Quality vector
Per-result tier + editorial standards + commercial intent + authoritative weight + signals with full reasoning. Read more →
sift
A transparent search-result vectorizer for AI agents.
sift wraps Brave Search and assigns every result a structured quality vector — a 9-level tier, editorial standards, commercial intent, authoritative weight, and signals. Downstream agents receive the augmented SERP plus aggregate metrics (tier distribution, vendor dominance, source diversity) so they can reason about source quality, not just content.
sift does not pre-filter. It surfaces what’s there. The prompt, the tier definitions, and the reasons behind every classification are in source and in the output.
Aggregate vector
SERP-level landscape: tier distribution, diversity entropy, vendor dominance. Read more →
Summary hints
Deterministic meta-observations agents must incorporate when summarizing biased or narrow SERPs. Read more →
Learning loop
Every classification is logged as an observation — the substrate for drift review and prompt refinement. Read more →