RESERVE features self-discoverable onboarding for Large Language Model based agents. Here is how it works.<\/p>\n\n\n\n
LLM based Agents use a number of techniques to leverage software programs. Notable software and related APIs are often already part of an LLMs learning. The FRED\u00ae API is a good example as Claude, OpenAI, Gemini, and other major AI platforms are well aware of this API and how it works. For other software programs, LLM based agents will often use a number of techniques to get up to speed on a piece of software. These include crawling online documentation, open-source repositories, and even using user accessible documentation including auto-completion features of command-line interfaces. RESERVE takes a much more robust approach.<\/p>\n\n\n\n
RESERVE has an entire command structure of ONBOARDING that emits machine consumable JSON allowing LLMs to onboard. The json features context, intent, examples, workflow guidance, and even “gotchas”. Here is how it works:<\/p>\n\n\n\n
A user can invoke LLM onboarding as follows:<\/p>\n\n\n\n