Abstract: Systems and methods for generating an optimized prompt using a language model are disclosed. A query is received at an application. A description is generated for the query based on information extracted from the query. The description is then used to identify a top-k most similar prompt from a prompt library. An optimized prompt is generated at the language model based on the description and the top-k most similar prompts. An optimized response is generated based on the optimized prompt. An evaluation prompt including the optimized response is generated. The evaluation prompt includes instructions to compare the optimized response to a non-optimized response based on the query. A rationale is generated indicating the results of the comparison. The results of the comparison may be interactive.

Abstract: A proactive execution system receives messages or other information from a plurality of different information channels. The proactive execution system automatically identifies messages that include a request for a user to perform a task. The proactive execution system then automatically generates a plan for executing that task and calls a plan execution system, with the plan, to perform the task. The proactive execution system receives a result from the plan execution system and generates an output indicative of that result, for access by the user.