Qwen Meetup Presentation, Function Calling Harness, 6.75% to 100%
Compiler-driven feedback loops force LLMs into 100% schema compliance on complex types.

The idea is a coding harness (independent of models) natively designed for C/C++ developer workflows.
I'm a C++ dev and do not find claude code work well with C++ toolchain like gdb and perf. The current version has integrations for gdb, clang-tidy, cppcheck, sanitizers, perf, benchmarking, compile DB navigation, Godbolt, symbolization, binary inspection, and decompilation.
It supports Anthropic, OpenAI, Gemini, and self-hosted models. There are editor workflows for VS Code, CLion, emacs, neovim, and cursor.
Compiler-driven feedback loops force LLMs into 100% schema compliance on complex types.
Parallel multi-agent research with thesis mode fights confirmation bias across rounds.
TypeScript only alternative to Instructor: compiler validation forces 100% function calling success.
Prolog-based agent logic beats prompt chaining for real control flow.
Unifies bpftop call counts with perf source-line profiling in one TUI.
Compiler-level validation turns Qwen's 6.75% structured output success rate into 100%.