AI・機械学習
Show HN: AI·rete·RAG – Reteルールエンジンが決定し、RAGが理由を説明
Show HN: AI·rete·RAG – a Rete rule engine decides, RAG explains why (ai-rete-rag.com)
要約
このプロジェクトは、監査が必要な意思決定（融資、不正検知、臨床トリアージなど）にLLMを直接使用するのではなく、まず純粋なPython ReteエンジンでYAMLルールに基づいて事実を評価し、その決定をLLMがRAG（Retrieval-Augmented Generation）を用いてポリシー文書から引用して説明する仕組みを提供します。これにより、決定の再現性と説明責任が保証されます。
全文翻訳
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.<p>It runs the two in series instead:<p>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.<p>A few things that went further than I expected:<p>- 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.<p>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`.<p>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.<p>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?