Canonical: https://botbento.com/usecases/explain-rule-based-case-decisions-with-cited/
Format: Markdown representation of the public HTML page.

# Explain rule-based case decisions with cited policy passages

[Operations](https://botbento.com/usecases/ops/) · Intermediate

Evaluate case facts against fixed rules, then draft a cited rationale

An AI bot reviews submitted case facts, applies a fixed set of policy rules to reach a verdict, then retrieves relevant policy passages and writes a plain-English rationale citing those passages. The verdict comes only from the rules; the explanation cannot change it.

## Quick answers

**What does it do?** Evaluate case facts against fixed rules, then draft a cited rationale. Result: Cited decision explanation.

**What does it need?** Tools: Docs, Database. Intermediate: some setup. The prompt includes an approval step.

**How do I run it?** When something happens: New case submitted. Copy the prompt below into a bot in BotBento.

## How it works

1. When something happens: New case submitted
2. Then: Evaluate rules and retrieve policy
3. Result: Cited decision explanation

## Prompt to start with

```text
You are an explanation bot for rule-based decisions. When a case arrives, load its facts and the current rule set. Evaluate every rule in order and record which conditions pass or fail. Take the verdict only from the rule evaluation. Retrieve only policy passages that match the fired rules and cite them in a short rationale. Never alter the verdict. Do not send, post, pay, delete, or contact anyone without the user's explicit approval; queue any such action for review.
```

## Tools it uses

Docs, Database

## Works with

BotBento

## Tags

decision-audit, policy, explainability, rules, retrieval

## Source

[Show HN: AI·rete·RAG – a Rete rule engine decides, RAG explains why](https://news.ycombinator.com/item?id=49803683) — Hacker News · checked 2026-11-13

Summarized in our own words. Any results described there are the authors’ own, not measured by BotBento.

Verified 2026-11-13: passed every automated gate and a second-model review (kimi-code/k3.1-pro). Automated, not human review. [How verification works](https://botbento.com/usecases/verification/)

By BotBento Editorial · Added 2026-11-13 · Updated 2026-11-13 · [Suggest a correction](https://botbento.com/contact/)

## Related use cases

- [Fraud rule drift review and variant selection](https://botbento.com/usecases/fraud-rule-drift-review-and-variant-selection/) — Check rule performance, spot drift and propose the best variant
- [Internal chat agent that scopes every request to the person asking](https://botbento.com/usecases/internal-chat-agent-that-scopes-every-request/) — Each request runs under the asker's own permissions, not a shared key
- [Legislative bill parser and neutral summary tracker](https://botbento.com/usecases/legislative-bill-parser-and-neutral-summary-tracker/) — Ingest complex legislative filings to produce plain-language policy overviews
