Log: news, updates, and research from Zaira Labs

Launch notes, research, and shipping updates from Zaira Labs. RSS

launch 2026-07-06

Zaira Labs is live

Trust signals for agents: the Zaira Standard, an open agent-readiness spec, and the Zaira Guide, structured tool decision data for coding agents.

research 2026-07-21

Improvised retrieval in constrained coding agents: an initial study

A Claude Code release capped web searches per session. Agents that hit the cap kept searching by constructing query URLs against keyless search endpoints and fetching the results. A 72-run study across four Claude models finds the behavior general: workaround rates reach 100% at the frontier tier and 100% on any task that cannot be completed without retrieval. No run fabricated an answer.

update 2026-07-20

The Best Practices Guide is now an Agent Skill

building-for-agents is a free Agent Skill that applies the Zaira Standard's guidance inside your repo: classification, gap review, and the trade-offs stated. Apache-2.0, no gate.

launch 2026-07-08

The Zaira Guide: structured developer tool intelligence AI agents can trust

The Zaira Guide tells AI coding agents which developer tools to use and when. 900+ tools, 60 categories, verified evidence, served via web, API, and MCP.

launch 2026-07-07

What 'agent-ready' actually means: introducing the Zaira Standard v0.9

Developer tools have a new class of customer. We wrote a 71-criteria open spec, then ran its Base criteria against 900+ tools. Fewer than half meet the bar.