SGScott Griffithsinprimevector.hashnode.dev·Apr 23 · 5 min readTesting AI Agents Like Code: the `oa test` HarnessYou wouldn't ship code without tests. But most AI agents ship with nothing — a handful of manual prompts in a notebook, a screenshot of "it worked once," and a prayer that production inputs don't look00
SGScott Griffithsinprimevector.hashnode.dev·Apr 20 · 5 min readComposable Agent Specs: Spec Delegation and the OAS RegistryMost agent frameworks solve reuse the way libraries do: write a class, import it, hope the abstractions line up. That works inside one codebase. Between teams or across organisations? It breaks down f00