# What Is an AI Hallucination? Causes & Fixes

Source: https://insertchat.com/glossary/ai-hallucination

> An AI hallucination is a confident answer that is false or unsupported. Learn why language models hallucinate, what it costs a business, and how to prevent it.

An AI hallucination is a response from an AI system that sounds confident but is false, made up, or unsupported by its sources, such as an invented price, policy, or appointment time. It happens because language models generate plausible text rather than looking facts up. For a business assistant, a hallucination is a promise the business never made.

## Why AI hallucinations happen

The US National Institute of Standards and Technology calls this risk confabulation in its [Generative AI Profile (NIST AI 600-1)](https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf): confidently stated but erroneous or false content. Models produce the most likely next words, and when the facts are missing, the most likely words can still be wrong.

For customer-facing assistants, the main causes are gaps in the knowledge base, outdated or conflicting sources, and instructions that reward always having an answer. The fixes are equally practical: answer only from approved sources, say when information isn’t available, list promises the assistant must never make, and send uncertain questions to a person.

## Example: an invented delivery fee

A party rental company’s chatbot is asked whether delivery to a nearby town is free. Its knowledge lists delivery fees only for the home city. An unguarded bot answers “Yes, delivery is free within 30 miles,” a policy the company never had. A guarded assistant says it doesn’t have the delivery fee for that town and asks the owner to confirm. This scenario is illustrative.

## How InsertChat guards against hallucinations

InsertChat’s assistant is instructed never to invent business facts, prices, policies, availability, or commitments, and to say so when information is missing or conflicting; that setting can’t be turned off. You can list promises or decisions it must not make, and by default it asks a person for help when an answer is uncertain.

On calls, it waits for a verified result before saying anything was booked. Knowledge gaps in [knowledge and answers](https://insertchat.com/product/knowledge) show which real questions need better sources. See the [party rental setup](https://insertchat.com/industries/party-rentals).

## Can AI hallucinations be completely eliminated?

Not entirely with today’s models. They can be made rare with grounded answers, clear instructions to admit gaps, testing, and human handoff for uncertain questions.

## Who is responsible when a business chatbot gives a wrong answer?

Customers generally treat the chatbot as speaking for the business. That is why businesses should limit what it can promise and review conversations regularly.

## Related terms

- [Retrieval-augmented generation (RAG)](https://insertchat.com/glossary/retrieval-augmented-generation): Retrieval-augmented generation, or RAG, is a technique where an AI system first searches a set of documents for passages relevant to a question, then writes its answer using those passages.
- [Fallback intent](https://insertchat.com/glossary/fallback-intent): A fallback intent is the response a chatbot or voice assistant uses when it can’t match a message to anything it knows how to handle, or doesn’t have the answer.
- [Knowledge base](https://insertchat.com/glossary/knowledge-base): A knowledge base is an organized collection of information that people or software use to answer questions.
- [Human handoff](https://insertchat.com/glossary/human-handoff): Human handoff is the point where an AI assistant passes a customer conversation to a person, along with everything said so far.

## Related InsertChat pages

- [AI knowledge base](https://insertchat.com/product/knowledge)
- [How to build your assistant’s knowledge base](https://insertchat.com/blog/prepare-your-assistants-knowledge)
- [AI front desk for party rentals](https://insertchat.com/industries/party-rentals)

## Sources

- [NIST AI 600-1, Generative Artificial Intelligence Profile (July 2024)](https://nvlpubs.nist.gov/nistpubs/ai/NIST.AI.600-1.pdf)