Glossary
Hallucination
When an AI model states something false or made-up with complete confidence, because it is predicting plausible text rather than checking facts.
A hallucination is a confident wrong answer. Because a language model generates the most plausible next words rather than looking up truth, it can invent citations, numbers, or policies that sound right but never existed.
Hallucinations can't be fully eliminated, but they can be managed. Grounding answers in your real documents, asking the model to cite sources, and letting it say 'I don't know' all sharply reduce how often it makes things up.
How we use it
We design systems that ground answers in trusted sources and we test them with evaluations, so you can see the real error rate instead of hoping for the best.
Related terms
Get in touch
Want to put this into practice?
If this concept is relevant to something you're building, a short note is the fastest way to get practical help.