Auto-Arch Tournament vs Waydev

Auto-Arch Tournament is an autonomous research system where an AI agent iteratively proposes, implements, and validates microarchitectural improvements to a RISC-V CPU. Starting from a standard 5-stage pipeline, the loop runs hypotheses in parallel, each going through formal verification (53 symbolic checks), cycle-accurate simulation, multi-seed FPGA place-and-route, and CoreMark CRC validation. Only hypotheses that beat the current champion get merged; everything else gets discarded. Starting from 301 iterations/second, the system hit 577 iter/s (+92%) across 73 attempts in 9.8 hours — producing a design 26% faster and 40% smaller in LUTs than the baseline. The insight the author drives home is that the real innovation isn't the AI agent — it's the verifier. The orchestrator is hardcoded to prevent agents from manipulating their own evaluation gates, a simple but critical design constraint that turns a creative process into a trustworthy one. Without a rigorous verification harness, agent-driven optimization becomes a confidence trick. This is early but fascinating proof that AI-driven hardware design loops can produce commercially meaningful gains. The repo uses Claude Code or Codex as the coding agent, SystemVerilog for the RTL, and standard open-source EDA tooling (Yosys, nextpnr, Verilator). It's a compelling template for anyone building agentic optimization loops where correctness matters.

Waydev has relaunched as the measurement layer for AI-written code, letting engineering teams track which AI agent wrote which code, tokens consumed per PR, cost-per-shipped-line, and acceptance rates — with a unified comparison dashboard across GitHub Copilot, Cursor, Claude Code, and other AI coding tools. Founded in 2017 and backed by Y Combinator (W21), Waydev spent nine years building engineering analytics infrastructure. The pivot to AI SDLC measurement uses that existing integration surface (GitHub, GitLab, Jira, Linear) to add agent attribution metadata on top of existing flow metrics. The result is the first tool that can answer 'our team spent $4,200 on AI coding tools last month — which $1,000 was actually worth it?' With enterprise engineering budgets now routinely including five-figure monthly AI tooling costs and no standardized way to measure output quality by tool, Waydev's timing is sharp. The YC pedigree and existing customer relationships mean this isn't starting from zero — they're adding a new measurement layer to existing installed base.