JevMade hello@JevMade.com
← Back to guides

JevMade field notes / Policy walkthrough

Filter dangerous messages sent to and from an AI assistant

This guide explains how to check messages sent to and from an AI assistant for harmful content. It shows how to score risks and decide whether to block a message, allow it, or ask a person to review it.

Original by TypeSafe AIGuardrails

Listen to this guide

JevMade’s plain-English explanation

0:00 /

AI narration

Credits

“Guardrails for LLMs” by TypeSafe AI. Read the original source.

This expanded guide is an AI-narrated adaptation prepared by JevMade. It expands the source’s essential ideas, examples and caveats in JevMade’s own words and is not a word-for-word reading. The synthetic voice does not imitate the author or imply their endorsement.

Our summary

People use this method to screen incoming questions and outgoing answers for dangerous topics. For example, it checks if a user asks for medical advice or help with a crime. This helps prevent the software from causing real-world harm.

The filter uses Jev, an AI tool that chooses from options rather than writing an answer. It reads a message and estimates the chance that it breaks a rule. The software then uses these scores to block, allow, or send the message to a human.

This setup is useful for developers who want to adjust how strict their safety rules are. However, this filter is not a perfect security wall. Cleverly written hostile text can trick the scoring tool, so a person still needs to check uncertain messages.

Key takeaways

  1. Score the danger of a message first, then use a separate rule to decide what to do.
  2. Test how different strict and relaxed rules handle the exact same user messages.
  3. Send confusing or borderline messages to a human for review instead of just blocking them automatically.

Using an AI tool to filter text is not a completely secure boundary. Hostile messages can still influence the software and change how it sorts the text.

TypeSafe cookbook · Source reviewed

Read the original guide Opens the author’s site in a new tab.