ARCHER: deterministic orchestration lets a self-hosted open-weights model reach 97.8% of frontier accuracy at a quarter the cost.

ARCHER is a test-driven multi-agent program-synthesis harness for building-compliance checking. Evaluating six harnesses of increasing agentic sophistication across four backbone models, deterministic orchestration won for every backbone, improving mean union accuracy 82% over naive single-pass prompting. Harness design, not model tier, closes most of the gap. That's the whole argument for data-sovereign agentic workflows in one result.