# Elsa AI Layer #### **AI agents** AI agents are constantly engaged in the following activities: * Monitoring and adapting to changing conditions in the environment * Influencing environmental circumstances through implemented actions * Employing logical reasoning and problem-solving to understand perceptions * Making predictions based on their deductions * Deciding on actions while anticipating their outcomes #### **LLM Models** Elsa AI Automata uses pre-trained language models (LLM) to: * Support AI agents when a specific query needs to be addressed. * Provide an interactive and personalized user experience by understanding and processing a wide range of inquiries. * **RAG (Retrieval-Augmented Generation)**: Elsa AI layer leverages RAG models to enhance the generative capabilities of the AI. This supports the creation of more accurate, contextually relevant responses that cater to user queries and intents, thereby improving the overall user experience. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.heyelsa.ai/architecture/elsa-ai-layer.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.