Add to Favourites
To login click here
Sierra Technologies Inc. has developed a new benchmark test, 𝜏-bench, to evaluate the performance of AI chatbots in real world settings. The test measures the ability of chatbots to complete complex tasks on behalf of human customer service agents, making them more advanced than previous benchmarks. Sierra’s AI agents have contextual awareness and can perform actions such as opening a ticket for a customer, allowing for self-service interactions. This benchmark is important for successful deployment of AI agents, as other companies are also developing advanced chatbots.
