Speaker
Description
AI-assisted coding is gaining significant traction at the EuXFEL. Among all LLM use cases facilitated by the facility’s enterprise foundation model provider, coding-related tasks have the highest token usage. However, there are still unanswered questions and evolving guidelines regarding AI-assisted and agentic coding. These include determining where we should embrace, tolerate, and avoid AI-generated code, how much we expect AI-coding to become the new norm, and how we can integrate tools that can quickly produce hundreds, if not thousands, of lines of code into code review and testing processes.
In this contribution, we will report on a condensed AI code camp scheduled for June. This intensive, hands-on exercise will involve a small cross-functional team with diverse experience in AI-driven coding. The team will examine, address, and challenge the aforementioned questions. The objective is to further develop a behavior tree-driven graphical sequencer for the facility, which is currently in a prototype stage. The task is to accomplish this within five days, taking advantage of agentic coding opportunities as much as possible.
