# Technical Architecture 1. **Off-chain Server:** NBT operates an off-chain server that hosts the built-in library of tools and frameworks for AI model training. This server provides users with access to a wide range of resources, including software packages, datasets, and pre-trained models, without the need to download or install anything locally. By centralizing these resources on the server, NBT simplifies the process of accessing and utilizing computational resources for AI model training. 2. **API Integration:** NBT offers API integration with popular deep learning frameworks such as TensorFlow, PyTorch, and Keras, allowing users to seamlessly integrate their existing workflows with the platform. Through these APIs, users can easily provision resources, upload datasets, initiate training jobs, and monitor progress, all within their preferred development environment. --- # 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://neuralbyte.gitbook.io/neuralbyte-erc/introduction/technical-architecture.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.