Teaching AI our testing standards helped us turn risky refactors into routine improvements. Here’s how.

Jerridan Quiring

Staff Software Engineer

Instead of using retrieval to improve generation, we use generation to improve retrieval. Sounds recursive? It is. And it works.

Christos Melidis

Staff Machine Learning Scientist

Here's how we use the LLMs to impact customer service, and what training processes we employ to ensure effective and secure deployment.

Sarah Fox

AI Content Specialist

Hallucinations in AI occur when an AI model generates information that is inaccurate or misleading but presents it as if it were true. For businesses relying on AI customer service, false or misleading information can erode customer trust and lead to operational inefficiencies.

Yochai Konig

Vice President, Machine Learning & AI

There’s no magic solution to eliminating hallucinations, but there are ways to circumvent them. Here's everything you need to know about grounding and AI hallucinations.

Gordon Gibson

Director, Applied Machine Learning

Why does AI hallucinate? Here's some clear and effective ways to prevent, detect, and correct AI hallucinations.

Gordon Gibson

Director, Applied Machine Learning

There are challenges to building a chatbot for customer service that provides high quality conversations and resolutions. Find out how we overcome them.

Bénédicte Pierrejean

Senior Machine Learning Scientist

A new metric is now the North Star for customer support: Automated Resolutions. Here's how to optimize for it.

Arnon Mazza

Staff Machine Learning Scientist

We're revealing the best practices Customer Success managers use to effectively implement generative AI in customer service automation.

Raj Ravichandiran, Robert D'Ippolito, and Andre Marcelo-Tanner

Engineering Team