Pillar Guide·4 min read
Every Search API passed. That was the useful result.
All three Search APIs passed 27 of 27 retrieval attempts. The tie exposed why pass rates are guardrails, not product rankings.
Topic Cluster · 5 articles
Search APIs
Benchmarks, implementation notes, and reproducible findings about Search APIs used by coding agents.
Search APIs·6 min read
How we benchmark Search APIs without grading vibes
A technical walkthrough of the protocol, normalization layer, evaluator, artifacts, and compromises behind our Search API benchmark.
Search APIs·4 min read
Publication dates are metadata, not a search-quality score
Date coverage varied from 33% to 100% in our Search API run. Here is why that matters for some agent tasks and misleads in others.
Search APIs·4 min read
We benchmarked three search APIs for coding agents
Exa, Perplexity Search, and Parallel Search all passed our retrieval test. The useful differences appeared in latency, metadata, onboarding, and integration surface.
Search APIs·3 min read
What coding agents need from Search API results
Titles and URLs are not enough. Coding agents need source rank, snippets, dates, stable shapes, and errors they can evaluate.