# Human-in-the-Loop (HITL)

AI Glossary · Agents & Automation
Canonical URL: https://aisat.uk/glossary/human-in-the-loop
Author: Lucy Gilmore, Assistant General Counsel, Product, Privacy & AI at Sprinklr | Practical Privacy, Product & AI Governance & Defensible Risk Decisions (https://www.linkedin.com/in/lucy-gilmore/)
Breadcrumb: [Glossary](https://aisat.uk/glossary) > [Agents](https://aisat.uk/glossary?category=agents) > Human-in-the-Loop (HITL)

## TL;DR

> **Human-in-the-Loop (HITL)** is an operational design pattern that inserts qualified human judgement at critical checkpoints inside an AI system's lifecycle. It ensures high-stakes decisions, low-confidence predictions, and irreversible tool actions are reviewed, edited, or approved by a person before execution.

## How Human-in-the-Loop (HITL) works in practice

As AI systems move from drafting text to taking actions via tools and agents, treating every request identically creates an unacceptable choice between reckless automation and manual bottlenecks. A well-engineered HITL architecture uses risk-based routing and confidence thresholds to interrupt automated execution only when human oversight adds real value.

At runtime, an agentic workflow proceeds autonomously through read-only gathering, retrieval, and drafting steps. When the system reaches a high-impact boundary, such as executing a write operation (`issue_refund`, `terminate_account`, `submit_regulatory_filing`), encountering a model confidence or verifier score below a threshold, or handling a sensitive category, the orchestrator serialises its state to a database, pauses the thread, and emits a structured review card to a human queue (in Slack, Teams, or an internal operations console). The human reviewer can approve the action, edit the parameters, or reject it with feedback.

Crucially, every human edit or rejection is logged as a structured preference pair (`model_draft` vs `human_approved`), feeding directly back into the team's golden eval dataset and future fine-tuning runs, as used by UK healthcare and legal teams to comply with Article 14 of the EU AI Act and UK GDPR Article 22 rules on automated decision-making.

## Why it matters and trade-offs

Human-in-the-loop is both a regulatory requirement for high-risk AI systems under Article 14 of the EU AI Act and the fastest path to earning operational trust with sceptical domain experts. It lets organisations deploy AI into high-value financial, clinical, or legal workflows on day one with bounded downside risk.

The primary failure mode of HITL is 'automation bias' (or rubber-stamping): when a reviewer is asked to click 'Approve' on 300 AI-generated summaries an hour that are 98 per cent accurate, human attention collapses and errors slip through unspotted, leaving the human as a legal scapegoat without genuine control. Effective HITL interfaces highlight exact uncertainty spans, show inline source diffs, and keep review volumes manageable by auto-clearing genuinely low-risk cases.

## Related AI concepts

- [EU AI Act](https://aisat.uk/glossary/eu-ai-act): The EU AI Act (Regulation (EU) 2024/1689) is the European Union's risk-based AI law: prohibited practices and AI literacy applied on 2 February 2025 and GPAI rules on 2 August 2025, while under the May 2026 Digital Omnibus agreement standalone high-risk duties apply from 2 December 2027.
- [AI Governance](https://aisat.uk/glossary/ai-governance): AI Governance is the operational framework of internal policies, model inventories, risk assessments, approval gates, human oversight rules and audit trails that an organisation uses to deploy artificial intelligence safely, ethically and legally.
- [Agentic Workflow](https://aisat.uk/glossary/agentic-workflow): An Agentic Workflow is a multi-step operational or engineering process in which a language model dynamically plans steps, calls external tools, critiques its own output and branches based on intermediate results within an orchestrated pipeline.
- [Evals (Evaluations)](https://aisat.uk/glossary/evals): Evals (Evaluations) are automated, repeatable testing pipelines that score an AI application's outputs against a golden dataset using deterministic assertions, reference metrics and LLM-as-a-judge rubrics before any prompt or model change ships.