We present Agentic AI Translate, an agentic translator prototype that operationalises the thesis of Yamada (forthcoming) -- that the metalanguage of Translation Studies has become an instruction code for generative AI. The system replaces the dominant text-in / text-out paradigm of machine translation with a four-stage agentic cycle (Identify -> Prompt -> Generate -> Verify), preceded by an interactive specification phase in which the user composes -- through model-assisted dialogue -- a structured translation brief grounded in skopos theory, register, audience, and genre conventions. The verification stage adopts the GEMBA-MQM error-span protocol (Kocmi & Federmann, 2023) for evidence-grounded scoring, and document-level coherence is preserved through a DelTA-lite memory of proper nouns and a running bilingual summary, after Wang et al. (2025). We describe the philosophical motivation, the architectural commitments, the four reference-material categories the system consumes, and the principal design tensions the architecture makes explicit. Empirical validation is left for future work; the contribution here is conceptual and architectural -- an executable embodiment of the position that translation in the GenAI era is communication design, not text conversion.

翻译：我们提出代理AI翻译（Agentic AI Translate）——一个代理式翻译器原型，它实现了Yamada（即将出版）的论点：翻译研究的元语言已成为生成式AI的指令代码。该系统取代了机器翻译中占主导地位的“文本输入/文本输出”范式，采用包含四个阶段的代理循环（识别→提示→生成→验证），并在其之前增设交互式说明阶段。在此阶段中，用户通过模型辅助对话，基于目的论、语域、受众和体裁惯例构建结构化的翻译要求。验证阶段采用GEMBA-MQM误差跨度协议（Kocmi & Federmann, 2023）进行基于证据的评分，并通过DelTA-lite专有名词记忆和运行时双语摘要（Wang等人，2025）保持文档级连贯性。我们阐述了哲学动机、架构承诺、系统消费的四种参考资料类别，以及该架构所揭示的主要设计张力。实证验证留待未来工作完成；本文的贡献在于概念与架构层面——将“生成式AI时代的翻译是沟通设计而非文本转换”这一立场付诸可执行的实现。