Sarrai doesn't make up answers
Most AI chatbots are trained to always seem helpful, even when they don't know the answer. So they invent one. We call that a hallucination. Sarrai works differently. If the answer couldn't be found in the knowledge base, we would rather have it say it doesn't know the answer and bring a human into the conversation.
No answers from AI-model's knowledge
Sarrai isn't allowed to say anything that isn't in your knowledge base. The underlying LLM AI model cannot use its own knowledge of the world.
"I don't know" is a valid answer
If Sarrai can't find a matching answer, it says so honestly and brings in a human. Those answers improve the knowledge base via the approval inbox.
Every answer comes with a source citation
Every answer Sarrai AI gives is accompanied with a source citation. No black box: you can always check which page Sarrai based its answer on.
A made-up answer is worse than no answer at all
A chatbot that always answers seems more impressive than one that sometimes stays silent. But a hallucinated answer can damage the trust your customer has in your company.
That's why it doesn't matter how many questions Sarrai answers, but how many customers were genuinely helped. If it doesn't know the answer, a human is automatically involved in the conversation to ensure a smooth customer service experience.
And when that human answers the question, your knowledge base is updated with the right information. That way Sarrai gets better every day, without you having to put hours of time into it yourself.
Try it out for yourself
Curious how Sarrai answers your customers' questions? Register for free and find out or book a demo with us. We'll gladly take you through it!
