Make auditable rule-based decisions with RAG-written explanations
A Rete rule engine decides loans, fraud and triage cases, then RAG over policy documents has an LLM explain the verdict, with an MCP server available.
Done withClaude
- What they did
- The page describes a design in which a Rete rule engine makes the decision, so it is repeatable and auditable. Retrieval-augmented generation over your own documents then supplies the reasons behind the verdict. The source text I could read is only a short description, with no setup steps or details of agent actions.
- How it went
- The source states no results, numbers or limitations. It only describes the split in which rules decide what happens and retrieval explains why.
- Worth knowing
- The fetched page held only a meta description, so check the site directly for setup, MCP details and costs.
Try it yourself with Claude Code
Build a small rule-based decision engine for [use case, e.g. loan approvals] using the rules in [policy document or list of rules]. For each case I give it, output the decision, the exact rules that fired, and a plain-English explanation grounded in quotes from the policy document. Done means it correctly handles these [5] sample cases and I can review the audit trail for each.
Discussion on HN · Sep 22, 2026
Five of these in your inbox every morning
The best things people got an AI agent to do, each with the prompt to try it.
More like this
- GitHub Copilot
Run a solo company with eight agent departments
A founder set up CEO, CFO, COO, lawyer, accountant, marketing, CTO, and improver agents that share memory and consult each other.
Revise courses from student evaluation feedback
A professor had Claude Code summarize course-evaluation PDFs, filed themes as GitHub issues, and used agents to revise his security course and two others.
Reconcile bank statements with invoices
Cowork cleaned vendor names, categorized expenses, matched invoices to transactions, flagged missing ones, built an Excel file and renamed invoice files.
Turn Notion PRDs into scoped Linear tickets
Devin's docs describe reading a Notion PRD to create Linear tickets, producing implementation plans for a backlog, and posting customer health summaries to Slack.
- Custom agent
Contact job candidates for initial HR screening
A job seeker reports an AI agent calling and emailing them for a first HR screening.
Learn personal scripts from a tools folder
Claude Cowork read a folder of personal scripts for email, CRM, research and drafting, added them to memory, and carried the capabilities to a new interface.