call-workflow
openai

AI Security and Safety Guardrails (OpenAI)

Artificial IntelligenceIntermediate

Overview

Use this flexible AI Utility Callable to enforce safety and security best practices for external facing AI Applications. The only setup required are your OpenAI credentials.

Prerequisites

To implement this AI powered automation, you will need:

  • API credentials for OpenAI Note: while this automation uses script steps, you do not need to understand or write scripts to benefit. If you want to learn more about what the script steps do we included comments in the code so you could reverse engineer what is happening if you want to. **

Getting Live

**Mandatory steps: **

  1. Map the source text that you want to evaluate Optional steps (to refine your evaluation job):
  • Include example Source Text and whether it should be flagged or not