摘要：通用大型语言模型（LLM）日益被用于回答宗教问题，但对于伊斯兰内容而言，它们存在两项严重风险：事实捏造（虚构《古兰经》经文或圣训）以及细微的价值观失准。我们提出 Ansari，这是一款已部署、以检索为基础的伊斯兰 AI 助手；自 2023 年 6 月以来，它已在 25 种以上语言中处理超过 14 万次对话。Ansari 围绕一个 Agent 式检索循环构建：使用工具的语言模型会针对经过认证的伊斯兰语料发起搜索——包括《古兰经》、圣训合集、多卷本教法学（fiqh）百科全书以及经注（tafsir）资料——并且仅依据其检索到的内容作答，同时附上引文以供验证。我们描述了该系统的架构（Agent 循环、检索工具、语料库，以及编码编辑与神学政策的系统提示词）、其多平台部署方式（Web、移动端、WhatsApp，以及作为 Model Context Protocol 服务器和 Agent Skill 的部署），并分析了 14 万次真实对话揭示的穆斯林用户实际使用此类工具的方式。我们报告了多项互补评测的结果——包括在获得认证的机构考试中的零样本表现、斋月期间的人类评分验证，以及两项独立、外部运行的基准测试；Ansari 目前在公开 IslamicMMLU 排行榜上领先于前沿模型，并且在伊斯兰法律推理（IslamicLegalBench）方面具有竞争力，同时能有效抵抗错误前提——并总结出可推广至伊斯兰教以外、任何信仰或价值观敏感型 LLM 部署的经验：溯源是必要的，但并不充分；系统提示词既是神学产物，也是技术产物；而模型形成过程中缺乏社区参与，仍然是一项难以弥补的缺口。

Abstract:General-purpose large language models (LLMs) are increasingly used to answer religious questions, but for Islamic content they carry two serious risks: factual fabrication (inventing Qur'anic verses or hadith) and subtle value misalignment. We present Ansari, a deployed, retrieval-grounded Islamic AI assistant that has handled more than 140,000 conversations across 25+ languages since June 2023. Ansari is built around an agentic retrieval loop: a tool-using language model issues searches against authenticated Islamic corpora -- the Qur'an, hadith collections, a multi-volume jurisprudence (fiqh) encyclopedia, and exegetical (tafsir) sources -- and answers only on the basis of what it retrieves, with citations attached for verification. We describe the system's architecture (the agent loop, the retrieval tools, the corpora, and the system prompt that encodes editorial and theological policy), its multi-platform deployment (web, mobile, WhatsApp, and as a Model Context Protocol server and an Agent Skill), and what 140,000 real conversations reveal about how Muslims actually use such a tool. We report results on several complementary evaluations -- zero-shot performance on accredited institutional exams, a human-rated validation during Ramadan, and two independent, externally run benchmarks on which Ansari currently tops the public IslamicMMLU leaderboard ahead of frontier models and is competitive on Islamic legal reasoning (IslamicLegalBench) while strongly resisting false premises -- and draw out lessons that generalize beyond Islam to any faith- or values-sensitive deployment of LLMs: grounding is necessary but not sufficient, the system prompt is a theological as much as a technical artifact, and the absence of community in how models are formed remains a hard gap.