An API Schema Describes Vendor Intent, Not Client Behavior
A documented hash in a VK button broke mini-app navigation; comparing three links found the cause where another schema-based hypothesis did not.
I design reliable AI-agent systems for production: tool contracts, memory, HITL, observability, and failure recovery.
I test where agent systems lie to us and to themselves.
A documented hash in a VK button broke mini-app navigation; comparing three links found the cause where another schema-based hypothesis did not.
A timestamp and memory near the start of a 92K-token agent request made every call cold; a stable prefix and cached-token metric made the defect testable.
Why a fresh llama.cpp build still crashed on Blackwell and how native SASS removed the incompatible PTX JIT path.
A slice taken from the wrong end made a multimodal agent receive the oldest images instead of the newest ones.
A minimalist macOS browser picker that routes links to the right browser and learns repeated choices.