sunbow.ai
What we do Research Team Careers Contact

Research.

We publish notes on training, evaluation, and deployment for specialist models that improve inside real production workflows.

BYO SWE-grep: automatically train blazing-fast search sub-agents on your knowledge base Search sub-agents that learn the structure of your internal knowledge for fast, reliable retrieval. Research Nov 11, 2025 Purpose-built LLMs for dental note-taking Frontier-style reasoning performance at a fraction of the latency. Case study Nov 5, 2025 Lumina: building self-improving evaluation through customer-in-the-loop refinement An adaptive evaluation engine that learns to judge like a subject matter expert. Research Oct 30, 2025 Attention-based attribution: what your model is actually looking at Interpretable signals for understanding model behavior. Research Oct 28, 2025 Upweight the strategy, not the tokens Rationale-guided training teaches the why, not just the what. Research Oct 28, 2025 Robust, sample-efficient SFT with prompt mutations Low-divergence prompt variation for better performance at lower cost. Research Oct 27, 2025 Training loss predicts evaluation performance A practical evaluation signal for non-verifiable tasks. Research Oct 27, 2025
Back