LLM

Build a serverless AI chatbot on Amazon Bedrock with streaming, RAG and real cost controls like model routing and prompt caching.

Learn to use every Mistral AI feature like a pro, from models and Mistral Vibe to knowledge bases, MCP servers, skills and custom agents.

Learn how to integrate Mistral Codestral in Visual Studio Code using the Mistral Studio API for cloud-based access or LM Studio for offline use.

Explore TOON, a lightweight alternative to JSON that cuts AI token usage and the carbon footprint of IT systems, and see how the two formats compare.