The software company also made enhancements to the system’s GenStudio, GenRuntime, and GenUX components
Intuit describes Workbench as a new foundational component to the OS in includes LLM Leaderboard, a tool for quickly identifying the best large Large Language Models for specific uses. It offers model cards to help technical and non-technical members of product development teams understand the context, performance, and applications for which an LLM may be the best match.
In addition, there is Prompt Management, a tool to help developers create, iterate, and deploy prompts faster throughout the GenAI development process via a systematic way to store, version, retrieve, manage and templatize prompts.
Another new tool is Evaluation Service for evaluating LLM and GenAI application performance (quality, latency, cost) using a wide range of services integrated into existing workflows—and augmented with manual testing—so developers with any level of GenAI proficiency can build customer experiences.