Insight for: Feature request: Add evaluation metric for comparing different approaches

The current development cycle for gbrain is bottlenecked by a lack of empirical validation. Relying on 'vibes' for tuning complex retrieval pipelines—specifically hybrid search parameters and embedding model selection—is unsustainable for production-grade agents. The proposed evaluation harness is a critical maturity milestone. By implementing a ground-truth schema and automated metrics (nDCG, MRR), the project moves toward a repeatable optimization loop. This is a prerequisite for integrating advanced techniques like DSPy-based prompt tuning. For the broader market, this signals that gbrain is shifting from a prototype to a robust infrastructure layer where retrieval performance can be quantified and compared against competing architectures.