Discovered · unverified
ai·rete·rag
ai·rete·rag splits deciding from explaining. The verdict comes from a Rete production-rule engine — deterministic, reproducible, and traceable to the exact rule that fired, with salience deciding which rule wins when two disagree. Only then does an LLM run, grounded by retrieval over your own policy documents, to render that verdict into prose that cites real policy text. The model never decides anything, so an explanation can't invent a threshold your rulebook doesn't have. Eight tools cover the whole loop: hand it a written policy and get back draft rules that cite the sentence each one enc
Check the source before connecting.
Vendor ownership, pricing, documentation, and execution are not verified for this discovery record. Appearing in the official MCP registry does not mean this server is vendor-owned or tested.
Relevance and review status.
Awaiting triage. Method: not yet classified.
Task signals: commerce, e-commerce.
Setup and documentation.
No verified installation steps or callable endpoint are supplied by this discovery record. Follow the original repository or directory entry to inspect current setup instructions, permissions, and authentication.
Source receipts.
- smithery · Observed 2026-10-17
Discovery ID: a9c50cbeddbaa7e40e89. Snapshot: 2026-10-17. Read this record as JSON · Full discovery dataset.
Submit primary documentation for review · Connect your agent to GTMMCPs