Skip to content

Human in the loop

Adrià Castany 2 min

What is human in the loop?

Human in the loop, or human oversight, is a design in which a person reviews, approves or corrects what an AI system does at the points where a mistake is expensive. In customer service, it means the tasks that wait for the team’s approval and the answers someone reviews.

Also called

HITL, human oversight, human approval, human review

Topic
AI in support
On this page
  1. Before acting and after
  2. Why it matters
  3. Where a person goes
  4. How much oversight, by risk
  5. What the EU AI Act says
  6. Human in the loop in Intake
  7. How Intake handles it
  8. Frequently asked questions

Before acting and after

There is oversight before, when a person approves the answer or the task before it reaches the customer, and oversight after, when a person reviews a sample of what the AI already did.

The first slows the agent down and the second does not. Most teams combine both depending on the risk of each topic.

Why it matters

It is the answer to the question every decision maker asks, can I trust the AI with my customers?

There is no need to review everything. There is a need to know which tasks it never does alone, who reads what it answered and what happens when it gets something wrong. Without that, trust depends on nothing going wrong.

Where a person goes

In customer service, human oversight sits at four points.

  • Before a sensitive task. A refund, a cancellation or a change of account holder waits for a person.
  • When the AI does not know. It hands the conversation over instead of answering.
  • In the daily review. A person reads a sample of answers and flags the wrong ones.
  • Before a change goes live. New instructions are tested with real questions.

How much oversight, by risk

Oversight is spread by topic.

Reviewing everything before it is sent removes the point of having an agent.

TopicOversightExample
How-to questionReview a sample, afterwardsHow to export a report
Question about account dataReview a sample and every failureThe status of an invoice
Task involving money or a contractApproval before doing itA refund
Sensitive topicAlways a personA complaint

What the EU AI Act says

Article 14 of Regulation (EU) 2024/1689 requires high-risk AI systems to be designed so that they can be effectively overseen by natural persons while they are in use.

Whether a specific use is high-risk is for the company’s legal advisers to assess.

Human in the loop in Intake

In Intake, an action marked as requiring human approval is not run by the AI, which hands the conversation to a person on the team.

On every answer, “Why it answered this way” shows the sources it read and the team marks whether it was right. Instructions, actions and guided responses are tested in draft before they are applied.

How Intake handles it

Frequently asked questions

What is human in the loop?

A design in which a person reviews, approves or corrects what an AI system does at the riskiest points. It is also called human oversight.

Do all the answers of an AI agent need reviewing?

No. A sample and every failure are reviewed, and sensitive tasks are approved beforehand or always go to a person. Reviewing everything before it is sent turns the agent into a copilot.

Which tasks should wait for a person?

Those that move money, change a contract or touch personal data in a way that is hard to undo. A refund, a cancellation or a change of account holder are the usual examples.

Does the law require human oversight of a chatbot?

The EU AI Act requires it for high-risk systems. Whether a customer service agent is one depends on its use, and the company’s legal advisers assess it.

Glossary

Keep reading

Glossary

Related terms

See the full glossary

Add it without dropping what you use

15 minutes, no commitment