Generative AI Toolkit -- a framework for increasing the quality of LLM-based applications over their whole life cycle
This addresses the need for scalable and continuous quality improvement in LLM-based applications used by millions, though it is incremental as it builds on existing DevOps practices.
The paper tackles the problem of manual, slow, and trial-and-error workflows in developing and maintaining LLM-based applications by introducing the Generative AI Toolkit, which automates configuration, testing, monitoring, and optimization to improve quality and shorten release cycles.
As LLM-based applications reach millions of customers, ensuring their scalability and continuous quality improvement is critical for success. However, the current workflows for developing, maintaining, and operating (DevOps) these applications are predominantly manual, slow, and based on trial-and-error. With this paper we introduce the Generative AI Toolkit, which automates essential workflows over the whole life cycle of LLM-based applications. The toolkit helps to configure, test, continuously monitor and optimize Generative AI applications such as agents, thus significantly improving quality while shortening release cycles. We showcase the effectiveness of our toolkit on representative use cases, share best practices, and outline future enhancements. Since we are convinced that our Generative AI Toolkit is helpful for other teams, we are open sourcing it on and hope that others will use, forward, adapt and improve