EN
Sign inGet started
Glossary

Automatic classification

What is Automatic classification?

Automatic classification assigns texts, documents or records to predefined categories without manual sorting. Traditionally, models learn this from labelled examples; large language models can also assign categories based on a description alone. Typical uses include sorting incoming emails by request type, assigning receipts or flagging urgent support tickets. For important cases, spot checks by people are advisable.

How KI.ordo helps

The KI.ordo “AI router” step assigns inputs to up to eight freely defined categories; the “Categorise text” template demonstrates this with question, complaint, order and other.

Learn more →: Automatic classification

Matching templates

Topics

  • Classification
  • Automation
  • Text processing

Try KI.ordo

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

Start demo
← All terms

Related terms

Text Classification

Text classification automatically assigns texts to predefined categories, for example emails by request type, reviews by sentiment or documents by topic. Previously this required training dedicated models on labelled examples; today large language models can often assign categories from a description alone. This makes it possible to pre-sort enquiries and route them to the right team faster.

  • NLP
  • Classification
  • +1
Template

Classifier

A classifier is a model or method that assigns inputs to one of several predefined categories. Classic variants such as decision trees or naive Bayes are trained on labelled examples; language models can also sort texts based on a description of the categories. Typical uses include spam detection, sorting customer enquiries by topic and categorising receipts. Quality is measured with metrics such as accuracy, precision and recall.

  • Classification
  • Machine learning
  • +1
Template

Lead Routing

Lead routing is the automatic assignment of incoming enquiries to the responsible person, department or region. Criteria may include topic, product, company size, language or urgency. AI can understand and categorise the free text of an enquiry, for instance whether it concerns a new quote, a support issue or a job application. Fast, accurate routing shortens response times and prevents enquiries from being left unanswered.

  • Sales
  • Automation
  • +1
Template

Supervised Learning

In supervised learning, a model learns from examples for which the correct answer is already known, such as emails labelled “spam” or “not spam”. From these it derives rules to classify new, unseen cases or to predict values. Typical tasks are classification and regression; most of the effort goes into creating cleanly labelled data.

  • Machine learning
  • Training
  • +1