build-evaluated-ai
Build or review AI features and MCP interfaces with evaluation and authority boundaries. Use for model/framework selection, prompts, structured output, Gemini, ADK or LangChain/LangGraph, optional transcription, standalone FastMCP tools and protocol verification.
Pinned to revision ff9c5ddc5a90, so it is the text this page describes rather than whatever the author pushed since.
Files
Every link opens the file at its source, pinned to the revision this page describes.