Glossary

Human-in-the-Loop

What is Human-in-the-Loop?

Human-in-the-loop describes workflows in which people step into an AI process at defined points: they review results, approve or correct them, or take over difficult cases. The principle reduces the risk of faulty output and keeps accountability with people, especially for decisions affecting individuals, money or legal matters. Example: an AI agent drafts replies to customer enquiries and a member of staff checks them before they are sent.

How KI.ordo helps

In KI.ordo projects, agents deliver drafts that people approve, and the website chat can hand conversations over to the team via a contact form.

Learn more →

Topics

Approval
Oversight
Accountability

Try KI.ordo

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

Start demo

← All terms

Related terms

AI Automation System

An AI automation system combines traditional process automation with AI capabilities such as understanding text, classification or decision support. This makes it possible to automate workflows with unstructured inputs too, such as emails, forms or enquiries. A typical setup is a chain of trigger, processing steps, conditions and output, with human approval at critical points. Example: incoming enquiries are automatically categorised, summarised and forwarded to the right department.

Automation
Processes
+1

Intelligent Agents

An intelligent agent is a system that perceives its environment, processes information and chooses actions on its own in order to reach a goal. Today the term usually refers to software built on large language models that follows instructions, draws on knowledge and calls tools such as a search function or an API. How much an agent may do independently should be decided deliberately. Example: an agent answers customer questions using the product documentation.

Agents
Autonomy
+1

Reinforcement learning from human feedback (RLHF)

RLHF is a training method that makes language models more helpful and safer. People compare and rate several of the model's answers; these judgements are used to train a reward model, which then further trains the language model itself through reinforcement learning. This teaches it, for instance, to answer more clearly or to decline problematic requests. RLHF takes place at the model provider before a model is released – not with individual users.

training
human feedback
+1

Hallucination

A hallucination is output from an AI model that sounds convincing but is wrong or entirely made up – such as a non-existent court ruling, an incorrect figure or an invented source. The cause: language models produce likely wording; they do not automatically look up facts. The risk falls when answers are based on verified sources, evidence is cited and people check important results.

Language models
Reliability
+1

Template