Search APIs · Pillar Guide
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.
4 min read·
Blog
All Them APIs Blog
Benchmarks, integration notes, and practical analysis of APIs for coding agents.
Search APIs
See allHow we benchmark Search APIs without grading vibes
A technical walkthrough of the protocol, normalization layer, evaluator, artifacts, and compromises behind our Search API benchmark.
6 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.
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.
4 min read
Agent-ready APIs
See allAgent-ready APIs · Pillar Guide
What makes an API ready for a coding agent?
An agent-ready API reduces discovery, authentication, and verification work. Here are the signals we inspect before trusting an integration.
3 min read·
Email APIs
See allEmail APIs · Pillar Guide
How to benchmark a transactional email API without cheating
A reproducible email API benchmark needs a fixed task, fresh workspaces, one send attempt, provider-native evidence, and honest blocked outcomes.
6 min read·
Mailgun vs SendGrid: similar job, different integration surface
Mailgun and SendGrid both send transactional email, but differ in authentication, payload shape, sender setup, test mode, and acceptance evidence.
5 min read
Resend vs Postmark: the important difference is how you test
Resend and Postmark both expose straightforward send APIs, but their test addresses, test tokens, sandbox servers, responses, and idempotency differ.
5 min read