Search That Works

Retrieval, end to end. Deep dives from building PreciseSearch: component selection that survives fine-tuning, learned sparse weights, distilled rerankers — and the stack-level tuning where the real headroom lives.

2 posts

Search That Works

vstackai-law-1: a best-in-class legal embedding model.

Announcing our embedding model for legal retrieval: top of the MTEB law leaderboard, a 32,000-token context, multilingual coverage, and roughly 3x the accuracy per dollar of the nearest legal-domain rival.

legal·6 min·Dec 2024

Search That Works

Component benchmarks lie. Tune the stack.

A ten-point component lead all but disappeared in the stack that shipped. The product boundary, not the leaderboard, is where the decision belongs.

retrieval·9 min·Jun 2026