AI·rete·RAG – a Rete rule engine decides, RAG explains why
Show HN: AI·rete·RAG – a Rete rule engine decides, RAG explains why
我们发现了什么
Show HN: AI·rete·RAG – a Rete rule engine decides, RAG explains why. Hi HN, I built ai·rete·rag because I kept seeing teams put an LLM in charge of decisions that need to be auditable (lendi
- 来源:Hacker News(发现于 2026-09-23)
- 证据等级:D · 发现产品或需求信号,暂未获得可核验的商业证据。
- 商业模式:待核验
- 主题:独立产品
- 初筛评分:19.1/100 · 收录 1 次
证据,比故事更重要。
规则清洗与初筛,未经人工商业核验。原文语境、实际客户和付费情况仍需自行验证。
引用与数字披露
来源类型(原作者自述/第三方测算/媒体转引)需采集端标注,本版尚未落字段。
- 作者
- 未标注
- 抓取日期
- 来源类型
- 未标注
- 币种
- 未标注
- 口径
- 未标注
- 披露主体
- 未标注
- 披露日期
- 未标注
中文辅助译文(全文)
你好,HN,我之所以构建 ai·rete·rag,是因为我不断看到团队把 LLM 放在那些需要可审计性的决策(贷款、欺诈、临床分诊)位置上,然后在事后硬加上所谓的"护栏"。ai·rete·rag 以串联的方式依次运行以下两部分:1. 一个纯 Python 的 Rete 引擎根据 YAML 规则对你的事实进行评估。最终判定完全由此得出。相同的事实,相同的判定,每次一致,并采用基于显著性的冲突解决机制。2.RAG 从你自己的政策文档中检索相关段落,然后由 LLM 用通俗易懂的语言撰写关于已做出决策的解释,并引用这些段落。LLM 不能更改该判定。一些超出我预期的特性:- 规则是一个图,而非扁平的列表:支持嵌套的 all/any/not,并且规则可以断言供其他规则使用的事实(前向链推理)。决策追踪会展示因果链。- 审计模式会记录评估的每条规则,包括未触发的规则,逐条记录条件,并附上规则集的快照以便重放。- 规则可以引导检索(一条被触发的规则会缩小需要搜索的文档范围),而检索到的文本可以转化为引擎所使用的事实。- 非技术背景的作者可以在可视化编辑器中构建规则,或粘贴政策文档以获取带引用的 LLM 起草规则。草稿未经审核绝不会保存。工程师仍可使用 YAML。落地页提供无需注册的实时演示(涵盖 8 个演示领域:贷款、欺诈、临床、保险、法律、运营、电商、区块链)。还有一款 MCP 服务器,使 Claude 等智能体可以像工具一样调用 /decide:uvx ai-rete-rag-mcp。先说在前面:这是一款带有免费层的托管产品。
MCP 客户端是开源的(MIT 协议,github.com/zaharajabeen13-create/ai-rete-rag-mcp);引擎和平台目前不是开源的。我尤其希望听到曾经需要向监管机构或审计师解释自动化决策的人的心声:他们究竟要求了什么?
译文由上游机器翻译生成,可能有误;判断请以英文原文为准。
英文原文(来源本站未改写)
Hi HN, I built ai·rete·rag because I kept seeing teams put an LLM in charge of decisions that need to be auditable (lending, fraud, clinical triage), then bolt on "guardrails" after the fact.It runs the two in series instead: 1.A pure-Python Rete engine evaluates YAML rules against your facts.The verdict comes only from here.Same facts, same verdict, every time, with salience-based conflict resolution. 2.RAG retrieves passages from your own policy documents, and an LLM writes a plain-English explanation of the decision that was already made, citing those passages.It can't change the verdict.
A few things that went further than I expected: - Rules are a graph, not flat lists: nested all/any/not, and rules can assert facts that other rules consume (forward chaining).The decision trace shows the causal chain. - Audit mode records every rule evaluated, including the ones that didn't fire, condition by condition, with a snapshot of the rule set for replay. - Rules can steer retrieval (a fired rule narrows which documents get searched), and retrieved text can be turned into facts for the engine. - Non-technical authors can build rules in a visual editor, or paste a policy document and get LLM-drafted rules with citations.Drafts are never saved without review.
YAML is still there for engineers.The landing page has a live demo with no signup (8 demo domains: loan, fraud, clinical, insurance, legal, ops, e-commerce, blockchain).There's also an MCP server, so Claude and other agents can call /decide as a tool: uvx ai-rete-rag-mcp.To be upfront: it's a hosted product with a free tier.The MCP client is open source (MIT, github.com/zaharajabeen13-create/ai-rete-rag-mcp);the engine and platform are not open source right now.I'd especially like to hear from anyone who has had to explain an automated decision to a regulator or an auditor: what did they actually ask for?
这条还缺什么证据?
下面每条都由本条已有字段推出(等级、理由、商业模式、来源次数、是否演示), 本站不生成推测性结论;通用验证方法放在方法论页。
- 可核验的收入或付费证据查官网定价页与付费口径;第三方数据源(如 GetLatka)只作旁证,需标注来源与时点。
- 商业模式未定确认按席位/按用量/授权还是开源托管版收费;开源项目另查 LICENSE 与是否存在付费版。
- 只有单一来源找一手站点或其他渠道是否重复出现同一产品;社区热帖数量不等于商业进展。
通用验证清单(谁有这个问题/谁愿意付费/一个人能交付哪一小步)见我们的筛选方法。