The presenter delves into advanced concepts, emphasizing the importance of time series in campaigns using bot hierarchies. They highlight the collection and branching of surveys based on user feedback, and the use of generative AI. The exploration and configuration of survey results, including filtering and splitting based on attributes, are demonstrated. The creation of custom dashboards with device data is introduced. The talk also touches on sustainability and green IT initiatives.

Join us as John teaches us the "Top 10" tips and tricks for more effective searches in Sumo Logic.

An LLM differs from a function in that it takes output and imputes, or infers, a function and its arguments. We first consider how this process works within Selector for an English phrase converted to a query. We then step through the design of Selector's LLM, which relies on a base LLM trained with English phrases and SQL translation, then fine-tuned, on-premises, with customer-specific entities. In this way, each of Selector's deployments relies on an LLM tailored to the customer at hand.

Selector translates English phrases to SQL queries through the use of an LLM. Each SQL query includes the table, or data set to be searched, along with filters, or conditions which prune the search results. We walk through a number of SQL queries and sample search results, before considering the LLM-based translation of a sample English phrase processed by Selector.