questions and generate code; well-known examples include Claude, GPT, Gemini and Llama. Without access to current sources, they only know what was in their training data.

  • Language models
  • Generative AI
  • +1