foundry-evaluation

End-to-end, self-paced Microsoft Foundry labs in English and Korean: build AI agents with Agent Framework, RAG, Azure AI Search, Foundry IQ, and MCP; explore workflows, evaluation, hosted deployment, observability, red teaming, and GitHub OIDC CI/CD.

Self-paced Microsoft Foundry evaluation labs with English/Korean guides: evaluate AI answers, improve prompts, and validate RAG using Azure AI Search, Foundry IQ, calibrated LLM judges, and fresh holdout tests.