Tag
A technical essay exploring the "push ifs up, fors down" programming idiom from TigerBeetle's Tiger Style and matklad's blog, extending it to SQL query optimization (early projections, late joins) and connecting it to functional programming and category theory, while discussing its limits.
The article argues that reliable AI agents require deterministic control flow and programmatic verification in software, rather than relying solely on complex prompt chains.
AgentSPEX introduces a domain-specific language for specifying modular, interpretable LLM-agent workflows with explicit control flow, state management, and a visual editor, outperforming existing Python-coupled frameworks.
This article systematically reviews AI Agent architecture and engineering practices, covering control flow, context engineering, tool design, memory, multi-agent organization, evaluation, tracing, and security. It is based on the OpenClaw implementation and emphasizes the critical role of Harness (testing and validation infrastructure) for system stability.