1 post tagged #reflect_llmschema.
#reflect_llmschema
In the AI agent era every tool you expose to Claude/GPT needs a JSON-Schema description. Today you write it by hand next to the C++ function. With C++26 reflection, a single consteval call emits the tool-use JSON at compile time — parameter names, types, docstrings, dispatch, done.
// We use Google Analytics to understand which posts get traction and how the wro.cpp community grows. Anonymised, no ads, and you can decline -- the site works either way.